metadata
tags:
- generated_from_trainer
model-index:
- name: berties-pretrained
results: []
berties-pretrained
This model is a fine-tuned version of Jean-Baptiste/camembert-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3922
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7047 | 0.21 | 500 | 5.0371 |
| 4.4116 | 0.43 | 1000 | 4.5143 |
| 4.0711 | 0.64 | 1500 | 4.3272 |
| 3.8657 | 0.86 | 2000 | 4.1704 |
| 3.6971 | 1.07 | 2500 | 3.9951 |
| 3.5093 | 1.29 | 3000 | 3.7682 |
| 3.3598 | 1.5 | 3500 | 3.6554 |
| 3.2389 | 1.72 | 4000 | 3.6167 |
| 3.1984 | 1.93 | 4500 | 3.4445 |
| 3.1063 | 2.15 | 5000 | 3.4206 |
| 3.0063 | 2.36 | 5500 | 3.4164 |
| 3.0069 | 2.57 | 6000 | 3.4115 |
| 2.9954 | 2.79 | 6500 | 3.3463 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3