Model save

README.md

@@ -1,10 +1,8 @@
 ---
-datasets: AI-MO/NuminaMath-TIR
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -12,7 +10,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +26,7 @@ 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/757885345/huggingface/runs/2rtkj3pl) 
+[<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/757885345/huggingface/runs/oy9ladut) 
 
 
 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": 1.862645149230957e-09,
-    "train_runtime": 10.0102,
+    "train_runtime": 21.5129,
     "train_samples": 6,
-    "train_samples_per_second": 0.599,
-    "train_steps_per_second": 0.1
+    "train_samples_per_second": 0.279,
+    "train_steps_per_second": 0.046
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f301d59ea1204790a259d51cce69fe450fc2ebb8d3f7b906f8c4a2dd5c787d8
-size 1260367448
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 1.862645149230957e-09,
-    "train_runtime": 10.0102,
+    "train_runtime": 21.5129,
     "train_samples": 6,
-    "train_samples_per_second": 0.599,
-    "train_steps_per_second": 0.1
+    "train_samples_per_second": 0.279,
+    "train_steps_per_second": 0.046
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 1.862645149230957e-09,
-      "train_runtime": 10.0102,
-      "train_samples_per_second": 0.599,
-      "train_steps_per_second": 0.1
+      "train_runtime": 21.5129,
+      "train_samples_per_second": 0.279,
+      "train_steps_per_second": 0.046
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c5641996e688af1f6dbe08328db839beee1d762e2267c4b8c20f826f5073be
+oid sha256:2b11383a208a2bc5300538c17a5a98acb1a32e2cb43dd361fbc6ca03daa3709f
 size 7288