Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-datasets: ZJU-REAL/InftyThink
 library_name: transformers
 model_name: OpenR1-Distill-7B
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for OpenR1-Distill-7B
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [ZJU-REAL/InftyThink](https://huggingface.co/datasets/ZJU-REAL/InftyThink) dataset.
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
 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/mingzeli/infinitythink/runs/usn36av9) 
+[<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/mingzeli/infinitythink/runs/xp9bvnb3) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 3.2446368662840934e+18,
-    "train_loss": 0.4391684692912486,
-    "train_runtime": 19223.6085,
-    "train_samples": 279477,
-    "train_samples_per_second": 72.691,
-    "train_steps_per_second": 0.284
+    "total_flos": 2.4054064625943183e+18,
+    "train_loss": 0.42931601253507656,
+    "train_runtime": 13617.0429,
+    "train_samples": 130637,
+    "train_samples_per_second": 47.968,
+    "train_steps_per_second": 0.188
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 3.2446368662840934e+18,
-    "train_loss": 0.4391684692912486,
-    "train_runtime": 19223.6085,
-    "train_samples": 279477,
-    "train_samples_per_second": 72.691,
-    "train_steps_per_second": 0.284
+    "total_flos": 2.4054064625943183e+18,
+    "train_loss": 0.42931601253507656,
+    "train_runtime": 13617.0429,
+    "train_samples": 130637,
+    "train_samples_per_second": 47.968,
+    "train_steps_per_second": 0.188
 }