Downloads · 30 days
6
4% of all-time downloads
huseyinatahaninan/mixed_agenttuning_2and3_apps_C2re-SFT-Qwen3-8B
mixed_agenttuning_2and3_apps_C2re-SFT-Qwen3-8B 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
6
4% of all-time downloads
All-time downloads
170
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Qwen/Qwen3-8B on the mixed_agenttuning_2and3_apps_C2re 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 |
|---|---|---|---|
| 0.363 | 0.0341 | 100 | 0.4019 |
| 0.2558 | 0.0682 | 200 | 0.3240 |
| 0.2861 | 0.1023 | 300 | 0.3028 |
| 0.2614 | 0.1364 | 400 | 0.2891 |
| 0.2278 | 0.1705 | 500 | 0.2823 |
| 0.2473 | 0.2046 | 600 | 0.2753 |
| 0.2398 | 0.2387 | 700 | 0.2726 |
| 0.2683 | 0.2728 | 800 | 0.2691 |
| 0.2546 | 0.3069 | 900 | 0.2657 |
| 0.2365 | 0.3409 | 1000 | 0.2642 |
| 0.2506 | 0.3750 | 1100 | 0.2614 |
| 0.2168 | 0.4091 | 1200 | 0.2601 |
| 0.2656 | 0.4432 | 1300 | 0.2585 |
| 0.2431 | 0.4773 | 1400 | 0.2571 |
| 0.2554 | 0.5114 | 1500 | 0.2552 |
| 0.245 | 0.5455 | 1600 | 0.2538 |
| 0.2393 | 0.5796 | 1700 | 0.2526 |
| 0.217 | 0.6137 | 1800 | 0.2515 |
| 0.2323 | 0.6478 | 1900 | 0.2506 |
| 0.2324 | 0.6819 | 2000 | 0.2492 |
| 0.2492 | 0.7160 | 2100 | 0.2483 |
| 0.2256 | 0.7501 | 2200 | 0.2480 |
| 0.2261 | 0.7842 | 2300 | 0.2474 |
| 0.2152 | 0.8183 | 2400 | 0.2468 |
| 0.2084 | 0.8524 | 2500 | 0.2463 |
| 0.2237 | 0.8865 | 2600 | 0.2455 |
| 0.2244 | 0.9206 | 2700 | 0.2456 |
| 0.2021 | 0.9547 | 2800 | 0.2453 |
| 0.2381 | 0.9887 | 2900 | 0.2454 |