Training in progress, step 1000, checkpoint

checkpoint-1000/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v2-meta-OWT",
+  "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": 128257
+}

checkpoint-1000/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-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5bec1d745bbe7cecc997ec9cdc825ace24554e26334e456ddde61494d261de
+size 4943282520

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3fef74f1f60443df4f4e0884707105b4149a8cf3253fb1e293c7fc9cf241cb
+size 3724602

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfc25b3273eba5695f36b6c766de6404d051067317b1ef3114d8046bcbf15c0
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0447a9bebd7de480acd87b320879adb806c367d23517603e388046e9c651125c
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.030636785588456058,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003063678558845606,
+      "grad_norm": 2.5270798206329346,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.1564,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.604092597961426,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.1166,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.5005924701690674,
+      "learning_rate": 3e-06,
+      "loss": 3.0905,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.7525177001953125,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.0652,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.5251283645629883,
+      "learning_rate": 5e-06,
+      "loss": 3.0351,
+      "step": 500
+    },
+    {
+      "epoch": 0.018382071353073636,
+      "grad_norm": 2.6771860122680664,
+      "learning_rate": 6e-06,
+      "loss": 3.0028,
+      "step": 600
+    },
+    {
+      "epoch": 0.02144574991191924,
+      "grad_norm": 2.4799458980560303,
+      "learning_rate": 7e-06,
+      "loss": 3.0007,
+      "step": 700
+    },
+    {
+      "epoch": 0.024509428470764847,
+      "grad_norm": 2.8402369022369385,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9753,
+      "step": 800
+    },
+    {
+      "epoch": 0.027573107029610452,
+      "grad_norm": 2.446842908859253,
+      "learning_rate": 9e-06,
+      "loss": 2.9737,
+      "step": 900
+    },
+    {
+      "epoch": 0.030636785588456058,
+      "grad_norm": 2.3989391326904297,
+      "learning_rate": 1e-05,
+      "loss": 2.9618,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "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": 9.5664155394048e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343fd12cd57f4f5c4c4d092162b0058e69041ee73092ab79cda1f02d0d79adab
+size 5368