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_hinduism
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_hinduism
 
-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_hinduism dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9551
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9390243902439024,
+    "eval_loss": 0.9551071524620056,
+    "eval_runtime": 13.9754,
+    "eval_samples_per_second": 39.569,
+    "eval_steps_per_second": 0.644,
+    "total_flos": 100292855070720.0,
+    "train_loss": 1.0310721079508463,
+    "train_runtime": 2262.9427,
+    "train_samples_per_second": 13.908,
+    "train_steps_per_second": 0.027
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9390243902439024,
+    "eval_loss": 0.9551071524620056,
+    "eval_runtime": 13.9754,
+    "eval_samples_per_second": 39.569,
+    "eval_steps_per_second": 0.644
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9390243902439024,
+    "total_flos": 100292855070720.0,
+    "train_loss": 1.0310721079508463,
+    "train_runtime": 2262.9427,
+    "train_samples_per_second": 13.908,
+    "train_steps_per_second": 0.027
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9390243902439024,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 10.282097247315418,
+      "learning_rate": 5e-06,
+      "loss": 1.1902,
+      "step": 10
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.984433069915849,
+      "learning_rate": 5e-06,
+      "loss": 1.0743,
+      "step": 20
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_loss": 1.0350981950759888,
+      "eval_runtime": 14.6976,
+      "eval_samples_per_second": 37.625,
+      "eval_steps_per_second": 0.612,
+      "step": 20
+    },
+    {
+      "epoch": 1.4695121951219512,
+      "grad_norm": 1.6186880804180996,
+      "learning_rate": 5e-06,
+      "loss": 1.069,
+      "step": 30
+    },
+    {
+      "epoch": 1.9573170731707317,
+      "grad_norm": 1.6522315978387943,
+      "learning_rate": 5e-06,
+      "loss": 0.971,
+      "step": 40
+    },
+    {
+      "epoch": 1.9573170731707317,
+      "eval_loss": 0.9772650599479675,
+      "eval_runtime": 14.3989,
+      "eval_samples_per_second": 38.406,
+      "eval_steps_per_second": 0.625,
+      "step": 40
+    },
+    {
+      "epoch": 2.451219512195122,
+      "grad_norm": 2.146880241938306,
+      "learning_rate": 5e-06,
+      "loss": 0.9811,
+      "step": 50
+    },
+    {
+      "epoch": 2.9390243902439024,
+      "grad_norm": 2.241864677555473,
+      "learning_rate": 5e-06,
+      "loss": 0.9008,
+      "step": 60
+    },
+    {
+      "epoch": 2.9390243902439024,
+      "eval_loss": 0.9551071524620056,
+      "eval_runtime": 13.407,
+      "eval_samples_per_second": 41.247,
+      "eval_steps_per_second": 0.671,
+      "step": 60
+    },
+    {
+      "epoch": 2.9390243902439024,
+      "step": 60,
+      "total_flos": 100292855070720.0,
+      "train_loss": 1.0310721079508463,
+      "train_runtime": 2262.9427,
+      "train_samples_per_second": 13.908,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "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": 100292855070720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}