metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa_token_classification_AraiEval24_Eng_multi_n_dupl
results: []
RoBERTa_token_classification_AraiEval24_Eng_multi_n_dupl
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6921
- Precision: 0.1617
- Recall: 0.0919
- F1: 0.1172
- Accuracy: 0.6855
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.3253 | 1.0 | 617 | 1.3214 | 0.1630 | 0.0115 | 0.0216 | 0.7059 |
| 1.1069 | 2.0 | 1234 | 1.2762 | 0.1354 | 0.0299 | 0.0490 | 0.7012 |
| 0.9809 | 3.0 | 1851 | 1.3347 | 0.1268 | 0.0614 | 0.0827 | 0.6621 |
| 0.8247 | 4.0 | 2468 | 1.4661 | 0.1354 | 0.0572 | 0.0804 | 0.6672 |
| 0.5789 | 5.0 | 3085 | 1.4868 | 0.1434 | 0.0593 | 0.0839 | 0.6698 |
| 0.4944 | 6.0 | 3702 | 1.5318 | 0.1525 | 0.0829 | 0.1074 | 0.6845 |
| 0.445 | 7.0 | 4319 | 1.6190 | 0.1608 | 0.0808 | 0.1076 | 0.6882 |
| 0.4139 | 8.0 | 4936 | 1.6784 | 0.1736 | 0.0945 | 0.1224 | 0.6906 |
| 0.3402 | 9.0 | 5553 | 1.6696 | 0.1599 | 0.0934 | 0.1180 | 0.6813 |
| 0.3125 | 10.0 | 6170 | 1.6921 | 0.1617 | 0.0919 | 0.1172 | 0.6855 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3