Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/verifiable-coding-problems-python
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Code-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Code-GRPO
 
-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 [open-r1/verifiable-coding-problems-python](https://huggingface.co/datasets/open-r1/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/krisezra87-ezras-xyz/huggingface/runs/deegr2ik) 
+[<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/krisezra87-ezras-xyz/huggingface/runs/2lu4u81d) 
 
 
 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": 6.35088568259618e-07,
-    "train_runtime": 79.2443,
+    "train_loss": 6.630085640590623e-07,
+    "train_runtime": 74.8932,
     "train_samples": 35735,
-    "train_samples_per_second": 176.669,
-    "train_steps_per_second": 6.31
+    "train_samples_per_second": 186.933,
+    "train_steps_per_second": 6.676
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 6.35088568259618e-07,
-    "train_runtime": 79.2443,
+    "train_loss": 6.630085640590623e-07,
+    "train_runtime": 74.8932,
     "train_samples": 35735,
-    "train_samples_per_second": 176.669,
-    "train_steps_per_second": 6.31
+    "train_samples_per_second": 186.933,
+    "train_steps_per_second": 6.676
 }

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05607947390513502,
+  "epoch": 0.05619140898278998,
   "eval_steps": 500,
-  "global_step": 501,
+  "global_step": 502,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7525,13 +7525,28 @@
       "step": 501
     },
     {
-      "epoch": 0.05607947390513502,
-      "step": 501,
+      "clip_ratio": 0.0,
+      "completion_length": 405.5714416503906,
+      "epoch": 0.05619140898278998,
+      "grad_norm": 0.009336894378066063,
+      "kl": 0.02581787109375,
+      "learning_rate": 5.001888090068784e-07,
+      "loss": 0.0003,
+      "num_tokens": 28429.0,
+      "reward": 0.10000000894069672,
+      "reward_std": 0.0,
+      "rewards/code_reward": 0.0,
+      "rewards/format_reward": 1.0,
+      "step": 502
+    },
+    {
+      "epoch": 0.05619140898278998,
+      "step": 502,
       "total_flos": 0.0,
-      "train_loss": 6.35088568259618e-07,
-      "train_runtime": 79.2443,
-      "train_samples_per_second": 176.669,
-      "train_steps_per_second": 6.31
+      "train_loss": 6.630085640590623e-07,
+      "train_runtime": 74.8932,
+      "train_samples_per_second": 186.933,
+      "train_steps_per_second": 6.676
     }
   ],
   "logging_steps": 1,