Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen3-8B-Base
-datasets: ZJU-REAL/InftyThink
+base_model: Qwen/Qwen2.5-7B-Instruct
 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 [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) on the [ZJU-REAL/InftyThink](https://huggingface.co/datasets/ZJU-REAL/InftyThink) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-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/mingzeli/infinitythink/runs/2xm9us4q) 
+[<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/p8m5hgmb) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 4.074741815159292e+18,
-    "train_loss": 0.24356672786271724,
-    "train_runtime": 32672.7788,
+    "total_flos": 9.86623593607594e+18,
+    "train_loss": 0.3486980376867475,
+    "train_runtime": 55837.618,
     "train_samples": 279477,
-    "train_samples_per_second": 34.215,
-    "train_steps_per_second": 0.134
+    "train_samples_per_second": 20.021,
+    "train_steps_per_second": 0.078
 }

generation_config.json

@@ -1,6 +1,11 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.54.1"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 4.074741815159292e+18,
-    "train_loss": 0.24356672786271724,
-    "train_runtime": 32672.7788,
+    "total_flos": 9.86623593607594e+18,
+    "train_loss": 0.3486980376867475,
+    "train_runtime": 55837.618,
     "train_samples": 279477,
-    "train_samples_per_second": 34.215,
-    "train_steps_per_second": 0.134
+    "train_samples_per_second": 20.021,
+    "train_steps_per_second": 0.078
 }