Downloads · 30 days
8
2% of all-time downloads
zhiguoxu/bert-base-chinese-finetuned-ner-food_requirement
bert-base-chinese-finetuned-ner-food_requirement is a token classification model from zhiguoxu. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
8
2% of all-time downloads
All-time downloads
391
Public
Repo size
814 MB
Likes
0
Public
Click a slice to open those files.
.bin407 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-chinese 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 | F1 |
|---|---|---|---|---|
| 3.169 | 1.0 | 3 | 1.7537 | 0.0 |
| 1.598 | 2.0 | 6 | 1.0914 | 0.5169 |
| 1.1569 | 3.0 | 9 | 0.6879 | 0.7057 |
| 0.6669 | 4.0 | 12 | 0.4194 | 0.8607 |
| 0.485 | 5.0 | 15 | 0.2528 | 0.9333 |
| 0.2807 | 6.0 | 18 | 0.1476 | 0.9836 |
| 0.2015 | 7.0 | 21 | 0.0834 | 0.9873 |
| 0.1145 | 8.0 | 24 | 0.0484 | 0.9924 |
| 0.0809 | 9.0 | 27 | 0.0283 | 1.0 |
| 0.0495 | 10.0 | 30 | 0.0180 | 1.0 |
| 0.0377 | 11.0 | 33 | 0.0126 | 1.0 |
| 0.0219 | 12.0 | 36 | 0.0095 | 1.0 |
| 0.0216 | 13.0 | 39 | 0.0076 | 1.0 |
| 0.015 | 14.0 | 42 | 0.0065 | 1.0 |
| 0.0176 | 15.0 | 45 | 0.0059 | 1.0 |
| 0.0161 | 16.0 | 48 | 0.0053 | 1.0 |
| 0.0133 | 17.0 | 51 | 0.0050 | 1.0 |
| 0.0119 | 18.0 | 54 | 0.0048 | 1.0 |
| 0.0116 | 19.0 | 57 | 0.0047 | 1.0 |
| 0.0126 | 20.0 | 60 | 0.0046 | 1.0 |