Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: ZJU-REAL/InftyThink
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 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/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) 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/m37j5hji) 
+[<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/zld6e5ib) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 4015528576122880.0,
-    "train_loss": 0.5220075631097996,
-    "train_runtime": 18814.5531,
+    "total_flos": 3.616368400286089e+18,
+    "train_loss": 0.38786625415632575,
+    "train_runtime": 21072.6897,
     "train_samples": 279477,
-    "train_samples_per_second": 74.271,
-    "train_steps_per_second": 0.29
+    "train_samples_per_second": 66.313,
+    "train_steps_per_second": 0.259
 }

generation_config.json

@@ -1,11 +1,9 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 151646,
   "do_sample": true,
-  "eos_token_id": 151645,
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
   "transformers_version": "4.54.1"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 4015528576122880.0,
-    "train_loss": 0.5220075631097996,
-    "train_runtime": 18814.5531,
+    "total_flos": 3.616368400286089e+18,
+    "train_loss": 0.38786625415632575,
+    "train_runtime": 21072.6897,
     "train_samples": 279477,
-    "train_samples_per_second": 74.271,
-    "train_steps_per_second": 0.29
+    "train_samples_per_second": 66.313,
+    "train_steps_per_second": 0.259
 }