End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: llama3-1_8b_math_100000_samples
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_math_100000_samples
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/math_100000_samples dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5704
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5704450607299805,
+    "eval_runtime": 8.3221,
+    "eval_samples_per_second": 271.324,
+    "eval_steps_per_second": 1.081,
+    "total_flos": 422109385850880.0,
+    "train_loss": 0.5631871157222323,
+    "train_runtime": 1874.1971,
+    "train_samples_per_second": 68.655,
+    "train_steps_per_second": 0.134
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5704450607299805,
+    "eval_runtime": 8.3221,
+    "eval_samples_per_second": 271.324,
+    "eval_steps_per_second": 1.081
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 422109385850880.0,
+    "train_loss": 0.5631871157222323,
+    "train_runtime": 1874.1971,
+    "train_samples_per_second": 68.655,
+    "train_steps_per_second": 0.134
+}

trainer_state.json

@@ -0,0 +1,241 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 26.617824687216622,
+      "learning_rate": 5e-06,
+      "loss": 0.7508,
+      "step": 10
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.8689351819227027,
+      "learning_rate": 5e-06,
+      "loss": 0.6727,
+      "step": 20
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.5792334038916935,
+      "learning_rate": 5e-06,
+      "loss": 0.633,
+      "step": 30
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.6218650960930915,
+      "learning_rate": 5e-06,
+      "loss": 0.6164,
+      "step": 40
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 1.140712919876654,
+      "learning_rate": 5e-06,
+      "loss": 0.6066,
+      "step": 50
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.8602592078396757,
+      "learning_rate": 5e-06,
+      "loss": 0.5966,
+      "step": 60
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.8320424935867776,
+      "learning_rate": 5e-06,
+      "loss": 0.5944,
+      "step": 70
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.49165318108555545,
+      "learning_rate": 5e-06,
+      "loss": 0.5861,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5798346996307373,
+      "eval_runtime": 8.4592,
+      "eval_samples_per_second": 266.928,
+      "eval_steps_per_second": 1.064,
+      "step": 84
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.6573425533819024,
+      "learning_rate": 5e-06,
+      "loss": 0.5663,
+      "step": 90
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.4670077635391962,
+      "learning_rate": 5e-06,
+      "loss": 0.5517,
+      "step": 100
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 0.5237829600316058,
+      "learning_rate": 5e-06,
+      "loss": 0.5546,
+      "step": 110
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.5547024135708416,
+      "learning_rate": 5e-06,
+      "loss": 0.5526,
+      "step": 120
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 0.47689471851329457,
+      "learning_rate": 5e-06,
+      "loss": 0.5466,
+      "step": 130
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5230783383262022,
+      "learning_rate": 5e-06,
+      "loss": 0.5472,
+      "step": 140
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.5674014749330538,
+      "learning_rate": 5e-06,
+      "loss": 0.5464,
+      "step": 150
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.47822121321020516,
+      "learning_rate": 5e-06,
+      "loss": 0.543,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5688267946243286,
+      "eval_runtime": 8.5104,
+      "eval_samples_per_second": 265.321,
+      "eval_steps_per_second": 1.058,
+      "step": 168
+    },
+    {
+      "epoch": 2.0238095238095237,
+      "grad_norm": 0.9393861948324864,
+      "learning_rate": 5e-06,
+      "loss": 0.5387,
+      "step": 170
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.5880801701644413,
+      "learning_rate": 5e-06,
+      "loss": 0.513,
+      "step": 180
+    },
+    {
+      "epoch": 2.261904761904762,
+      "grad_norm": 0.7573868967310241,
+      "learning_rate": 5e-06,
+      "loss": 0.5084,
+      "step": 190
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.5149453817597104,
+      "learning_rate": 5e-06,
+      "loss": 0.5065,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.48769983126777056,
+      "learning_rate": 5e-06,
+      "loss": 0.5096,
+      "step": 210
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.6168117709375799,
+      "learning_rate": 5e-06,
+      "loss": 0.51,
+      "step": 220
+    },
+    {
+      "epoch": 2.738095238095238,
+      "grad_norm": 0.6182244851253141,
+      "learning_rate": 5e-06,
+      "loss": 0.5075,
+      "step": 230
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.5115158649844643,
+      "learning_rate": 5e-06,
+      "loss": 0.5129,
+      "step": 240
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "grad_norm": 0.6056742291106577,
+      "learning_rate": 5e-06,
+      "loss": 0.51,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5704450607299805,
+      "eval_runtime": 8.2035,
+      "eval_samples_per_second": 275.249,
+      "eval_steps_per_second": 1.097,
+      "step": 252
+    },
+    {
+      "epoch": 3.0,
+      "step": 252,
+      "total_flos": 422109385850880.0,
+      "train_loss": 0.5631871157222323,
+      "train_runtime": 1874.1971,
+      "train_samples_per_second": 68.655,
+      "train_steps_per_second": 0.134
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 422109385850880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}