Downloads · 30 days
18
41% of all-time downloads
multibert_seed37_1311
Tommert25/multibert_seed37_1311
multibert_seed37_1311 is a token classification model from Tommert25. Use it when you need labels on individual words, such as names. 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. --
All-time downloads
44
Public
Parameters
167M
8.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors667 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023
- SHA
- 56b2c6ef
Try a prompt
Base models
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. -->
multibert_seed37_1311
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3744
- Precisions: 0.8548
- Recall: 0.8200
- F-measure: 0.8358
- Accuracy: 0.9371
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: 7.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 37
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 14
Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4464 | 1.0 | 236 | 0.2769 | 0.8836 | 0.7193 | 0.7495 | 0.9197 |
| 0.2278 | 2.0 | 472 | 0.2576 | 0.8850 | 0.7524 | 0.7965 | 0.9296 |
| 0.1314 | 3.0 | 708 | 0.3066 | 0.8740 | 0.7725 | 0.8059 | 0.9284 |
| 0.0964 | 4.0 | 944 | 0.3072 | 0.8267 | 0.7989 | 0.8054 | 0.9311 |
| 0.0612 | 5.0 | 1180 | 0.3229 | 0.8601 | 0.8044 | 0.8297 | 0.9340 |
| 0.0446 | 6.0 | 1416 | 0.3647 | 0.8433 | 0.7686 | 0.7952 | 0.9320 |
| 0.0319 | 7.0 | 1652 | 0.3744 | 0.8548 | 0.8200 | 0.8358 | 0.9371 |
| 0.0192 | 8.0 | 1888 | 0.4170 | 0.8724 | 0.7854 | 0.8176 | 0.9359 |
| 0.0132 | 9.0 | 2124 | 0.3994 | 0.8723 | 0.7887 | 0.8178 | 0.9371 |
| 0.0099 | 10.0 | 2360 | 0.4482 | 0.8750 | 0.8026 | 0.8327 | 0.9373 |
| 0.005 | 11.0 | 2596 | 0.4510 | 0.8731 | 0.7887 | 0.8244 | 0.9371 |
| 0.0024 | 12.0 | 2832 | 0.4455 | 0.8543 | 0.7969 | 0.8210 | 0.9373 |
| 0.0016 | 13.0 | 3068 | 0.4603 | 0.8742 | 0.8062 | 0.8355 | 0.9395 |
| 0.0018 | 14.0 | 3304 | 0.4660 | 0.8729 | 0.7996 | 0.8306 | 0.9393 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023