Downloads · 30 days
26
6% of all-time downloads
bert-small-unidic-bpe2
schnell/bert-small-unidic-bpe2
bert-small-unidic-bpe2 is a fill-mask model from schnell. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
468
Public
Repo size
5.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin118 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Feb 22, 2023
- Updated
- Mar 3, 2023
- SHA
- 5483fb95
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bert-small-unidic-bpe2
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5665
- Accuracy: 0.6690
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 768
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 14
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.111 | 1.0 | 69473 | 1.9831 | 0.6056 |
| 1.9667 | 2.0 | 138946 | 1.8334 | 0.6277 |
| 1.8918 | 3.0 | 208419 | 1.7656 | 0.6376 |
| 1.8518 | 4.0 | 277892 | 1.7219 | 0.6444 |
| 1.8202 | 5.0 | 347365 | 1.6904 | 0.6490 |
| 1.7996 | 6.0 | 416838 | 1.6705 | 0.6524 |
| 1.7767 | 7.0 | 486311 | 1.6479 | 0.6558 |
| 1.7663 | 8.0 | 555784 | 1.6339 | 0.6577 |
| 1.7524 | 9.0 | 625257 | 1.6159 | 0.6611 |
| 1.7398 | 10.0 | 694730 | 1.6020 | 0.6627 |
| 1.7229 | 11.0 | 764203 | 1.5920 | 0.6645 |
| 1.7127 | 12.0 | 833676 | 1.5836 | 0.6658 |
| 1.7011 | 13.0 | 903149 | 1.5737 | 0.6677 |
| 1.7 | 14.0 | 972622 | 1.5665 | 0.6690 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Feb 22, 2023
- Updated
- Mar 3, 2023