End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_mrpc_101112_1760638023
 
-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: 0.1069
+- Loss: 0.1057
 - Num Input Tokens Seen: 6767120
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.10569468885660172,
+    "eval_runtime": 4.5792,
+    "eval_samples_per_second": 80.145,
+    "eval_steps_per_second": 20.091,
+    "num_input_tokens_seen": 6767120,
+    "total_flos": 3.047283378978816e+17,
+    "train_loss": 0.12708782535497343,
+    "train_runtime": 2732.6214,
+    "train_samples_per_second": 24.16,
+    "train_steps_per_second": 6.045
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.10569468885660172,
+    "eval_runtime": 4.5792,
+    "eval_samples_per_second": 80.145,
+    "eval_steps_per_second": 20.091,
+    "num_input_tokens_seen": 6767120
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 6767120,
+    "total_flos": 3.047283378978816e+17,
+    "train_loss": 0.12708782535497343,
+    "train_runtime": 2732.6214,
+    "train_samples_per_second": 24.16,
+    "train_steps_per_second": 6.045
+}