Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-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/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) 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

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 83412022984704.0,
-    "train_loss": 0.6596692787564319,
-    "train_runtime": 4532.2478,
+    "train_loss": 0.0,
+    "train_runtime": 0.0447,
     "train_samples": 93733,
-    "train_samples_per_second": 20.681,
-    "train_steps_per_second": 0.041
+    "train_samples_per_second": 2097588.378,
+    "train_steps_per_second": 4117.613
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 83412022984704.0,
-    "train_loss": 0.6596692787564319,
-    "train_runtime": 4532.2478,
+    "train_loss": 0.0,
+    "train_runtime": 0.0447,
     "train_samples": 93733,
-    "train_samples_per_second": 20.681,
-    "train_steps_per_second": 0.041
+    "train_samples_per_second": 2097588.378,
+    "train_steps_per_second": 4117.613
 }

trainer_state.json

@@ -1669,10 +1669,10 @@
       "epoch": 1.0,
       "step": 184,
       "total_flos": 83412022984704.0,
-      "train_loss": 0.6596692787564319,
-      "train_runtime": 4532.2478,
-      "train_samples_per_second": 20.681,
-      "train_steps_per_second": 0.041
+      "train_loss": 0.0,
+      "train_runtime": 0.0447,
+      "train_samples_per_second": 2097588.378,
+      "train_steps_per_second": 4117.613
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf946c90843b0101e78159d55cefda51ad0d9f222ff0cd910abe39e1ce3ee786
+oid sha256:96a9ad10736c1ecaa6e91ee4d71131de9cdef2036ddd856318e9629d69e9e4f4
 size 7544