End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # OpenR1-Math-Raw-all-correct-5k
 
-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 neginr/OpenR1-Math-Raw-all-correct-5k dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5246,
-    "train_samples_per_second": 13863.535,
-    "train_steps_per_second": 144.181
+    "train_runtime": 2.6671,
+    "train_samples_per_second": 13122.755,
+    "train_steps_per_second": 136.477
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5246,
-    "train_samples_per_second": 13863.535,
-    "train_steps_per_second": 144.181
+    "train_runtime": 2.6671,
+    "train_samples_per_second": 13122.755,
+    "train_steps_per_second": 136.477
 }

trainer_state.json

@@ -2561,9 +2561,9 @@
       "step": 364,
       "total_flos": 3.947982283988664e+17,
       "train_loss": 0.0,
-      "train_runtime": 2.5246,
-      "train_samples_per_second": 13863.535,
-      "train_steps_per_second": 144.181
+      "train_runtime": 2.6671,
+      "train_samples_per_second": 13122.755,
+      "train_steps_per_second": 136.477
     }
   ],
   "logging_steps": 1,