End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_math_qa_101112_1760638065
 
-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 math_qa dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0976
+- Loss: 1.0945
 - Num Input Tokens Seen: 77914328
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 1.094519853591919,
+    "eval_runtime": 45.4849,
+    "eval_samples_per_second": 65.604,
+    "eval_steps_per_second": 16.401,
+    "num_input_tokens_seen": 77914328,
+    "total_flos": 3.508571438521123e+18,
+    "train_loss": 1.0935145752146587,
+    "train_runtime": 26420.3063,
+    "train_samples_per_second": 20.328,
+    "train_steps_per_second": 5.082
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 1.094519853591919,
+    "eval_runtime": 45.4849,
+    "eval_samples_per_second": 65.604,
+    "eval_steps_per_second": 16.401,
+    "num_input_tokens_seen": 77914328
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 77914328,
+    "total_flos": 3.508571438521123e+18,
+    "train_loss": 1.0935145752146587,
+    "train_runtime": 26420.3063,
+    "train_samples_per_second": 20.328,
+    "train_steps_per_second": 5.082
+}