xlm-roberta-base-finetuned-panx-all
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: 0.5155
- F1: 0.8005
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: 24
- eval_batch_size: 24
- 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 | F1 |
|---|---|---|---|---|
| 0.4866 | 1.0 | 438 | 0.3960 | 0.6932 |
| 0.2614 | 2.0 | 876 | 0.3196 | 0.7360 |
| 0.1845 | 3.0 | 1314 | 0.3218 | 0.7698 |
| 0.1353 | 4.0 | 1752 | 0.3439 | 0.7701 |
| 0.096 | 5.0 | 2190 | 0.3638 | 0.7885 |
| 0.0689 | 6.0 | 2628 | 0.3983 | 0.7991 |
| 0.0474 | 7.0 | 3066 | 0.4359 | 0.7962 |
| 0.0317 | 8.0 | 3504 | 0.4701 | 0.8032 |
| 0.0219 | 9.0 | 3942 | 0.5055 | 0.8032 |
| 0.0153 | 10.0 | 4380 | 0.5155 | 0.8005 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3