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/gongc1995-city-university-of-hong-kong/huggingface/runs/anhd3jid) 
+[<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/gongc1995-city-university-of-hong-kong/huggingface/runs/9yt5mw64) 
 
 
 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

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0063387130697568255,
-    "train_runtime": 1106.1477,
+    "train_loss": 0.0,
+    "train_runtime": 1.6296,
     "train_samples": 100,
-    "train_samples_per_second": 0.271,
-    "train_steps_per_second": 0.003
+    "train_samples_per_second": 184.095,
+    "train_steps_per_second": 1.841
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0063387130697568255,
-    "train_runtime": 1106.1477,
+    "train_loss": 0.0,
+    "train_runtime": 1.6296,
     "train_samples": 100,
-    "train_samples_per_second": 0.271,
-    "train_steps_per_second": 0.003
+    "train_samples_per_second": 184.095,
+    "train_steps_per_second": 1.841
 }

trainer_state.json

@@ -9,21 +9,13 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "clip_ratio": 0.0,
-      "completion_length": 629.5277777777778,
       "epoch": 2.8,
-      "kl": 8.5857179429796e-05,
-      "reward": 0.851686547199885,
-      "reward_std": 0.37670273126827347,
-      "rewards/accuracy_reward": 0.3849206546114551,
-      "rewards/format_reward": 0.1567460395809677,
-      "rewards/tag_count_reward": 0.3100198532144229,
       "step": 3,
       "total_flos": 0.0,
-      "train_loss": 0.0063387130697568255,
-      "train_runtime": 1106.1477,
-      "train_samples_per_second": 0.271,
-      "train_steps_per_second": 0.003
+      "train_loss": 0.0,
+      "train_runtime": 1.6296,
+      "train_samples_per_second": 184.095,
+      "train_steps_per_second": 1.841
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f63a9cf71e93599321d35b5fcca2440d96c6d7bf5e187309ee44315a076938c6
+oid sha256:e6e25df1a6475c7c5f1815a6b0d296cd7dccfd262fc4fa85b7c9131060f6cd39
 size 8056