Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 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-Distill
 
-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 [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) 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/kawamuramasaki/open-r1/runs/gkc638sj) 
+[<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/kawamuramasaki/open-r1/runs/jv1rnqpw) 
 
 
 This model was trained with SFT.
@@ -37,9 +35,9 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.16.0.dev0
-- Transformers: 4.49.0.dev0
+- Transformers: 4.49.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

all_results.json

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.7649670839309692,
-    "eval_runtime": 2.4402,
-    "eval_samples": 100,
-    "eval_samples_per_second": 52.866,
-    "eval_steps_per_second": 3.688,
-    "total_flos": 76774385909760.0,
-    "train_loss": 0.7816428508532154,
-    "train_runtime": 1403.6888,
-    "train_samples": 16610,
-    "train_samples_per_second": 15.404,
-    "train_steps_per_second": 0.24
+    "total_flos": 488051495141376.0,
+    "train_loss": 0.6885459087119324,
+    "train_runtime": 16426.9677,
+    "train_samples": 93733,
+    "train_samples_per_second": 33.366,
+    "train_steps_per_second": 0.261
 }

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.49.0.dev0"
+  "transformers_version": "4.49.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 76774385909760.0,
-    "train_loss": 0.7816428508532154,
-    "train_runtime": 1403.6888,
-    "train_samples": 16610,
-    "train_samples_per_second": 15.404,
-    "train_steps_per_second": 0.24
+    "total_flos": 488051495141376.0,
+    "train_loss": 0.6885459087119324,
+    "train_runtime": 16426.9677,
+    "train_samples": 93733,
+    "train_samples_per_second": 33.366,
+    "train_steps_per_second": 0.261
 }