End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft-16k
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the open_r1_math dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.9993856739157145,
     "total_flos": 1.9337325951414436e+18,
-    "train_loss": 0.40084112101655106,
-    "train_runtime": 91247.8765,
-    "train_samples_per_second": 2.141,
-    "train_steps_per_second": 0.134
+    "train_loss": 0.40084019302589413,
+    "train_runtime": 90458.8938,
+    "train_samples_per_second": 2.159,
+    "train_steps_per_second": 0.135
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.9993856739157145,
     "total_flos": 1.9337325951414436e+18,
-    "train_loss": 0.40084112101655106,
-    "train_runtime": 91247.8765,
-    "train_samples_per_second": 2.141,
-    "train_steps_per_second": 0.134
+    "train_loss": 0.40084019302589413,
+    "train_runtime": 90458.8938,
+    "train_samples_per_second": 2.159,
+    "train_steps_per_second": 0.135
 }