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: stackexchange_physics
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_physics
 
-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/stackexchange_physics dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8525
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.979310344827586,
+    "eval_loss": 0.8525338172912598,
+    "eval_runtime": 25.539,
+    "eval_samples_per_second": 38.255,
+    "eval_steps_per_second": 0.626,
+    "total_flos": 180694642851840.0,
+    "train_loss": 0.8558892673916287,
+    "train_runtime": 3801.0513,
+    "train_samples_per_second": 14.649,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.979310344827586,
+    "eval_loss": 0.8525338172912598,
+    "eval_runtime": 25.539,
+    "eval_samples_per_second": 38.255,
+    "eval_steps_per_second": 0.626
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.979310344827586,
+    "total_flos": 180694642851840.0,
+    "train_loss": 0.8558892673916287,
+    "train_runtime": 3801.0513,
+    "train_samples_per_second": 14.649,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.979310344827586,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 7.99272917412018,
+      "learning_rate": 5e-06,
+      "loss": 1.0372,
+      "step": 10
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 1.3943848882036196,
+      "learning_rate": 5e-06,
+      "loss": 0.9401,
+      "step": 20
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 1.0575396228689353,
+      "learning_rate": 5e-06,
+      "loss": 0.9015,
+      "step": 30
+    },
+    {
+      "epoch": 0.993103448275862,
+      "eval_loss": 0.8885926604270935,
+      "eval_runtime": 26.5641,
+      "eval_samples_per_second": 36.779,
+      "eval_steps_per_second": 0.602,
+      "step": 36
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 1.2477575212494822,
+      "learning_rate": 5e-06,
+      "loss": 0.936,
+      "step": 40
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 1.0469251972786897,
+      "learning_rate": 5e-06,
+      "loss": 0.8346,
+      "step": 50
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.9988632319097552,
+      "learning_rate": 5e-06,
+      "loss": 0.8219,
+      "step": 60
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.9140527353187675,
+      "learning_rate": 5e-06,
+      "loss": 0.8158,
+      "step": 70
+    },
+    {
+      "epoch": 1.986206896551724,
+      "eval_loss": 0.8567079305648804,
+      "eval_runtime": 25.9826,
+      "eval_samples_per_second": 37.602,
+      "eval_steps_per_second": 0.616,
+      "step": 72
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 1.5245621594542598,
+      "learning_rate": 5e-06,
+      "loss": 0.843,
+      "step": 80
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 1.0372960320477767,
+      "learning_rate": 5e-06,
+      "loss": 0.7585,
+      "step": 90
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.9305737492177628,
+      "learning_rate": 5e-06,
+      "loss": 0.7606,
+      "step": 100
+    },
+    {
+      "epoch": 2.979310344827586,
+      "eval_loss": 0.8525338172912598,
+      "eval_runtime": 24.5522,
+      "eval_samples_per_second": 39.793,
+      "eval_steps_per_second": 0.652,
+      "step": 108
+    },
+    {
+      "epoch": 2.979310344827586,
+      "step": 108,
+      "total_flos": 180694642851840.0,
+      "train_loss": 0.8558892673916287,
+      "train_runtime": 3801.0513,
+      "train_samples_per_second": 14.649,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 108,
+  "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": 180694642851840.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}