Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-7B
-datasets: DigitalLearningGmbH/MATH-lighteval
 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 [DigitalLearningGmbH/MATH-lighteval](https://huggingface.co/datasets/DigitalLearningGmbH/MATH-lighteval) 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
@@ -29,18 +27,18 @@ 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/wanghaichuan/huggingface/runs/eovbfgxo) 
+[<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/wanghaichuan/huggingface/runs/13u15bim) 
 
 
 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).
 
 ### Framework versions
 
-- TRL: 0.15.0.dev0
-- Transformers: 4.49.0.dev0
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
 - Pytorch: 2.5.1
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
+- Datasets: 3.4.0
+- Tokenizers: 0.21.1
 
 ## Citations
 

all_results.json

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.0003125647781416774,
-    "eval_runtime": 2181.3395,
-    "eval_samples": 5000,
-    "eval_samples_per_second": 2.292,
-    "eval_steps_per_second": 0.024,
     "total_flos": 0.0,
-    "train_loss": 1.2402063848306162,
-    "train_runtime": 35030.8408,
+    "train_loss": 0.04672712115020638,
+    "train_runtime": 102271.8167,
     "train_samples": 7500,
-    "train_samples_per_second": 0.214,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 0.073,
+    "train_steps_per_second": 0.009
 }

config.json

@@ -19,11 +19,11 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
-  "sliding_window": null,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0.dev0",
-  "use_cache": true,
+  "transformers_version": "4.49.0",
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json

@@ -2,5 +2,5 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
-  "transformers_version": "4.49.0.dev0"
+  "transformers_version": "4.49.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e69be4d87367acb672fc350b2f7046dd9e2cf9ec618cc0dec52498909317321
+oid sha256:7dcc0bde40bdebe6c68a646753ed9c5a622e3ee940a1d93996cf3a2818fd425e
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3458aa7ffac11ae8ca5246d72a62a9f8ec01bf58697b62c79c6a7768d1339b2b
+oid sha256:32d6e2b1ded3b5ac1353a256c3c88dcf8a34c5a35bf230f0383023cf8680e33c
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5643906fe24b7997e2b7526af64e1c67d031a5c00322502a2da8baaf08965da6
+oid sha256:d0e6d03348992189553c9e4098e91b3c1dd0cea3a1856c8a69824a82c0fa6d2a
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d61362ab237cfd9e3b5983d8f2fca8919a1eda6fd17ca3a62e568b5a98e6542
+oid sha256:559b09a7573e2b791190f0929c6f09e757985fed99f102ea89042f0040a4eab9
 size 1089994880

tokenizer_config.json

@@ -202,7 +202,6 @@
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 1.2402063848306162,
-    "train_runtime": 35030.8408,
+    "train_loss": 0.04672712115020638,
+    "train_runtime": 102271.8167,
     "train_samples": 7500,
-    "train_samples_per_second": 0.214,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 0.073,
+    "train_steps_per_second": 0.009
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4168a8b1403b82181fdcb547faea4b2772074aaa3495cbe3296d7263bc74c14
-size 7480
+oid sha256:c079e39586a2dd2e18ea4f75e053a693fcb56f1cf9f4a09a9df76f1d1ec00fcb
+size 7992