End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
+datasets: yentinglin/s1K-1.1-trl-format
 library_name: transformers
 model_name: Deepseek-Coder-V2-Lite-13B-Instruct-sft-s1K
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Deepseek-Coder-V2-Lite-13B-Instruct-sft-s1K
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct) on the [yentinglin/s1K-1.1-trl-format](https://huggingface.co/datasets/yentinglin/s1K-1.1-trl-format) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -54,7 +54,7 @@
   "topk_method": "greedy",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 102400
 }

training.log

@@ -215,3 +215,5 @@ weight_decay=0.0,
   (lm_head): Linear(in_features=2048, out_features=102400, bias=False)
 )
 2025-08-14 03:40:52 - INFO - __main__ - *** Save model ***
+2025-08-14 03:52:38 - INFO - __main__ - Model saved to data/DeepSeek-Coder-V2-Lite-Instruct/sft/s1K
+2025-08-14 03:52:38 - INFO - __main__ - Pushing to hub...