End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_hellaswag_123_1760637745
 
-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: 0.0824
+- Loss: 0.0771
 - Num Input Tokens Seen: 218506144
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.07710938155651093,
+    "eval_runtime": 111.2207,
+    "eval_samples_per_second": 35.884,
+    "eval_steps_per_second": 8.973,
+    "num_input_tokens_seen": 218506144,
+    "total_flos": 9.839490666870866e+18,
+    "train_loss": 0.07811526285345054,
+    "train_runtime": 67479.3134,
+    "train_samples_per_second": 10.644,
+    "train_steps_per_second": 2.661
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.07710938155651093,
+    "eval_runtime": 111.2207,
+    "eval_samples_per_second": 35.884,
+    "eval_steps_per_second": 8.973,
+    "num_input_tokens_seen": 218506144
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 218506144,
+    "total_flos": 9.839490666870866e+18,
+    "train_loss": 0.07811526285345054,
+    "train_runtime": 67479.3134,
+    "train_samples_per_second": 10.644,
+    "train_steps_per_second": 2.661
+}