Training in progress, step 3

README.md

@@ -0,0 +1,183 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- AiAF/Codename-75567-Pretrainin.jsonl
+model-index:
+- name: Pretrained-QLoRA-Codename-75567-V1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+# optionally might have model_type or tokenizer_type
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+hub_model_id: AiAF/Pretrained-QLoRA-Codename-75567-V1
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: AiAF/Codename-75567-Pretrainin.jsonl
+    type: completion
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./outputs/qlora-out
+save_total_limit: 10
+
+adapter: qlora
+lora_model_dir:
+lora_r: 256
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+sequence_len: 512
+sample_packing: true
+pad_to_sequence_len: true
+eval_sample_packing: false
+
+wandb_project: "LLM-Pretraining"
+wandb_watch: "all"
+wandb_name: "QLoRA-Codename-75567-V1"
+wandb_log_model: "false"
+wandb_run_id: "QLoRA-Codename-75567-V1"
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 10
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.000005
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 1
+evals_per_epoch: 5
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# Pretrained-QLoRA-Codename-75567-V1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the AiAF/Codename-75567-Pretrainin.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6938
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8916        | 0.3333 | 1    | 1.8880          |
+| 2.017         | 0.6667 | 2    | 1.8847          |
+| 1.9119        | 1.0    | 3    | 1.8795          |
+| 1.9716        | 1.3333 | 4    | 1.8711          |
+| 1.8532        | 1.6667 | 5    | 1.8601          |
+| 1.9759        | 2.0    | 6    | 1.8488          |
+| 1.856         | 2.3333 | 7    | 1.8357          |
+| 1.8404        | 2.6667 | 8    | 1.8241          |
+| 1.976         | 3.0    | 9    | 1.8131          |
+| 1.8504        | 3.3333 | 10   | 1.8012          |
+| 1.8574        | 3.6667 | 11   | 1.7860          |
+| 1.8194        | 4.0    | 12   | 1.7749          |
+| 1.8022        | 4.3333 | 13   | 1.7646          |
+| 1.7632        | 4.6667 | 14   | 1.7525          |
+| 1.8326        | 5.0    | 15   | 1.7440          |
+| 1.7696        | 5.3333 | 16   | 1.7325          |
+| 1.8039        | 5.6667 | 17   | 1.7257          |
+| 1.7019        | 6.0    | 18   | 1.7164          |
+| 1.7878        | 6.3333 | 19   | 1.7132          |
+| 1.718         | 6.6667 | 20   | 1.7093          |
+| 1.6994        | 7.0    | 21   | 1.7049          |
+| 1.785         | 7.3333 | 22   | 1.6996          |
+| 1.6659        | 7.6667 | 23   | 1.6977          |
+| 1.7241        | 8.0    | 24   | 1.6970          |
+| 1.7397        | 8.3333 | 25   | 1.6952          |
+| 1.6894        | 8.6667 | 26   | 1.6934          |
+| 1.723         | 9.0    | 27   | 1.6932          |
+| 1.7999        | 9.3333 | 28   | 1.6927          |
+| 1.6715        | 9.6667 | 29   | 1.6941          |
+| 1.6696        | 10.0   | 30   | 1.6938          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25113e000e1f86d846675d12d9356e07d289d9b9f88a54cc8551515dd1d9679
+size 2684416208

config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669717c0d642a513afde9c40be0e82002bafe8b5ea4e70454e420936561f78b9
+size 6584