Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-7B
-datasets: simplescaling/s1K-1.1
 library_name: transformers
 model_name: Qwen-2.5-7B-Simple-RL
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen-2.5-7B-Simple-RL
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) on the [simplescaling/s1K-1.1](https://huggingface.co/datasets/simplescaling/s1K-1.1) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +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/224015062-chinese-university-of-hong-kong-shenzhen/huggingface/runs/a4a15ba6) 
+[<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/224015062-chinese-university-of-hong-kong-shenzhen/huggingface/runs/xat7vdik) 
 
 
 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": 0.0031312393787499915,
-    "train_runtime": 3307.7091,
+    "train_loss": 0.0,
+    "train_runtime": 5.0189,
     "train_samples": 998,
-    "train_samples_per_second": 0.302,
-    "train_steps_per_second": 0.002
+    "train_samples_per_second": 198.848,
+    "train_steps_per_second": 1.395
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 152064

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": 0.0031312393787499915,
-    "train_runtime": 3307.7091,
+    "train_loss": 0.0,
+    "train_runtime": 5.0189,
     "train_samples": 998,
-    "train_samples_per_second": 0.302,
-    "train_steps_per_second": 0.002
+    "train_samples_per_second": 198.848,
+    "train_steps_per_second": 1.395
 }

trainer_state.json

@@ -35,19 +35,13 @@
       "step": 5
     },
     {
-      "completion_length": 768.3912982940674,
       "epoch": 0.896,
-      "kl": 0.001620173454284668,
-      "reward": 0.4889322998933494,
-      "reward_std": 0.05055095534771681,
-      "rewards/accuracy_reward": 0.4889322998933494,
-      "rewards/format_reward": 0.0,
       "step": 7,
       "total_flos": 0.0,
-      "train_loss": 0.0031312393787499915,
-      "train_runtime": 3307.7091,
-      "train_samples_per_second": 0.302,
-      "train_steps_per_second": 0.002
+      "train_loss": 0.0,
+      "train_runtime": 5.0189,
+      "train_samples_per_second": 198.848,
+      "train_steps_per_second": 1.395
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9c3075c2c2b0f632e0ca15c81577e6c5833f1f37f10237a1b35eb27fde5128
+oid sha256:4e65ee56a5701b8445dc0c9d735738ae75ac41d7a7d5eb9efff23e9f669ca3eb
 size 7864