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: stackoverflow_5000tasks_.75p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackoverflow_5000tasks_.75p
 
-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/stackoverflow_5000tasks_.75p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7304
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.981818181818182,
+    "eval_loss": 0.7303929924964905,
+    "eval_runtime": 23.1495,
+    "eval_samples_per_second": 40.001,
+    "eval_steps_per_second": 0.648,
+    "total_flos": 170644419379200.0,
+    "train_loss": 0.7476259855663075,
+    "train_runtime": 3636.8482,
+    "train_samples_per_second": 14.512,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.981818181818182,
+    "eval_loss": 0.7303929924964905,
+    "eval_runtime": 23.1495,
+    "eval_samples_per_second": 40.001,
+    "eval_steps_per_second": 0.648
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.981818181818182,
+    "total_flos": 170644419379200.0,
+    "train_loss": 0.7476259855663075,
+    "train_runtime": 3636.8482,
+    "train_samples_per_second": 14.512,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.981818181818182,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 6.897545667801919,
+      "learning_rate": 5e-06,
+      "loss": 0.9216,
+      "step": 10
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 3.7987497029563437,
+      "learning_rate": 5e-06,
+      "loss": 0.8217,
+      "step": 20
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 1.6786976414779686,
+      "learning_rate": 5e-06,
+      "loss": 0.784,
+      "step": 30
+    },
+    {
+      "epoch": 0.9890909090909091,
+      "eval_loss": 0.7713841795921326,
+      "eval_runtime": 24.4352,
+      "eval_samples_per_second": 37.896,
+      "eval_steps_per_second": 0.614,
+      "step": 34
+    },
+    {
+      "epoch": 1.170909090909091,
+      "grad_norm": 1.3947991819307355,
+      "learning_rate": 5e-06,
+      "loss": 0.8212,
+      "step": 40
+    },
+    {
+      "epoch": 1.461818181818182,
+      "grad_norm": 1.4557421257115206,
+      "learning_rate": 5e-06,
+      "loss": 0.7242,
+      "step": 50
+    },
+    {
+      "epoch": 1.7527272727272727,
+      "grad_norm": 1.6761487724396338,
+      "learning_rate": 5e-06,
+      "loss": 0.7099,
+      "step": 60
+    },
+    {
+      "epoch": 1.9854545454545454,
+      "eval_loss": 0.7391919493675232,
+      "eval_runtime": 24.121,
+      "eval_samples_per_second": 38.39,
+      "eval_steps_per_second": 0.622,
+      "step": 68
+    },
+    {
+      "epoch": 2.050909090909091,
+      "grad_norm": 0.87855024715639,
+      "learning_rate": 5e-06,
+      "loss": 0.7641,
+      "step": 70
+    },
+    {
+      "epoch": 2.341818181818182,
+      "grad_norm": 1.7629080076755046,
+      "learning_rate": 5e-06,
+      "loss": 0.6552,
+      "step": 80
+    },
+    {
+      "epoch": 2.632727272727273,
+      "grad_norm": 0.9203794085894584,
+      "learning_rate": 5e-06,
+      "loss": 0.6497,
+      "step": 90
+    },
+    {
+      "epoch": 2.923636363636364,
+      "grad_norm": 0.6126232896883246,
+      "learning_rate": 5e-06,
+      "loss": 0.6438,
+      "step": 100
+    },
+    {
+      "epoch": 2.981818181818182,
+      "eval_loss": 0.7303929924964905,
+      "eval_runtime": 23.3096,
+      "eval_samples_per_second": 39.726,
+      "eval_steps_per_second": 0.644,
+      "step": 102
+    },
+    {
+      "epoch": 2.981818181818182,
+      "step": 102,
+      "total_flos": 170644419379200.0,
+      "train_loss": 0.7476259855663075,
+      "train_runtime": 3636.8482,
+      "train_samples_per_second": 14.512,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 102,
+  "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": 170644419379200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}