Downloads · 30 days
13
17% of all-time downloads
qwertyjas29/medical-CoT-qwen3-v3
medical-CoT-qwen3-v3 is a text generation model from qwertyjas29. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
13
17% of all-time downloads
All-time downloads
75
Public
Repo size
5.8 GB
Likes
0
Public
Click a slice to open those files.
.pt3.9 GB · 63%
From the Hugging Face model README
This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown 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 | Token Accuracy |
|---|---|---|---|---|
| 1.7462 | 0.0870 | 100 | 1.7504 | 0.5748 |
| 1.7454 | 0.1740 | 200 | 1.7122 | 0.5800 |
| 1.6780 | 0.2610 | 300 | 1.6921 | 0.5832 |
| 1.6648 | 0.3481 | 400 | 1.6775 | 0.5849 |
| 1.6587 | 0.4351 | 500 | 1.6667 | 0.5867 |
| 1.6539 | 0.5221 | 600 | 1.6583 | 0.5881 |
| 1.6239 | 0.6091 | 700 | 1.6515 | 0.5892 |
| 1.6510 | 0.6961 | 800 | 1.6464 | 0.5899 |
| 1.6310 | 0.7831 | 900 | 1.6432 | 0.5901 |
| 1.6201 | 0.8701 | 1000 | 1.6415 | 0.5905 |
| 1.6439 | 0.9571 | 1100 | 1.6408 | 0.5908 |
| 1.7867 | 1.0 | 1150 | 1.6408 | 0.5907 |
| 1.6096 | 1.0435 | 1200 | 1.6441 | 0.5902 |
| 1.5954 | 1.1305 | 1300 | 1.6415 | 0.5899 |
| 1.5987 | 1.2175 | 1400 | 1.6383 | 0.5910 |
| 1.6229 | 1.3045 | 1500 | 1.6346 | 0.5916 |
| 1.6102 | 1.3916 | 1600 | 1.6321 | 0.5916 |
| 1.5951 | 1.4786 | 1700 | 1.6297 | 0.5921 |
| 1.5989 | 1.5656 | 1800 | 1.6278 | 0.5924 |
| 1.5738 | 1.6526 | 1900 | 1.6265 | 0.5927 |
| 1.5614 | 1.7396 | 2000 | 1.6259 | 0.5927 |
| 1.6200 | 1.8266 | 2100 | 1.6253 | 0.5928 |
| 1.5960 | 1.9136 | 2200 | 1.6251 | 0.5928 |
| 1.8934 | 2.0 | 2300 | 1.6251 | 0.5929 |