diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed9a49a51fb35949284759ed539779ee5e77339b --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35719c346338ae667399c0a301c4e6473be52af263fb628a65f6ae32d2f7ee7 +size 7098016 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-100/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-100/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb3ea7f9048d38506fcaac21cb3e902769b6af74 --- /dev/null +++ b/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a2d26697636a71d1a256939176e99ebaf4973a8590b8514cad71f084813574 +size 7098016 diff --git a/checkpoint-100/added_tokens.json b/checkpoint-100/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-100/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..599b61af294797a71dc5f9e7fb64cfbc7adfd11e --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6c1a6e0124289aa1b609abb18f3999d2eea982380f1926d4f7564f58bd650b +size 14272762 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..99f772e150567ae2529007c9815aa085fc68cf3f --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ffd2e67a5e106bcbed7941bfeb9076b68a447bab53d273e41d280ee2e05187 +size 13990 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1dd98f7becd38f63ea738f1c4f7e7217c262ae63 --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238808d3e43d57749e77b6f5311a10cf263fadd2a37de54c7eee213d8dc27e07 +size 1064 diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-100/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-100/spiece.model b/checkpoint-100/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-100/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-100/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8eab5f1bc027bc7a7f2143c3c07e2f5c6bc9217c --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,55 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6666666666666666, + "eval_steps": 100, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 491514966835200.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-1000/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-1000/adapter_config.json b/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-1000/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1000/adapter_model.safetensors b/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc74b0dc76ad216524df285e82dba0ce0cb4e42b --- /dev/null +++ b/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30beced01d878e7a36ad3f3035261310d19bf9bb615d3480ffd46ac550b4b9b6 +size 7098016 diff --git a/checkpoint-1000/added_tokens.json b/checkpoint-1000/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-1000/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..568fd66fe4c138ea40a8744b9d814f19988dac40 --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516c59c51e07f2b075a5d6665bd912e343c371a2a7b978d374577e80d8b34d38 +size 14272762 diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba85229b1fbc4309b6b3bcc26e26e9399f6eea15 --- /dev/null +++ b/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa62f413cc398503362a2cd0e320ea0dddbd77764c1e024a5456a7968f8d762 +size 13990 diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f33d735ae580ea115516ff3846bb5f734dac884 --- /dev/null +++ b/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f339bd8276c8e26dbc7484d483a8ac4d5602c7f90ccdbdd545d97392fbbc4f6e +size 1064 diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-1000/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1000/spiece.model b/checkpoint-1000/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-1000/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-1000/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a86d4e41244742693228ee198a43fd1f74a034c4 --- /dev/null +++ b/checkpoint-1000/trainer_state.json @@ -0,0 +1,253 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 6.666666666666667, + "eval_steps": 100, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + }, + { + "epoch": 5.0, + "grad_norm": 0.09571962058544159, + "learning_rate": 0.00012272727272727272, + "loss": 0.0161, + "step": 750 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.08587690442800522, + "learning_rate": 0.00010909090909090908, + "loss": 0.016, + "step": 800 + }, + { + "epoch": 5.333333333333333, + "eval_loss": 0.005752269644290209, + "eval_runtime": 24.7224, + "eval_samples_per_second": 24.269, + "eval_steps_per_second": 3.034, + "step": 800 + }, + { + "epoch": 5.666666666666667, + "grad_norm": 0.07417745888233185, + "learning_rate": 9.545454545454545e-05, + "loss": 0.0152, + "step": 850 + }, + { + "epoch": 6.0, + "grad_norm": 0.08311035484075546, + "learning_rate": 8.18181818181818e-05, + "loss": 0.0143, + "step": 900 + }, + { + "epoch": 6.0, + "eval_loss": 0.00478348508477211, + "eval_runtime": 26.3439, + "eval_samples_per_second": 22.776, + "eval_steps_per_second": 2.847, + "step": 900 + }, + { + "epoch": 6.333333333333333, + "grad_norm": 0.06424418836832047, + "learning_rate": 6.818181818181817e-05, + "loss": 0.0139, + "step": 950 + }, + { + "epoch": 6.666666666666667, + "grad_norm": 0.06728924065828323, + "learning_rate": 5.454545454545454e-05, + "loss": 0.013, + "step": 1000 + }, + { + "epoch": 6.666666666666667, + "eval_loss": 0.00447163125500083, + "eval_runtime": 28.703, + "eval_samples_per_second": 20.904, + "eval_steps_per_second": 2.613, + "step": 1000 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4915149668352000.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-1100/README.md b/checkpoint-1100/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-1100/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-1100/adapter_config.json b/checkpoint-1100/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-1100/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1100/adapter_model.safetensors b/checkpoint-1100/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50566725e111b111068bf8b887e2d955c6dd74ba --- /dev/null +++ b/checkpoint-1100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b797c6afc50c3be27374915466b8df1c4d767a35a175bacb612f777e89cd6fe4 +size 7098016 diff --git a/checkpoint-1100/added_tokens.json b/checkpoint-1100/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-1100/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..38137b765c1531ceb58f1ace05ad09902688ed49 --- /dev/null +++ b/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feec53576c474df782a854003a1824e6acd3b67d501e2e9cccc82169b5ad474b +size 14272762 diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..85147804b89c0d512fa4a53800142d98b3d72b46 --- /dev/null +++ b/checkpoint-1100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a0cdf733ea83ad812b32242bfde199c159738da6e392156d845fb88eeb73cf +size 13990 diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..45d8c0d6afb01777e125e7791b70bf2516f26834 --- /dev/null +++ b/checkpoint-1100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1949ec79a34ffd0e9fb32276adb07b36cc70417c210b9261cb1e27fa261ce2d1 +size 1064 diff --git a/checkpoint-1100/special_tokens_map.json b/checkpoint-1100/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-1100/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1100/spiece.model b/checkpoint-1100/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-1100/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-1100/tokenizer_config.json b/checkpoint-1100/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-1100/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..152035e5c3ce441050d20cd2b80e776632148d47 --- /dev/null +++ b/checkpoint-1100/trainer_state.json @@ -0,0 +1,275 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.333333333333333, + "eval_steps": 100, + "global_step": 1100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + }, + { + "epoch": 5.0, + "grad_norm": 0.09571962058544159, + "learning_rate": 0.00012272727272727272, + "loss": 0.0161, + "step": 750 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.08587690442800522, + "learning_rate": 0.00010909090909090908, + "loss": 0.016, + "step": 800 + }, + { + "epoch": 5.333333333333333, + "eval_loss": 0.005752269644290209, + "eval_runtime": 24.7224, + "eval_samples_per_second": 24.269, + "eval_steps_per_second": 3.034, + "step": 800 + }, + { + "epoch": 5.666666666666667, + "grad_norm": 0.07417745888233185, + "learning_rate": 9.545454545454545e-05, + "loss": 0.0152, + "step": 850 + }, + { + "epoch": 6.0, + "grad_norm": 0.08311035484075546, + "learning_rate": 8.18181818181818e-05, + "loss": 0.0143, + "step": 900 + }, + { + "epoch": 6.0, + "eval_loss": 0.00478348508477211, + "eval_runtime": 26.3439, + "eval_samples_per_second": 22.776, + "eval_steps_per_second": 2.847, + "step": 900 + }, + { + "epoch": 6.333333333333333, + "grad_norm": 0.06424418836832047, + "learning_rate": 6.818181818181817e-05, + "loss": 0.0139, + "step": 950 + }, + { + "epoch": 6.666666666666667, + "grad_norm": 0.06728924065828323, + "learning_rate": 5.454545454545454e-05, + "loss": 0.013, + "step": 1000 + }, + { + "epoch": 6.666666666666667, + "eval_loss": 0.00447163125500083, + "eval_runtime": 28.703, + "eval_samples_per_second": 20.904, + "eval_steps_per_second": 2.613, + "step": 1000 + }, + { + "epoch": 7.0, + "grad_norm": 0.05669340118765831, + "learning_rate": 4.09090909090909e-05, + "loss": 0.0123, + "step": 1050 + }, + { + "epoch": 7.333333333333333, + "grad_norm": 0.06817171722650528, + "learning_rate": 2.727272727272727e-05, + "loss": 0.0126, + "step": 1100 + }, + { + "epoch": 7.333333333333333, + "eval_loss": 0.004406072199344635, + "eval_runtime": 25.9017, + "eval_samples_per_second": 23.164, + "eval_steps_per_second": 2.896, + "step": 1100 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5406664635187200.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-1100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-1200/README.md b/checkpoint-1200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-1200/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-1200/adapter_config.json b/checkpoint-1200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-1200/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1200/adapter_model.safetensors b/checkpoint-1200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed9a49a51fb35949284759ed539779ee5e77339b --- /dev/null +++ b/checkpoint-1200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35719c346338ae667399c0a301c4e6473be52af263fb628a65f6ae32d2f7ee7 +size 7098016 diff --git a/checkpoint-1200/added_tokens.json b/checkpoint-1200/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-1200/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..af43d80c6e5cad6dc36a7837f115189d177fe5ac --- /dev/null +++ b/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:696c856a337232fae312d9edde31a614e14f53b7d2f9f57c54dea8efb6830893 +size 14272762 diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f91008861c5263abc3bb00215f4633b2c080c3c --- /dev/null +++ b/checkpoint-1200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e39748b1efa39a5c7c195bcbfa712350a4a33bb6044081048e2ce4d4454a96 +size 13990 diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1bbab7547db885fa7057788177deeedd26644c3 --- /dev/null +++ b/checkpoint-1200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1896239e3fc1bc6e037b5a247659a5a03ae97b309614655b34585b037e01c174 +size 1064 diff --git a/checkpoint-1200/special_tokens_map.json b/checkpoint-1200/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-1200/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1200/spiece.model b/checkpoint-1200/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-1200/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-1200/tokenizer_config.json b/checkpoint-1200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-1200/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c834a118fe14ded7d06350defb25c0982fb087a5 --- /dev/null +++ b/checkpoint-1200/trainer_state.json @@ -0,0 +1,297 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 8.0, + "eval_steps": 100, + "global_step": 1200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + }, + { + "epoch": 5.0, + "grad_norm": 0.09571962058544159, + "learning_rate": 0.00012272727272727272, + "loss": 0.0161, + "step": 750 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.08587690442800522, + "learning_rate": 0.00010909090909090908, + "loss": 0.016, + "step": 800 + }, + { + "epoch": 5.333333333333333, + "eval_loss": 0.005752269644290209, + "eval_runtime": 24.7224, + "eval_samples_per_second": 24.269, + "eval_steps_per_second": 3.034, + "step": 800 + }, + { + "epoch": 5.666666666666667, + "grad_norm": 0.07417745888233185, + "learning_rate": 9.545454545454545e-05, + "loss": 0.0152, + "step": 850 + }, + { + "epoch": 6.0, + "grad_norm": 0.08311035484075546, + "learning_rate": 8.18181818181818e-05, + "loss": 0.0143, + "step": 900 + }, + { + "epoch": 6.0, + "eval_loss": 0.00478348508477211, + "eval_runtime": 26.3439, + "eval_samples_per_second": 22.776, + "eval_steps_per_second": 2.847, + "step": 900 + }, + { + "epoch": 6.333333333333333, + "grad_norm": 0.06424418836832047, + "learning_rate": 6.818181818181817e-05, + "loss": 0.0139, + "step": 950 + }, + { + "epoch": 6.666666666666667, + "grad_norm": 0.06728924065828323, + "learning_rate": 5.454545454545454e-05, + "loss": 0.013, + "step": 1000 + }, + { + "epoch": 6.666666666666667, + "eval_loss": 0.00447163125500083, + "eval_runtime": 28.703, + "eval_samples_per_second": 20.904, + "eval_steps_per_second": 2.613, + "step": 1000 + }, + { + "epoch": 7.0, + "grad_norm": 0.05669340118765831, + "learning_rate": 4.09090909090909e-05, + "loss": 0.0123, + "step": 1050 + }, + { + "epoch": 7.333333333333333, + "grad_norm": 0.06817171722650528, + "learning_rate": 2.727272727272727e-05, + "loss": 0.0126, + "step": 1100 + }, + { + "epoch": 7.333333333333333, + "eval_loss": 0.004406072199344635, + "eval_runtime": 25.9017, + "eval_samples_per_second": 23.164, + "eval_steps_per_second": 2.896, + "step": 1100 + }, + { + "epoch": 7.666666666666667, + "grad_norm": 0.07227382808923721, + "learning_rate": 1.3636363636363635e-05, + "loss": 0.0122, + "step": 1150 + }, + { + "epoch": 8.0, + "grad_norm": 0.06451401859521866, + "learning_rate": 0.0, + "loss": 0.0121, + "step": 1200 + }, + { + "epoch": 8.0, + "eval_loss": 0.004362119827419519, + "eval_runtime": 25.4411, + "eval_samples_per_second": 23.584, + "eval_steps_per_second": 2.948, + "step": 1200 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5898179602022400.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-1200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-1800/README.md b/checkpoint-1800/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-1800/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-1800/adapter_config.json b/checkpoint-1800/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1b54766aeff68cb83651e511ab3c25d9a3923c2d --- /dev/null +++ b/checkpoint-1800/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v", + "q" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1800/adapter_model.safetensors b/checkpoint-1800/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cd751ff085ef4523c432351f62ae8364031f553 --- /dev/null +++ b/checkpoint-1800/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d75c4c4f1c9fd03eb8f1f4197f66d90255f49e03270eafe1d424db0d1bce2f +size 3558888 diff --git a/checkpoint-1800/added_tokens.json b/checkpoint-1800/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-1800/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..10e89b6625bcd8ed4552b163147a42281ba9ba13 --- /dev/null +++ b/checkpoint-1800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37de690f49eb68359a7580f7cd5846f8396db95101ef1370931afeaa65c07cd +size 7194874 diff --git a/checkpoint-1800/rng_state.pth b/checkpoint-1800/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5272c8d48c627ba5dceaef898d15ac37a7670e86 --- /dev/null +++ b/checkpoint-1800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0b7659a63e1836612be0a090b93019e7f4209ad01bfffa613498191b369ed9 +size 13990 diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d93242850d409d4237c252d51be480fe105245ad --- /dev/null +++ b/checkpoint-1800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c634fb8f6d793f9891581eb9c21e86c2bb78a54e10ef662a226903cb4f65c2 +size 1064 diff --git a/checkpoint-1800/special_tokens_map.json b/checkpoint-1800/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-1800/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1800/spiece.model b/checkpoint-1800/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-1800/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-1800/tokenizer_config.json b/checkpoint-1800/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-1800/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a6113fd7aeba131571037c510ebdff9bc87470df --- /dev/null +++ b/checkpoint-1800/trainer_state.json @@ -0,0 +1,78 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.8333333333333334, + "grad_norm": 0.6994049549102783, + "learning_rate": 0.0001666666666666667, + "loss": 0.8261, + "step": 500 + }, + { + "epoch": 1.0, + "eval_loss": 0.021863408386707306, + "eval_runtime": 14.7955, + "eval_samples_per_second": 40.553, + "eval_steps_per_second": 10.138, + "step": 600 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.3775118589401245, + "learning_rate": 0.00013333333333333334, + "loss": 0.0428, + "step": 1000 + }, + { + "epoch": 2.0, + "eval_loss": 0.010692029260098934, + "eval_runtime": 22.0677, + "eval_samples_per_second": 27.189, + "eval_steps_per_second": 6.797, + "step": 1200 + }, + { + "epoch": 2.5, + "grad_norm": 0.30723807215690613, + "learning_rate": 0.0001, + "loss": 0.0259, + "step": 1500 + }, + { + "epoch": 3.0, + "eval_loss": 0.01044970378279686, + "eval_runtime": 24.6966, + "eval_samples_per_second": 24.295, + "eval_steps_per_second": 6.074, + "step": 1800 + } + ], + "logging_steps": 500, + "max_steps": 3000, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1101016439193600.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4433738af62f971e5bbd49757a3ad5112db8457d --- /dev/null +++ b/checkpoint-1800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b552b3f24d1618d676f333dd3e4fe69d4e00f71878e3ae340f8a35a5c8a7510f +size 5240 diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-200/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-200/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..323abeb20efc910e46e21877c83aa4c2ea72214f --- /dev/null +++ b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e35ef126a43afaf9f8bf2be7c524d79595db82555c7e219bd049c721b1dc46c +size 7098016 diff --git a/checkpoint-200/added_tokens.json b/checkpoint-200/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-200/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..efd5d449daf75ec836dcfe566b5a4abbda81c91b --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8edc60b7a8a0ec7d7472efd7d8a8a0ca0e34eda0eef8f0846d938becccdaa870 +size 14272762 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..7634604b2ea2d15ce43ee2d773ae387bc49bf422 --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a52e1687874240dc2f195388b3a14e21795a08a2e06360226802394635c650d +size 13990 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..071f5c45f923a4335552c32e8bb32c949a38756c --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349edc342664e2c47375ad5bf4e89d6fea268393799c71ca0b0ac234658a983d +size 1064 diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-200/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-200/spiece.model b/checkpoint-200/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-200/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-200/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..4bff5102c7cb00c5a3c772d79eb46737a7bffe85 --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,77 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3333333333333333, + "eval_steps": 100, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 983029933670400.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-2400/README.md b/checkpoint-2400/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-2400/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-2400/adapter_config.json b/checkpoint-2400/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1b54766aeff68cb83651e511ab3c25d9a3923c2d --- /dev/null +++ b/checkpoint-2400/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v", + "q" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-2400/adapter_model.safetensors b/checkpoint-2400/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b8f5b750264e10be6ccbf97db45d3426b646828 --- /dev/null +++ b/checkpoint-2400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc0540797fec5dd45bc73e4ce3b2c904fac4517254570e5956bc89051c3c501 +size 3558888 diff --git a/checkpoint-2400/added_tokens.json b/checkpoint-2400/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-2400/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-2400/optimizer.pt b/checkpoint-2400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..39e42b5490313acec2abda388071716a01275c43 --- /dev/null +++ b/checkpoint-2400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8259bf093a59c738f3050ff00c848952fcc7d2f05f9fcf99600abc203a1cbd4b +size 7194874 diff --git a/checkpoint-2400/rng_state.pth b/checkpoint-2400/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9a66a6cf5a36815004b33f48ae673f94f8ff2ac --- /dev/null +++ b/checkpoint-2400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1057e177fad7ca76f4331923531a2db285ec84cb6a578a5354e58ec41f3e61f8 +size 13990 diff --git a/checkpoint-2400/scheduler.pt b/checkpoint-2400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bae8a678254c53b8058d6e26a3822afabda39a66 --- /dev/null +++ b/checkpoint-2400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6503463a4dd58d4bb7073482ea917b0f786c88f90da82d164b8372ba01aa34b +size 1064 diff --git a/checkpoint-2400/special_tokens_map.json b/checkpoint-2400/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-2400/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-2400/spiece.model b/checkpoint-2400/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-2400/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-2400/tokenizer_config.json b/checkpoint-2400/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-2400/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-2400/trainer_state.json b/checkpoint-2400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d75d858359d3020626716cb80c5cc4ed0f753c40 --- /dev/null +++ b/checkpoint-2400/trainer_state.json @@ -0,0 +1,93 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.0, + "eval_steps": 500, + "global_step": 2400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.8333333333333334, + "grad_norm": 0.6994049549102783, + "learning_rate": 0.0001666666666666667, + "loss": 0.8261, + "step": 500 + }, + { + "epoch": 1.0, + "eval_loss": 0.021863408386707306, + "eval_runtime": 14.7955, + "eval_samples_per_second": 40.553, + "eval_steps_per_second": 10.138, + "step": 600 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.3775118589401245, + "learning_rate": 0.00013333333333333334, + "loss": 0.0428, + "step": 1000 + }, + { + "epoch": 2.0, + "eval_loss": 0.010692029260098934, + "eval_runtime": 22.0677, + "eval_samples_per_second": 27.189, + "eval_steps_per_second": 6.797, + "step": 1200 + }, + { + "epoch": 2.5, + "grad_norm": 0.30723807215690613, + "learning_rate": 0.0001, + "loss": 0.0259, + "step": 1500 + }, + { + "epoch": 3.0, + "eval_loss": 0.01044970378279686, + "eval_runtime": 24.6966, + "eval_samples_per_second": 24.295, + "eval_steps_per_second": 6.074, + "step": 1800 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.16843050718307495, + "learning_rate": 6.666666666666667e-05, + "loss": 0.0206, + "step": 2000 + }, + { + "epoch": 4.0, + "eval_loss": 0.009754649363458157, + "eval_runtime": 17.7248, + "eval_samples_per_second": 33.851, + "eval_steps_per_second": 8.463, + "step": 2400 + } + ], + "logging_steps": 500, + "max_steps": 3000, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1468021918924800.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2400/training_args.bin b/checkpoint-2400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4433738af62f971e5bbd49757a3ad5112db8457d --- /dev/null +++ b/checkpoint-2400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b552b3f24d1618d676f333dd3e4fe69d4e00f71878e3ae340f8a35a5c8a7510f +size 5240 diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-300/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-300/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae24771b3e2833a352268e95fda0ec3b6e79d7ba --- /dev/null +++ b/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86775c0c773eaff1b7c6e0f8a059b68b6a17da5273a2394348e011d320c873a0 +size 7098016 diff --git a/checkpoint-300/added_tokens.json b/checkpoint-300/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-300/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..45d022301cb47650a1a22c6a072167795dcacba3 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffeb4bcb54007d67059922f91db5dce41b586ccb0f9ec8be858b2e6ad9f9c83 +size 14272762 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..080a329e6f6747c1136a7223d63851ee85c4b7cd --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49bcc13f10b1188ce8a0d9b98d73cf3f39a03086591cd9be44a83cd39f8c7398 +size 13990 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..986edd35526abe57799044cdfad60b9615ea1eb3 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301b359905e77284899515be263d2fe84dd964c3fb73a9eac0faf698191736f4 +size 1064 diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-300/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-300/spiece.model b/checkpoint-300/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-300/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-300/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..97f5202d72eadb99fa670dc7b0fee3edd9065b70 --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,99 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 100, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1474544900505600.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-3000/README.md b/checkpoint-3000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-3000/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-3000/adapter_config.json b/checkpoint-3000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1b54766aeff68cb83651e511ab3c25d9a3923c2d --- /dev/null +++ b/checkpoint-3000/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v", + "q" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-3000/adapter_model.safetensors b/checkpoint-3000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca339076d7b52eac7b4f5de1903ca3d0029774ac --- /dev/null +++ b/checkpoint-3000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:852b2907b35b920df2e90bf45c381f620539385302518475b16e1d5f2c4ddf09 +size 3558888 diff --git a/checkpoint-3000/added_tokens.json b/checkpoint-3000/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-3000/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..61b2fc5f0815d1a5b3f33fc27a73878f7c95ec7e --- /dev/null +++ b/checkpoint-3000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed39048b0771e9535cb5ea227324452ee3c32d822c844bbe969f6898deeb67e7 +size 7194874 diff --git a/checkpoint-3000/rng_state.pth b/checkpoint-3000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1437106a880b23360a4cf079a5be4559010b2236 --- /dev/null +++ b/checkpoint-3000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b30ecbbfcb232ca847dc5e84bfdfc8c660f7f374f7373d4c90c916a30bbff0 +size 13990 diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1276b1ecd42f1b6f6ea6a3647cf7b21327240f5c --- /dev/null +++ b/checkpoint-3000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59674a70397ef91cca79fea761a480286c3aec7b02c1aaadcdeb7d16b72e17cb +size 1064 diff --git a/checkpoint-3000/special_tokens_map.json b/checkpoint-3000/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-3000/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-3000/spiece.model b/checkpoint-3000/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-3000/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-3000/tokenizer_config.json b/checkpoint-3000/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-3000/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d179fead9a958ad987d9cba7c0f8c5c110d356cb --- /dev/null +++ b/checkpoint-3000/trainer_state.json @@ -0,0 +1,115 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.0, + "eval_steps": 500, + "global_step": 3000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.8333333333333334, + "grad_norm": 0.6994049549102783, + "learning_rate": 0.0001666666666666667, + "loss": 0.8261, + "step": 500 + }, + { + "epoch": 1.0, + "eval_loss": 0.021863408386707306, + "eval_runtime": 14.7955, + "eval_samples_per_second": 40.553, + "eval_steps_per_second": 10.138, + "step": 600 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.3775118589401245, + "learning_rate": 0.00013333333333333334, + "loss": 0.0428, + "step": 1000 + }, + { + "epoch": 2.0, + "eval_loss": 0.010692029260098934, + "eval_runtime": 22.0677, + "eval_samples_per_second": 27.189, + "eval_steps_per_second": 6.797, + "step": 1200 + }, + { + "epoch": 2.5, + "grad_norm": 0.30723807215690613, + "learning_rate": 0.0001, + "loss": 0.0259, + "step": 1500 + }, + { + "epoch": 3.0, + "eval_loss": 0.01044970378279686, + "eval_runtime": 24.6966, + "eval_samples_per_second": 24.295, + "eval_steps_per_second": 6.074, + "step": 1800 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.16843050718307495, + "learning_rate": 6.666666666666667e-05, + "loss": 0.0206, + "step": 2000 + }, + { + "epoch": 4.0, + "eval_loss": 0.009754649363458157, + "eval_runtime": 17.7248, + "eval_samples_per_second": 33.851, + "eval_steps_per_second": 8.463, + "step": 2400 + }, + { + "epoch": 4.166666666666667, + "grad_norm": 0.21057139337062836, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.0178, + "step": 2500 + }, + { + "epoch": 5.0, + "grad_norm": 0.23059837520122528, + "learning_rate": 0.0, + "loss": 0.0171, + "step": 3000 + }, + { + "epoch": 5.0, + "eval_loss": 0.009692327119410038, + "eval_runtime": 18.3471, + "eval_samples_per_second": 32.703, + "eval_steps_per_second": 8.176, + "step": 3000 + } + ], + "logging_steps": 500, + "max_steps": 3000, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1835027398656000.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4433738af62f971e5bbd49757a3ad5112db8457d --- /dev/null +++ b/checkpoint-3000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b552b3f24d1618d676f333dd3e4fe69d4e00f71878e3ae340f8a35a5c8a7510f +size 5240 diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-400/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-400/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9290eea347196b6ec07f472c5c627a1a9c63406 --- /dev/null +++ b/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f97be4b5f987e22cfce2b044224d2c6093dcef30df1158841c04becb500a9ff +size 7098016 diff --git a/checkpoint-400/added_tokens.json b/checkpoint-400/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-400/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d454a1ebdab4ec9ec882558613cd79ccee23d837 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228d53dfb293386b81d75b96f3a72a38507cae0a2a3805467a289e461ad7bab4 +size 14272762 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..d372fdd0a83ba03ed42e2099e1e7abf03d62b576 --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313197ad728be17c0e8901a451d547f8b4bb02ccc62f005a6369fd5fcbb66fad +size 13990 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1e96750a1af3649c98720d3ba3cec207d2d1ec2 --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9fa42d0c14fea0431132c0264f0560a2dcea42ba336c434f57a11a35dc0a54 +size 1064 diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-400/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-400/spiece.model b/checkpoint-400/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-400/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-400/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..98e6fe62ca1cff664e57e1d79ce2ea14b3804d46 --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,121 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.6666666666666665, + "eval_steps": 100, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1966059867340800.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..680e731f237f3476ce294c75fb7947fb1a5ca88b --- /dev/null +++ b/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0f10b402c0f6a74885cc19c391da6d2a65958e5294c3bcdb8cad706eb069d0 +size 7098016 diff --git a/checkpoint-500/added_tokens.json b/checkpoint-500/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-500/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5dd0606b703f0e6502ee199daa4eb225ee690034 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9794636b04b9822ba82a3e434b69f3243e9df9fc1f70ab6e1a413d0b694593af +size 14272762 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b6e1ba8777add05686ba782d045e043759a973b --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd4a25f353618f1bf6450bbeb7c90597f294e3e26f7feb26cc341761c5ac040 +size 13990 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6a0f8a0492ef7becfc73ac078dbbc4fefde317e --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8e7a1dd9fedd286d092d61436288e35d4852af67652260d698ae562de4a70c +size 1064 diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-500/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-500/spiece.model b/checkpoint-500/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-500/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-500/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..319b9baf1ba5e5353ab94f927940ae027b49bef1 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,143 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.3333333333333335, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2457574834176000.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-600/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-600/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ce964c0b597521dfc59ea14652c1d883bb501e4 --- /dev/null +++ b/checkpoint-600/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4b1322a977e85151520917204650c2e34a2b313b80615b753a13ef52618bca +size 7098016 diff --git a/checkpoint-600/added_tokens.json b/checkpoint-600/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-600/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cae37a13310f9fecb4a77654937e7feac687b45 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4be86657ba41fa2d727d430c938ad636da9248fd7a10b9fdc23aa91dac55a03 +size 14272762 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1437106a880b23360a4cf079a5be4559010b2236 --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b30ecbbfcb232ca847dc5e84bfdfc8c660f7f374f7373d4c90c916a30bbff0 +size 13990 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..dba466001a62f08c79a06f875bed391e9ae028c5 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afa48dc49080dde43a63fca28ad931d4c6b3563ab1df9bd86dfd06bdda7249c +size 1064 diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-600/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-600/spiece.model b/checkpoint-600/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-600/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-600/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b544178420110d3fa5106c13fbb39062e0561209 --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,165 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.0, + "eval_steps": 100, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2949089801011200.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-700/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-700/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-700/adapter_model.safetensors b/checkpoint-700/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6daafeadfff69f51179c875d07a37cae47cfc1a5 --- /dev/null +++ b/checkpoint-700/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2bb5d17b10204fb37cef73de210da1c47d6bdd8f31fd45b02681d005248c7c2 +size 7098016 diff --git a/checkpoint-700/added_tokens.json b/checkpoint-700/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-700/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1df029d719467879530bf120247366fc52e51c7c --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8594664aa12e8a5fabef641393716e0731825cb2055fb0d8d4b9f0bda6455801 +size 14272762 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ec9cf196c710b33da97914e4c52966fc8f88393 --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3022d69db36cea90846f1ca2e78804a702ab9622e0c6fc750b053509f32470ef +size 13990 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..70fbb1aa2a7a02c3588d323ad83aa02084fa1534 --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741f152619b15d601fe781125c919c17e34fd28820e2a145b2e7367a2d1850d9 +size 1064 diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-700/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-700/spiece.model b/checkpoint-700/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-700/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-700/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d13cfa1266bfe440dfa5e3026f756d44451b7f19 --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.666666666666667, + "eval_steps": 100, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3440604767846400.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-750/README.md b/checkpoint-750/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-750/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-750/adapter_config.json b/checkpoint-750/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1b54766aeff68cb83651e511ab3c25d9a3923c2d --- /dev/null +++ b/checkpoint-750/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v", + "q" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-750/adapter_model.safetensors b/checkpoint-750/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c47445b2e32c74e19e6d6383bd9ca89d5d3820b --- /dev/null +++ b/checkpoint-750/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4cca89839d2a558cc0651a6760a10996473e2a31b2a05ce6ac469b1337c62a +size 3558888 diff --git a/checkpoint-750/added_tokens.json b/checkpoint-750/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-750/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-750/optimizer.pt b/checkpoint-750/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed12146877c43f8b29203dfbae8de030c0a5d3c4 --- /dev/null +++ b/checkpoint-750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0dd8a5d5353587b5a5a2c8175dbcf19f6ef9056680365d474e90757cbad514 +size 7194874 diff --git a/checkpoint-750/rng_state.pth b/checkpoint-750/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..99f772e150567ae2529007c9815aa085fc68cf3f --- /dev/null +++ b/checkpoint-750/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ffd2e67a5e106bcbed7941bfeb9076b68a447bab53d273e41d280ee2e05187 +size 13990 diff --git a/checkpoint-750/scheduler.pt b/checkpoint-750/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bcee509b4fd8182bd7d758722ccf70052b46cad1 --- /dev/null +++ b/checkpoint-750/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc1cd8cb21602d226561e78eff50aea7a240e4d2ae58ac0f0b7b5c0d3e16e49 +size 1064 diff --git a/checkpoint-750/special_tokens_map.json b/checkpoint-750/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-750/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-750/spiece.model b/checkpoint-750/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-750/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-750/tokenizer_config.json b/checkpoint-750/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-750/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-750/trainer_state.json b/checkpoint-750/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..db04451c70a24c4fb662cbe362ec1a032cfd6648 --- /dev/null +++ b/checkpoint-750/trainer_state.json @@ -0,0 +1,48 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.6666666666666666, + "grad_norm": 0.6573247313499451, + "learning_rate": 0.00017333333333333334, + "loss": 0.8032, + "step": 500 + }, + { + "epoch": 1.0, + "eval_loss": 0.015370051376521587, + "eval_runtime": 137.2289, + "eval_samples_per_second": 21.861, + "eval_steps_per_second": 5.465, + "step": 750 + } + ], + "logging_steps": 500, + "max_steps": 3750, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 458756849664000.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-750/training_args.bin b/checkpoint-750/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4433738af62f971e5bbd49757a3ad5112db8457d --- /dev/null +++ b/checkpoint-750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b552b3f24d1618d676f333dd3e4fe69d4e00f71878e3ae340f8a35a5c8a7510f +size 5240 diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-800/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-800/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6245ad4cfad1150b8dc20f9bd52a3ca14924043e --- /dev/null +++ b/checkpoint-800/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796c9ea051918043d59c5c947123695eaa7038ce007cbf51d1f63bc4c72479e8 +size 7098016 diff --git a/checkpoint-800/added_tokens.json b/checkpoint-800/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-800/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..58feb896a509ab327917e9a7e946c95b092f215d --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb223aea60cb90d9a1b40847c65f63b2204511eb03a51018d063b0d5f279fa53 +size 14272762 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..87c45bd11fd493526f4eb1d314e71cdc24b0cfff --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b891d4932c1901429ae4534e9a417088a1b1a0e3ff25691c3f78d49f4eac44 +size 13990 diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f729186788588044cc5444a8b9d52cbf2356ef41 --- /dev/null +++ b/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c445ce8eb11f6b3c0cb94f86fb1da27cebae8826da430eedee0d152a9c6c0e +size 1064 diff --git a/checkpoint-800/special_tokens_map.json b/checkpoint-800/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-800/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-800/spiece.model b/checkpoint-800/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-800/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-800/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c4590c6f46e51d7857b3253a607cda5374a39ecc --- /dev/null +++ b/checkpoint-800/trainer_state.json @@ -0,0 +1,209 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.333333333333333, + "eval_steps": 100, + "global_step": 800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + }, + { + "epoch": 5.0, + "grad_norm": 0.09571962058544159, + "learning_rate": 0.00012272727272727272, + "loss": 0.0161, + "step": 750 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.08587690442800522, + "learning_rate": 0.00010909090909090908, + "loss": 0.016, + "step": 800 + }, + { + "epoch": 5.333333333333333, + "eval_loss": 0.005752269644290209, + "eval_runtime": 24.7224, + "eval_samples_per_second": 24.269, + "eval_steps_per_second": 3.034, + "step": 800 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3932119734681600.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39a5b6353ee2b076ea99aa6059ea928b3e8b8e2f --- /dev/null +++ b/checkpoint-900/README.md @@ -0,0 +1,202 @@ +--- +base_model: t5-base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-900/adapter_config.json b/checkpoint-900/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ff550ad0a4f9f54210a6e0ae254e89e55d433ed --- /dev/null +++ b/checkpoint-900/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "t5-base", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q", + "v" + ], + "task_type": "SEQ_2_SEQ_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-900/adapter_model.safetensors b/checkpoint-900/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7607e24824e9b2de9d83bd37750300e222cb02c4 --- /dev/null +++ b/checkpoint-900/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b108b03c22294e8a3fe516c5bcef01cac491776e533fa8ff9c5328a5c98b50 +size 7098016 diff --git a/checkpoint-900/added_tokens.json b/checkpoint-900/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/checkpoint-900/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..af8f14edd9a8f249bf587b0671b4b324fcf5c0dd --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7bb74015540408e177c54c0bd39d78dcbee12a8417d333ecac69353733894fb +size 14272762 diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2bc02fcf44e068ddf159c377770cf25449bbe7d7 --- /dev/null +++ b/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc1ad7dd842383f28326cbc62801e658fdc1989cca4212d56053d6084cc1bc7 +size 13990 diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e24bb83fc9bc9e73c7660fcd042334f744f498d --- /dev/null +++ b/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62678c5d63cd750689211fc5f8b823762c87637da12ba06279ad43d139282a6 +size 1064 diff --git a/checkpoint-900/special_tokens_map.json b/checkpoint-900/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/checkpoint-900/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-900/spiece.model b/checkpoint-900/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/checkpoint-900/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/checkpoint-900/tokenizer_config.json b/checkpoint-900/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/checkpoint-900/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..78266dde3b618b6e2e8450d6c76f08b6aac98e48 --- /dev/null +++ b/checkpoint-900/trainer_state.json @@ -0,0 +1,231 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 6.0, + "eval_steps": 100, + "global_step": 900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.3333333333333333, + "grad_norm": 6.638962268829346, + "learning_rate": 0.00015, + "loss": 11.1435, + "step": 50 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.32958298921585083, + "learning_rate": 0.0003, + "loss": 1.3737, + "step": 100 + }, + { + "epoch": 0.6666666666666666, + "eval_loss": 0.5655200481414795, + "eval_runtime": 19.9386, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 3.762, + "step": 100 + }, + { + "epoch": 1.0, + "grad_norm": 0.33953434228897095, + "learning_rate": 0.00028636363636363636, + "loss": 0.5027, + "step": 150 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.2767198383808136, + "learning_rate": 0.0002727272727272727, + "loss": 0.2077, + "step": 200 + }, + { + "epoch": 1.3333333333333333, + "eval_loss": 0.04386770725250244, + "eval_runtime": 41.6128, + "eval_samples_per_second": 14.419, + "eval_steps_per_second": 1.802, + "step": 200 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.2200630158185959, + "learning_rate": 0.00025909090909090907, + "loss": 0.1041, + "step": 250 + }, + { + "epoch": 2.0, + "grad_norm": 0.19840039312839508, + "learning_rate": 0.00024545454545454545, + "loss": 0.0635, + "step": 300 + }, + { + "epoch": 2.0, + "eval_loss": 0.013007530942559242, + "eval_runtime": 25.1999, + "eval_samples_per_second": 23.81, + "eval_steps_per_second": 2.976, + "step": 300 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.13067609071731567, + "learning_rate": 0.0002318181818181818, + "loss": 0.0458, + "step": 350 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.14327284693717957, + "learning_rate": 0.00021818181818181816, + "loss": 0.0347, + "step": 400 + }, + { + "epoch": 2.6666666666666665, + "eval_loss": 0.009889846667647362, + "eval_runtime": 24.6225, + "eval_samples_per_second": 24.368, + "eval_steps_per_second": 3.046, + "step": 400 + }, + { + "epoch": 3.0, + "grad_norm": 0.12795384228229523, + "learning_rate": 0.0002045454545454545, + "loss": 0.0292, + "step": 450 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.10173379629850388, + "learning_rate": 0.0001909090909090909, + "loss": 0.0259, + "step": 500 + }, + { + "epoch": 3.3333333333333335, + "eval_loss": 0.008001920767128468, + "eval_runtime": 28.8328, + "eval_samples_per_second": 20.81, + "eval_steps_per_second": 2.601, + "step": 500 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.10923352837562561, + "learning_rate": 0.00017727272727272728, + "loss": 0.0223, + "step": 550 + }, + { + "epoch": 4.0, + "grad_norm": 0.09930842369794846, + "learning_rate": 0.0001636363636363636, + "loss": 0.0206, + "step": 600 + }, + { + "epoch": 4.0, + "eval_loss": 0.006877058185636997, + "eval_runtime": 26.3527, + "eval_samples_per_second": 22.768, + "eval_steps_per_second": 2.846, + "step": 600 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.14481599628925323, + "learning_rate": 0.00015, + "loss": 0.0196, + "step": 650 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.10063868761062622, + "learning_rate": 0.00013636363636363634, + "loss": 0.0178, + "step": 700 + }, + { + "epoch": 4.666666666666667, + "eval_loss": 0.006417799741029739, + "eval_runtime": 25.4573, + "eval_samples_per_second": 23.569, + "eval_steps_per_second": 2.946, + "step": 700 + }, + { + "epoch": 5.0, + "grad_norm": 0.09571962058544159, + "learning_rate": 0.00012272727272727272, + "loss": 0.0161, + "step": 750 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.08587690442800522, + "learning_rate": 0.00010909090909090908, + "loss": 0.016, + "step": 800 + }, + { + "epoch": 5.333333333333333, + "eval_loss": 0.005752269644290209, + "eval_runtime": 24.7224, + "eval_samples_per_second": 24.269, + "eval_steps_per_second": 3.034, + "step": 800 + }, + { + "epoch": 5.666666666666667, + "grad_norm": 0.07417745888233185, + "learning_rate": 9.545454545454545e-05, + "loss": 0.0152, + "step": 850 + }, + { + "epoch": 6.0, + "grad_norm": 0.08311035484075546, + "learning_rate": 8.18181818181818e-05, + "loss": 0.0143, + "step": 900 + }, + { + "epoch": 6.0, + "eval_loss": 0.00478348508477211, + "eval_runtime": 26.3439, + "eval_samples_per_second": 22.776, + "eval_steps_per_second": 2.847, + "step": 900 + } + ], + "logging_steps": 50, + "max_steps": 1200, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4423634701516800.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..89f57793fe21f3b5110254ab72bb9a91aefa0480 --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39e1f90d3cf57d19d93e81b5d86272403ec2e8d685534391b5ad0a48cb97d33 +size 5240 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/spiece.model b/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..be77fb8064b6948f0cc9224b4203193f2a651346 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32004": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32005": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32006": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32007": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32008": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32009": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32010": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32039": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32040": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32041": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32042": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32043": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32044": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32045": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32046": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32047": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32048": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32049": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32050": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32051": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32052": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32053": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32054": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32055": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32056": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32057": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32058": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32059": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32060": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32061": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32062": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32063": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32064": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32065": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32066": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32067": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32068": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32069": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32070": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32071": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32072": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32073": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32074": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32075": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32076": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32077": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32078": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32079": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32080": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32081": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32082": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32083": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32084": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32085": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32086": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32087": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32088": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32089": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32090": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32091": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32092": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32093": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32094": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32095": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32096": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32097": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32098": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32099": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +}