Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yuanyige/OpenR1/runs/uclfg0aq) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yuanyige/OpenR1/runs/83pavv6e) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

all_results.json

@@ -7,8 +7,8 @@
     "eval_steps_per_second": 0.025,
     "total_flos": 0.0,
     "train_loss": 18.18843185901642,
-    "train_runtime": 28.8641,
+    "train_runtime": 28.7694,
     "train_samples": 72441,
-    "train_samples_per_second": 3.43,
+    "train_samples_per_second": 3.441,
     "train_steps_per_second": 0.035
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 18.18843185901642,
-    "train_runtime": 28.8641,
+    "train_runtime": 28.7694,
     "train_samples": 72441,
-    "train_samples_per_second": 3.43,
+    "train_samples_per_second": 3.441,
     "train_steps_per_second": 0.035
 }

trainer_state.json

@@ -19,8 +19,8 @@
       "step": 0,
       "total_flos": 0.0,
       "train_loss": 18.18843185901642,
-      "train_runtime": 28.8641,
-      "train_samples_per_second": 3.43,
+      "train_runtime": 28.7694,
+      "train_samples_per_second": 3.441,
       "train_steps_per_second": 0.035
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cb960ae5f3824a0620531afc22d0e5240365c7568a5b3c920037d0ad3450e7
+oid sha256:18b2b87d79dce701d2c1845ef7906b24c20a4c1316dc593d94aa32576dbe9276
 size 7608