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: metamath_seeding_stackexchange_codegolf
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # metamath_seeding_stackexchange_codegolf
 
-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/metamath_seeding_stackexchange_codegolf dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1392
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.954954954954955,
+    "eval_loss": 1.1392163038253784,
+    "eval_runtime": 29.5712,
+    "eval_samples_per_second": 25.295,
+    "eval_steps_per_second": 0.406,
+    "total_flos": 135468637224960.0,
+    "train_loss": 1.2098971104916232,
+    "train_runtime": 5037.896,
+    "train_samples_per_second": 8.452,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.954954954954955,
+    "eval_loss": 1.1392163038253784,
+    "eval_runtime": 29.5712,
+    "eval_samples_per_second": 25.295,
+    "eval_steps_per_second": 0.406
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.954954954954955,
+    "total_flos": 135468637224960.0,
+    "train_loss": 1.2098971104916232,
+    "train_runtime": 5037.896,
+    "train_samples_per_second": 8.452,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.954954954954955,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 2.250641924316355,
+      "learning_rate": 5e-06,
+      "loss": 1.393,
+      "step": 10
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 1.2330501862526917,
+      "learning_rate": 5e-06,
+      "loss": 1.2523,
+      "step": 20
+    },
+    {
+      "epoch": 0.972972972972973,
+      "eval_loss": 1.189139485359192,
+      "eval_runtime": 30.2485,
+      "eval_samples_per_second": 24.728,
+      "eval_steps_per_second": 0.397,
+      "step": 27
+    },
+    {
+      "epoch": 1.0990990990990992,
+      "grad_norm": 1.5166016651002805,
+      "learning_rate": 5e-06,
+      "loss": 1.3046,
+      "step": 30
+    },
+    {
+      "epoch": 1.4594594594594594,
+      "grad_norm": 1.2046661423953837,
+      "learning_rate": 5e-06,
+      "loss": 1.1666,
+      "step": 40
+    },
+    {
+      "epoch": 1.8198198198198199,
+      "grad_norm": 1.191682944257929,
+      "learning_rate": 5e-06,
+      "loss": 1.1629,
+      "step": 50
+    },
+    {
+      "epoch": 1.9639639639639639,
+      "eval_loss": 1.148915410041809,
+      "eval_runtime": 30.0787,
+      "eval_samples_per_second": 24.868,
+      "eval_steps_per_second": 0.399,
+      "step": 54
+    },
+    {
+      "epoch": 2.1981981981981984,
+      "grad_norm": 2.1203811944634414,
+      "learning_rate": 5e-06,
+      "loss": 1.2105,
+      "step": 60
+    },
+    {
+      "epoch": 2.5585585585585586,
+      "grad_norm": 1.0865067343650627,
+      "learning_rate": 5e-06,
+      "loss": 1.1106,
+      "step": 70
+    },
+    {
+      "epoch": 2.918918918918919,
+      "grad_norm": 1.0589269191759534,
+      "learning_rate": 5e-06,
+      "loss": 1.0923,
+      "step": 80
+    },
+    {
+      "epoch": 2.954954954954955,
+      "eval_loss": 1.1392163038253784,
+      "eval_runtime": 29.1201,
+      "eval_samples_per_second": 25.687,
+      "eval_steps_per_second": 0.412,
+      "step": 81
+    },
+    {
+      "epoch": 2.954954954954955,
+      "step": 81,
+      "total_flos": 135468637224960.0,
+      "train_loss": 1.2098971104916232,
+      "train_runtime": 5037.896,
+      "train_samples_per_second": 8.452,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 81,
+  "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": 135468637224960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}