Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: chansung/verifiable-coding-problems-python
 library_name: transformers
 model_name: Qwen2.5-1.5B-CRL-Open-R1-Code-GRPO-exp1
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-CRL-Open-R1-Code-GRPO-exp1
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [chansung/verifiable-coding-problems-python](https://huggingface.co/datasets/chansung/verifiable-coding-problems-python) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 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/chansung18/huggingface/runs/ekt9nbsx) 
+[<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/chansung18/huggingface/runs/upi517ul) 
 
 
 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": 0.0,
-    "train_runtime": 1.2498,
+    "train_runtime": 1.1082,
     "train_samples": 949,
-    "train_samples_per_second": 1518.669,
-    "train_steps_per_second": 46.408
+    "train_samples_per_second": 1712.724,
+    "train_steps_per_second": 52.338
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 1.2498,
+    "train_runtime": 1.1082,
     "train_samples": 949,
-    "train_samples_per_second": 1518.669,
-    "train_steps_per_second": 46.408
+    "train_samples_per_second": 1712.724,
+    "train_steps_per_second": 52.338
 }

trainer_state.json

@@ -1514,9 +1514,9 @@
       "step": 100,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 1.2498,
-      "train_samples_per_second": 1518.669,
-      "train_steps_per_second": 46.408
+      "train_runtime": 1.1082,
+      "train_samples_per_second": 1712.724,
+      "train_steps_per_second": 52.338
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1fd71891db881a097397969327d52f21ed217f14db9c60387e5a9f621777bd
+oid sha256:65ba1b01efec9e384ca8ec2a49c38a228e6f6e625c6523ecd58a7c022d15f3a1
 size 8440