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_matheducators
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_matheducators
 
-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_matheducators dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9905
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9130434782608696,
+    "eval_loss": 0.9905301332473755,
+    "eval_runtime": 7.3496,
+    "eval_samples_per_second": 42.179,
+    "eval_steps_per_second": 0.68,
+    "total_flos": 55066849443840.0,
+    "train_loss": 1.0955960244843455,
+    "train_runtime": 1391.7626,
+    "train_samples_per_second": 12.662,
+    "train_steps_per_second": 0.024
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9130434782608696,
+    "eval_loss": 0.9905301332473755,
+    "eval_runtime": 7.3496,
+    "eval_samples_per_second": 42.179,
+    "eval_steps_per_second": 0.68
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9130434782608696,
+    "total_flos": 55066849443840.0,
+    "train_loss": 1.0955960244843455,
+    "train_runtime": 1391.7626,
+    "train_samples_per_second": 12.662,
+    "train_steps_per_second": 0.024
+}

trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9130434782608696,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 7.130644673359026,
+      "learning_rate": 5e-06,
+      "loss": 1.1687,
+      "step": 10
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "eval_loss": 1.0667738914489746,
+      "eval_runtime": 8.2133,
+      "eval_samples_per_second": 37.743,
+      "eval_steps_per_second": 0.609,
+      "step": 11
+    },
+    {
+      "epoch": 1.7608695652173914,
+      "grad_norm": 2.6728196396174853,
+      "learning_rate": 5e-06,
+      "loss": 1.1156,
+      "step": 20
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "eval_loss": 1.0284854173660278,
+      "eval_runtime": 8.249,
+      "eval_samples_per_second": 37.58,
+      "eval_steps_per_second": 0.606,
+      "step": 22
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 1.6279998496954122,
+      "learning_rate": 5e-06,
+      "loss": 1.0483,
+      "step": 30
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "eval_loss": 0.9905301332473755,
+      "eval_runtime": 7.1515,
+      "eval_samples_per_second": 43.347,
+      "eval_steps_per_second": 0.699,
+      "step": 33
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "step": 33,
+      "total_flos": 55066849443840.0,
+      "train_loss": 1.0955960244843455,
+      "train_runtime": 1391.7626,
+      "train_samples_per_second": 12.662,
+      "train_steps_per_second": 0.024
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 33,
+  "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": 55066849443840.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}