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_movies
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_movies
 
-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_movies dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0959
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9230769230769234,
+    "eval_loss": 1.0959041118621826,
+    "eval_runtime": 14.2048,
+    "eval_samples_per_second": 36.959,
+    "eval_steps_per_second": 0.634,
+    "total_flos": 95267743334400.0,
+    "train_loss": 1.1790305020516378,
+    "train_runtime": 2175.4715,
+    "train_samples_per_second": 13.743,
+    "train_steps_per_second": 0.026
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9230769230769234,
+    "eval_loss": 1.0959041118621826,
+    "eval_runtime": 14.2048,
+    "eval_samples_per_second": 36.959,
+    "eval_steps_per_second": 0.634
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9230769230769234,
+    "total_flos": 95267743334400.0,
+    "train_loss": 1.1790305020516378,
+    "train_runtime": 2175.4715,
+    "train_samples_per_second": 13.743,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9230769230769234,
+  "eval_steps": 500,
+  "global_step": 57,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 16.278400614202585,
+      "learning_rate": 5e-06,
+      "loss": 1.3652,
+      "step": 10
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "eval_loss": 1.1945005655288696,
+      "eval_runtime": 15.0734,
+      "eval_samples_per_second": 34.83,
+      "eval_steps_per_second": 0.597,
+      "step": 19
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 2.920964786273589,
+      "learning_rate": 5e-06,
+      "loss": 1.2843,
+      "step": 20
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 2.7828054078375986,
+      "learning_rate": 5e-06,
+      "loss": 1.1511,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1268930435180664,
+      "eval_runtime": 14.4077,
+      "eval_samples_per_second": 36.439,
+      "eval_steps_per_second": 0.625,
+      "step": 39
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 1.4101570404308965,
+      "learning_rate": 5e-06,
+      "loss": 1.1621,
+      "step": 40
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 1.0326156619051292,
+      "learning_rate": 5e-06,
+      "loss": 1.042,
+      "step": 50
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_loss": 1.0959041118621826,
+      "eval_runtime": 13.015,
+      "eval_samples_per_second": 40.338,
+      "eval_steps_per_second": 0.692,
+      "step": 57
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "step": 57,
+      "total_flos": 95267743334400.0,
+      "train_loss": 1.1790305020516378,
+      "train_runtime": 2175.4715,
+      "train_samples_per_second": 13.743,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 57,
+  "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": 95267743334400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}