End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_hellaswag_42_1760637624
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the hellaswag dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7598
 - Num Input Tokens Seen: 193996096

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.7598461508750916,
+    "eval_runtime": 222.4585,
+    "eval_samples_per_second": 35.876,
+    "eval_steps_per_second": 8.972,
+    "num_input_tokens_seen": 193996096,
+    "total_flos": 8.735556522852483e+18,
+    "train_loss": 0.4391089803562205,
+    "train_runtime": 42168.6289,
+    "train_samples_per_second": 15.141,
+    "train_steps_per_second": 3.785
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.7598461508750916,
+    "eval_runtime": 222.4585,
+    "eval_samples_per_second": 35.876,
+    "eval_steps_per_second": 8.972,
+    "num_input_tokens_seen": 193996096
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 193996096,
+    "total_flos": 8.735556522852483e+18,
+    "train_loss": 0.4391089803562205,
+    "train_runtime": 42168.6289,
+    "train_samples_per_second": 15.141,
+    "train_steps_per_second": 3.785
+}