Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
-datasets: drproduck/open-r1-integral-answer
 library_name: transformers
 model_name: r1-qwen-7b-open-r1-integral-answer
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for r1-qwen-7b-open-r1-integral-answer
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the [drproduck/open-r1-integral-answer](https://huggingface.co/datasets/drproduck/open-r1-integral-answer) dataset.
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,18 +27,18 @@ 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/tuan-team/huggingface/runs/koms2pmv) 
+[<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/drproduck/aimo2/runs/7257127495.69918-069bc575-5b61-4f84-9b9c-1432b7f5db87) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0.dev0
-- Transformers: 4.49.0
+- TRL: 0.16.0
+- Transformers: 4.50.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.2
-- Tokenizers: 0.21.0
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
 
 ## Citations
 

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 57928056832000.0,
-    "train_loss": 0.7219923734664917,
-    "train_runtime": 509.5863,
+    "total_flos": 1.4930386504298529e+19,
+    "train_loss": 0.11175073871796486,
+    "train_runtime": 69821.5108,
     "train_samples": 40979,
-    "train_samples_per_second": 0.063,
-    "train_steps_per_second": 0.002
+    "train_samples_per_second": 5.869,
+    "train_steps_per_second": 0.046
 }

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.49.0"
+  "transformers_version": "4.50.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 57928056832000.0,
-    "train_loss": 0.7219923734664917,
-    "train_runtime": 509.5863,
+    "total_flos": 1.4930386504298529e+19,
+    "train_loss": 0.11175073871796486,
+    "train_runtime": 69821.5108,
     "train_samples": 40979,
-    "train_samples_per_second": 0.063,
-    "train_steps_per_second": 0.002
+    "train_samples_per_second": 5.869,
+    "train_steps_per_second": 0.046
 }