Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-7B-Instruct
-datasets: simplescaling/s1K-1.1_tokenized
 library_name: transformers
 model_name: Qwen-7B-SFT-S1
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen-7B-SFT-S1
 
-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 [simplescaling/s1K-1.1_tokenized](https://huggingface.co/datasets/simplescaling/s1K-1.1_tokenized) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,17 +27,17 @@ 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/fandou-team/huggingface/runs/wdkto3jb) 
+[<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/fandou-team/huggingface/runs/px8v53mb) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0.dev0
-- Transformers: 4.50.0.dev0
+- TRL: 0.15.2
+- Transformers: 4.49.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.1
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 8.208456082469683e+16,
-    "train_loss": 0.763681680386346,
-    "train_runtime": 47391.6339,
+    "total_flos": 100755151257600.0,
+    "train_loss": 0.47903451394183727,
+    "train_runtime": 14467.9344,
     "train_samples": 1000,
-    "train_samples_per_second": 1.037,
-    "train_steps_per_second": 0.065
+    "train_samples_per_second": 3.396,
+    "train_steps_per_second": 0.213
 }

generation_config.json

@@ -5,5 +5,5 @@
     151643
   ],
   "pad_token_id": 151643,
-  "transformers_version": "4.50.0.dev0"
+  "transformers_version": "4.49.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 8.208456082469683e+16,
-    "train_loss": 0.763681680386346,
-    "train_runtime": 47391.6339,
+    "total_flos": 100755151257600.0,
+    "train_loss": 0.47903451394183727,
+    "train_runtime": 14467.9344,
     "train_samples": 1000,
-    "train_samples_per_second": 1.037,
-    "train_steps_per_second": 0.065
+    "train_samples_per_second": 3.396,
+    "train_steps_per_second": 0.213
 }