End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_mrpc_123_1760637675
 
-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 mrpc dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6401
 - Num Input Tokens Seen: 6014864

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6400911808013916,
+    "eval_runtime": 9.0184,
+    "eval_samples_per_second": 81.389,
+    "eval_steps_per_second": 20.403,
+    "num_input_tokens_seen": 6014864,
+    "total_flos": 2.7084660739394765e+17,
+    "train_loss": 0.1357176489409822,
+    "train_runtime": 1671.0675,
+    "train_samples_per_second": 35.115,
+    "train_steps_per_second": 8.785
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6400911808013916,
+    "eval_runtime": 9.0184,
+    "eval_samples_per_second": 81.389,
+    "eval_steps_per_second": 20.403,
+    "num_input_tokens_seen": 6014864
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 6014864,
+    "total_flos": 2.7084660739394765e+17,
+    "train_loss": 0.1357176489409822,
+    "train_runtime": 1671.0675,
+    "train_samples_per_second": 35.115,
+    "train_steps_per_second": 8.785
+}