tmp
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3272
- Precision: 0.5560
- Recall: 0.3209
- F1: 0.4069
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.7083 | 0.35 | 500 | 0.4423 | 0.2785 | 0.0529 | 0.0889 |
| 0.4849 | 0.7 | 1000 | 0.4009 | 0.3623 | 0.1803 | 0.2408 |
| 0.4021 | 1.04 | 1500 | 0.3621 | 0.5027 | 0.2212 | 0.3072 |
| 0.3276 | 1.39 | 2000 | 0.3606 | 0.4006 | 0.3077 | 0.3481 |
| 0.2857 | 1.74 | 2500 | 0.3432 | 0.5073 | 0.25 | 0.3349 |
| 0.251 | 2.09 | 3000 | 0.3481 | 0.4431 | 0.3413 | 0.3856 |
| 0.2184 | 2.43 | 3500 | 0.3309 | 0.5274 | 0.3353 | 0.4100 |
| 0.2162 | 2.78 | 4000 | 0.3411 | 0.4167 | 0.3726 | 0.3934 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for OSainz/mdt-ie-re-entity-pair
Base model
FacebookAI/xlm-roberta-base