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_stackoverflow
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_stackoverflow
 
-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_stackoverflow dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8003
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.8002719879150391,
+    "eval_runtime": 24.347,
+    "eval_samples_per_second": 38.732,
+    "eval_steps_per_second": 0.616,
+    "total_flos": 175669531115520.0,
+    "train_loss": 0.7949266456422351,
+    "train_runtime": 3759.0674,
+    "train_samples_per_second": 14.299,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.8002719879150391,
+    "eval_runtime": 24.347,
+    "eval_samples_per_second": 38.732,
+    "eval_steps_per_second": 0.616
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 175669531115520.0,
+    "train_loss": 0.7949266456422351,
+    "train_runtime": 3759.0674,
+    "train_samples_per_second": 14.299,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.8775508227330162,
+      "learning_rate": 5e-06,
+      "loss": 0.9902,
+      "step": 10
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 5.202773227442544,
+      "learning_rate": 5e-06,
+      "loss": 0.8825,
+      "step": 20
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.5616534372045574,
+      "learning_rate": 5e-06,
+      "loss": 0.8516,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8306872248649597,
+      "eval_runtime": 24.6974,
+      "eval_samples_per_second": 38.182,
+      "eval_steps_per_second": 0.607,
+      "step": 35
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.0376556039392277,
+      "learning_rate": 5e-06,
+      "loss": 0.8187,
+      "step": 40
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7862654572661807,
+      "learning_rate": 5e-06,
+      "loss": 0.7827,
+      "step": 50
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.7941732477008099,
+      "learning_rate": 5e-06,
+      "loss": 0.7745,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6579183557112935,
+      "learning_rate": 5e-06,
+      "loss": 0.7677,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8009844422340393,
+      "eval_runtime": 24.1786,
+      "eval_samples_per_second": 39.001,
+      "eval_steps_per_second": 0.62,
+      "step": 70
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.8097066764842236,
+      "learning_rate": 5e-06,
+      "loss": 0.7107,
+      "step": 80
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.7278435165038939,
+      "learning_rate": 5e-06,
+      "loss": 0.7068,
+      "step": 90
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.5934790606088474,
+      "learning_rate": 5e-06,
+      "loss": 0.7058,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8002719879150391,
+      "eval_runtime": 23.5358,
+      "eval_samples_per_second": 40.067,
+      "eval_steps_per_second": 0.637,
+      "step": 105
+    },
+    {
+      "epoch": 3.0,
+      "step": 105,
+      "total_flos": 175669531115520.0,
+      "train_loss": 0.7949266456422351,
+      "train_runtime": 3759.0674,
+      "train_samples_per_second": 14.299,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 105,
+  "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": 175669531115520.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}