Downloads · 30 days
11
7% of all-time downloads
huseyinatahaninan/appworld_distillation_sft_v2-SFT-Qwen3-14B
appworld_distillation_sft_v2-SFT-Qwen3-14B is a text generation model from huseyinatahaninan. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
11
7% of all-time downloads
All-time downloads
154
Public
Parameters
14.8B
29.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors29.5 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Qwen/Qwen3-14B on the appworld_distillation_sft_v2 dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9822 | 1.0 | 2 | 1.0912 |
| 0.942 | 2.0 | 4 | 1.0091 |
| 0.8898 | 3.0 | 6 | 0.9136 |
| 0.8198 | 4.0 | 8 | 0.8144 |
| 0.7626 | 5.0 | 10 | 0.7954 |
| 0.6661 | 6.0 | 12 | 0.7088 |
| 0.6173 | 7.0 | 14 | 0.6720 |
| 0.5818 | 8.0 | 16 | 0.6458 |
| 0.5537 | 9.0 | 18 | 0.6342 |
| 0.4807 | 10.0 | 20 | 0.6177 |
| 0.439 | 11.0 | 22 | 0.6065 |
| 0.3972 | 12.0 | 24 | 0.6031 |
| 0.3871 | 13.0 | 26 | 0.6017 |
| 0.3619 | 14.0 | 28 | 0.6034 |
| 0.3209 | 15.0 | 30 | 0.6126 |
| 0.3113 | 16.0 | 32 | 0.6090 |
| 0.2768 | 17.0 | 34 | 0.6095 |
| 0.2749 | 18.0 | 36 | 0.6223 |
| 0.2563 | 19.0 | 38 | 0.6323 |
| 0.2355 | 20.0 | 40 | 0.6318 |
| 0.2367 | 21.0 | 42 | 0.6320 |
| 0.2243 | 22.0 | 44 | 0.6353 |
| 0.2356 | 23.0 | 46 | 0.6386 |
| 0.2343 | 24.0 | 48 | 0.6403 |
| 0.2294 | 25.0 | 50 | 0.6408 |