End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # e1_science_longest_r1
 
-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 mlfoundations-dev/e1_science_longest_r1 dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 4.9869587897756915,
     "total_flos": 2.8011398523411825e+18,
     "train_loss": 0.0,
-    "train_runtime": 5.0033,
-    "train_samples_per_second": 30641.958,
-    "train_steps_per_second": 238.844
+    "train_runtime": 3.7901,
+    "train_samples_per_second": 40449.714,
+    "train_steps_per_second": 315.292
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 4.9869587897756915,
     "total_flos": 2.8011398523411825e+18,
     "train_loss": 0.0,
-    "train_runtime": 5.0033,
-    "train_samples_per_second": 30641.958,
-    "train_steps_per_second": 238.844
+    "train_runtime": 3.7901,
+    "train_samples_per_second": 40449.714,
+    "train_steps_per_second": 315.292
 }

trainer_state.json

@@ -8378,9 +8378,9 @@
       "step": 1195,
       "total_flos": 2.8011398523411825e+18,
       "train_loss": 0.0,
-      "train_runtime": 5.0033,
-      "train_samples_per_second": 30641.958,
-      "train_steps_per_second": 238.844
+      "train_runtime": 3.7901,
+      "train_samples_per_second": 40449.714,
+      "train_steps_per_second": 315.292
     }
   ],
   "logging_steps": 1,