Model save

README.md

@@ -1,19 +1,17 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-datasets: knoveleng/open-rs
 library_name: transformers
 model_name: MMR-DAPO
 tags:
 - generated_from_trainer
-- open-r1
-- dapo
 - trl
+- dapo
 licence: license
 ---
 
 # Model Card for MMR-DAPO
 
-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 [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) 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
@@ -38,7 +36,7 @@ This model was trained with DAPO, a method introduced in [DAPO: An Open-Source L
 
 - TRL: 0.16.0.dev0
 - Transformers: 4.57.1
-- Pytorch: 2.5.1+cu121
+- Pytorch: 2.5.1
 - Datasets: 3.2.0
 - Tokenizers: 0.22.1
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.02002632762067895,
-    "train_runtime": 76982.959,
+    "train_loss": 0.025048209376691374,
+    "train_runtime": 15561.5871,
     "train_samples": 7000,
-    "train_samples_per_second": 0.312,
+    "train_samples_per_second": 0.308,
     "train_steps_per_second": 0.006
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.02002632762067895,
-    "train_runtime": 76982.959,
+    "train_loss": 0.025048209376691374,
+    "train_runtime": 15561.5871,
     "train_samples": 7000,
-    "train_samples_per_second": 0.312,
+    "train_samples_per_second": 0.308,
     "train_steps_per_second": 0.006
 }