Downloads · 30 days
6
1% of all-time downloads
BiggieW/chinese-bert-wwm-finetuned-chnsenticorp
chinese-bert-wwm-finetuned-chnsenticorp is a fill-mask model from BiggieW. Use it when you need the model to fill a missing word. 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
1% of all-time downloads
All-time downloads
446
Public
Repo size
818 MB
Likes
0
Public
Click a slice to open those files.
.bin409 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of hfl/chinese-bert-wwm on a small subset of chnsenticorp 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 |
|---|---|---|---|
| 1.0096 | 1.0 | 15 | 3.7742 |
| 1.7336 | 2.0 | 30 | 3.9102 |
| 2.5286 | 3.0 | 45 | 3.4744 |
| 2.8892 | 4.0 | 60 | 3.1142 |
| 2.7188 | 5.0 | 75 | 2.7622 |
| 2.7923 | 6.0 | 90 | 3.1119 |
| 2.4094 | 7.0 | 105 | 3.0426 |
| 2.5928 | 8.0 | 120 | 2.8928 |
| 2.4072 | 9.0 | 135 | 2.9462 |
| 2.4349 | 10.0 | 150 | 2.7645 |