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_music
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_music
 
-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_music dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9631
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.973684210526316,
+    "eval_loss": 0.9630991816520691,
+    "eval_runtime": 18.9639,
+    "eval_samples_per_second": 40.34,
+    "eval_steps_per_second": 0.633,
+    "total_flos": 140493748961280.0,
+    "train_loss": 1.022699855622791,
+    "train_runtime": 3014.0633,
+    "train_samples_per_second": 14.461,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.973684210526316,
+    "eval_loss": 0.9630991816520691,
+    "eval_runtime": 18.9639,
+    "eval_samples_per_second": 40.34,
+    "eval_steps_per_second": 0.633
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.973684210526316,
+    "total_flos": 140493748961280.0,
+    "train_loss": 1.022699855622791,
+    "train_runtime": 3014.0633,
+    "train_samples_per_second": 14.461,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.973684210526316,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 4.601614024655165,
+      "learning_rate": 5e-06,
+      "loss": 1.2073,
+      "step": 10
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 3.0288654015564656,
+      "learning_rate": 5e-06,
+      "loss": 1.088,
+      "step": 20
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "eval_loss": 1.035239577293396,
+      "eval_runtime": 19.9672,
+      "eval_samples_per_second": 38.313,
+      "eval_steps_per_second": 0.601,
+      "step": 28
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 1.8333560228741572,
+      "learning_rate": 5e-06,
+      "loss": 1.1323,
+      "step": 30
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 3.598396267794485,
+      "learning_rate": 5e-06,
+      "loss": 0.9925,
+      "step": 40
+    },
+    {
+      "epoch": 1.7675438596491229,
+      "grad_norm": 2.0082293179495063,
+      "learning_rate": 5e-06,
+      "loss": 0.9729,
+      "step": 50
+    },
+    {
+      "epoch": 1.9780701754385965,
+      "eval_loss": 0.9812449812889099,
+      "eval_runtime": 19.1781,
+      "eval_samples_per_second": 39.889,
+      "eval_steps_per_second": 0.626,
+      "step": 56
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 1.0866452884036952,
+      "learning_rate": 5e-06,
+      "loss": 1.0281,
+      "step": 60
+    },
+    {
+      "epoch": 2.482456140350877,
+      "grad_norm": 1.0302039701003738,
+      "learning_rate": 5e-06,
+      "loss": 0.9086,
+      "step": 70
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 1.0030764620888597,
+      "learning_rate": 5e-06,
+      "loss": 0.9026,
+      "step": 80
+    },
+    {
+      "epoch": 2.973684210526316,
+      "eval_loss": 0.9630991816520691,
+      "eval_runtime": 17.9565,
+      "eval_samples_per_second": 42.603,
+      "eval_steps_per_second": 0.668,
+      "step": 84
+    },
+    {
+      "epoch": 2.973684210526316,
+      "step": 84,
+      "total_flos": 140493748961280.0,
+      "train_loss": 1.022699855622791,
+      "train_runtime": 3014.0633,
+      "train_samples_per_second": 14.461,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 84,
+  "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": 140493748961280.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}