Training in progress, step 500, checkpoint

checkpoint-500/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c030315683a323ceca5e5012742bc2f5c9e67042b7e0c3925d8894ad6085b15
+size 4943274328

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356c78a95732ad01571cc229bb95a1e459d26b3e0e06ebd6f609f6544eda13b4
+size 3724602

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6587012b8ddc07c7eddd5570d48ae1120338348aab08b812e93d2688428be5ec
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb33f73969fe0349574459d6fe04a07eb8949a6b61b9bac446685eddfc5afaa
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.015318392794228029,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003063678558845606,
+      "grad_norm": 2.937537670135498,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.9979,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.9786553382873535,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9223,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.899183750152588,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.9009,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.9656615257263184,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.8884,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.785738468170166,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.8738,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 4.7832077697024e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143b5f6c6fe08f3f5ae3c56265d9e4157a9e86249acdc63737a238135515a88f
+size 5432