Downloads · 30 days
5
15% of all-time downloads
Full-8epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news
DioBot2000/Full-8epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news
Full-8epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news is a token classification model from DioBot2000. 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
33
Public
Parameters
177M
709 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors709 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jun 3, 2024
- Updated
- Jun 3, 2024
- SHA
- 05be4192
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. -->
Full-8epoch-BERT-base-multilingual-finetuned-CEFR_ner-60000news
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0772
- Accuracy: 0.3055
- Precision: 0.5539
- Recall: 0.8444
- F1: 0.5463
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1609 | 1.0 | 1563 | 0.1237 | 0.3003 | 0.5394 | 0.8062 | 0.5257 |
| 0.1031 | 2.0 | 3126 | 0.0926 | 0.3033 | 0.5628 | 0.8280 | 0.5475 |
| 0.0805 | 3.0 | 4689 | 0.0831 | 0.3043 | 0.5396 | 0.8360 | 0.5317 |
| 0.0687 | 4.0 | 6252 | 0.0789 | 0.3048 | 0.5514 | 0.8404 | 0.5428 |
| 0.0595 | 5.0 | 7815 | 0.0767 | 0.3051 | 0.5386 | 0.8415 | 0.5347 |
| 0.0529 | 6.0 | 9378 | 0.0770 | 0.3053 | 0.5506 | 0.8425 | 0.5444 |
| 0.048 | 7.0 | 10941 | 0.0765 | 0.3055 | 0.5516 | 0.8444 | 0.5451 |
| 0.0453 | 8.0 | 12504 | 0.0772 | 0.3055 | 0.5539 | 0.8444 | 0.5463 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jun 3, 2024
- Updated
- Jun 3, 2024