roberta-base-coco-NER
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1246
- Precision: 0.9442
- Recall: 0.9482
- F1: 0.9462
- Accuracy: 0.9652
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: 1e-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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1332 | 1.0 | 5441 | 0.1285 | 0.9314 | 0.9425 | 0.9369 | 0.9593 |
0.1017 | 2.0 | 10882 | 0.1193 | 0.9374 | 0.9440 | 0.9407 | 0.9621 |
0.0924 | 3.0 | 16323 | 0.1174 | 0.9401 | 0.9482 | 0.9441 | 0.9641 |
0.0773 | 4.0 | 21764 | 0.1224 | 0.9423 | 0.9469 | 0.9446 | 0.9644 |
0.0712 | 5.0 | 27205 | 0.1246 | 0.9442 | 0.9482 | 0.9462 | 0.9652 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 14