End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_math_qa_456_1760637835
 
-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: 0.8015
+- Loss: 0.8014
 - Num Input Tokens Seen: 77891968
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.8014279007911682,
+    "eval_runtime": 70.5042,
+    "eval_samples_per_second": 42.324,
+    "eval_steps_per_second": 10.581,
+    "num_input_tokens_seen": 77891968,
+    "total_flos": 3.507440114363007e+18,
+    "train_loss": 0.8179087050248016,
+    "train_runtime": 29814.1808,
+    "train_samples_per_second": 18.014,
+    "train_steps_per_second": 4.504
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.8014279007911682,
+    "eval_runtime": 70.5042,
+    "eval_samples_per_second": 42.324,
+    "eval_steps_per_second": 10.581,
+    "num_input_tokens_seen": 77891968
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 77891968,
+    "total_flos": 3.507440114363007e+18,
+    "train_loss": 0.8179087050248016,
+    "train_runtime": 29814.1808,
+    "train_samples_per_second": 18.014,
+    "train_steps_per_second": 4.504
+}