xlm-roberta-base-finetuned-panx-it
This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset. It achieves the following results on the evaluation set:
- Loss: 0.2562
- F1: 0.8223
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.8175 | 1.0 | 70 | 0.3331 | 0.7147 |
| 0.2807 | 2.0 | 140 | 0.2745 | 0.8045 |
| 0.1836 | 3.0 | 210 | 0.2562 | 0.8223 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 10
Model tree for bousejin/xlm-roberta-base-finetuned-panx-it
Base model
FacebookAI/xlm-roberta-baseDataset used to train bousejin/xlm-roberta-base-finetuned-panx-it
Evaluation results
- F1 on xtremeself-reported0.822