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: llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_0p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_0p
 
-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_25000tasks_0p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5040
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9962264150943394,
+    "eval_loss": 0.5040494799613953,
+    "eval_runtime": 102.6465,
+    "eval_samples_per_second": 8.7,
+    "eval_steps_per_second": 0.273,
+    "total_flos": 166038066954240.0,
+    "train_loss": 0.14297527737087673,
+    "train_runtime": 5416.3296,
+    "train_samples_per_second": 9.388,
+    "train_steps_per_second": 0.018
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9962264150943394,
+    "eval_loss": 0.5040494799613953,
+    "eval_runtime": 102.6465,
+    "eval_samples_per_second": 8.7,
+    "eval_steps_per_second": 0.273
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9962264150943394,
+    "total_flos": 166038066954240.0,
+    "train_loss": 0.14297527737087673,
+    "train_runtime": 5416.3296,
+    "train_samples_per_second": 9.388,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9962264150943394,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 21.225251759950595,
+      "learning_rate": 5e-06,
+      "loss": 0.731,
+      "step": 10
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 1.0446485810142683,
+      "learning_rate": 5e-06,
+      "loss": 0.6309,
+      "step": 20
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 0.7875866396966491,
+      "learning_rate": 5e-06,
+      "loss": 0.5802,
+      "step": 30
+    },
+    {
+      "epoch": 0.9962264150943396,
+      "eval_loss": 0.5490819811820984,
+      "eval_runtime": 104.8082,
+      "eval_samples_per_second": 8.52,
+      "eval_steps_per_second": 0.267,
+      "step": 33
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 1.0679356010512076,
+      "learning_rate": 5e-06,
+      "loss": 0.5315,
+      "step": 40
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.8804894677784992,
+      "learning_rate": 5e-06,
+      "loss": 0.5003,
+      "step": 50
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 0.8917839639052948,
+      "learning_rate": 5e-06,
+      "loss": 0.4917,
+      "step": 60
+    },
+    {
+      "epoch": 1.9924528301886792,
+      "eval_loss": 0.511838436126709,
+      "eval_runtime": 105.8422,
+      "eval_samples_per_second": 8.437,
+      "eval_steps_per_second": 0.265,
+      "step": 66
+    },
+    {
+      "epoch": 2.120754716981132,
+      "grad_norm": 1.36131330698531,
+      "learning_rate": 5e-06,
+      "loss": 0.4456,
+      "step": 70
+    },
+    {
+      "epoch": 2.422641509433962,
+      "grad_norm": 1.2433331474192404,
+      "learning_rate": 5e-06,
+      "loss": 0.431,
+      "step": 80
+    },
+    {
+      "epoch": 2.7245283018867923,
+      "grad_norm": 1.139861283901317,
+      "learning_rate": 5e-06,
+      "loss": 0.4262,
+      "step": 90
+    },
+    {
+      "epoch": 2.9962264150943394,
+      "eval_loss": 0.5040494799613953,
+      "eval_runtime": 106.7796,
+      "eval_samples_per_second": 8.363,
+      "eval_steps_per_second": 0.262,
+      "step": 99
+    },
+    {
+      "epoch": 2.9962264150943394,
+      "step": 99,
+      "total_flos": 166038066954240.0,
+      "train_loss": 0.14297527737087673,
+      "train_runtime": 5416.3296,
+      "train_samples_per_second": 9.388,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 99,
+  "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": 166038066954240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}