Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-Math-7B-Instruct
-datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.2-end-start-0.5
+base_model: flyingbugs/Qwen2.5-Math-7B-Instruct
 library_name: transformers
 model_name: Qwen2.5-Math-7B-Instruct-keep-0.2-end-start-0.5-eos
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-Math-7B-Instruct-keep-0.2-end-start-0.5-eos
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the [flyingbugs/OpenR1-Math-220k-pruned-keep-0.2-end-start-0.5](https://huggingface.co/datasets/flyingbugs/OpenR1-Math-220k-pruned-keep-0.2-end-start-0.5) dataset.
+This model is a fine-tuned version of [flyingbugs/Qwen2.5-Math-7B-Instruct](https://huggingface.co/flyingbugs/Qwen2.5-Math-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/jjh233/huggingface/runs/wi9sdg8m) 
+[<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/jjh233/huggingface/runs/u4jcnkdv) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 1.5578375880118895e+19,
-    "train_loss": 0.39975321637486494,
-    "train_runtime": 116840.5239,
+    "train_loss": 0.4592563231913725,
+    "train_runtime": 43286.824,
     "train_samples": 93733,
-    "train_samples_per_second": 0.192,
-    "train_steps_per_second": 0.012
+    "train_samples_per_second": 0.518,
+    "train_steps_per_second": 0.032
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 1.5578375880118895e+19,
-    "train_loss": 0.39975321637486494,
-    "train_runtime": 116840.5239,
+    "train_loss": 0.4592563231913725,
+    "train_runtime": 43286.824,
     "train_samples": 93733,
-    "train_samples_per_second": 0.192,
-    "train_steps_per_second": 0.012
+    "train_samples_per_second": 0.518,
+    "train_steps_per_second": 0.032
 }