<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlm-roberta-base-Final_Mixed-aug_insert_BERT-2
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: 0.9737
- Accuracy: 0.72
- F1: 0.7141
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: 16
- eval_batch_size: 16
- seed: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0807 | 1.0 | 88 | 0.9024 | 0.64 | 0.6254 |
| 0.8512 | 2.0 | 176 | 0.6824 | 0.75 | 0.7396 |
| 0.7009 | 3.0 | 264 | 0.6368 | 0.74 | 0.7363 |
| 0.5649 | 4.0 | 352 | 0.6994 | 0.76 | 0.7494 |
| 0.458 | 5.0 | 440 | 0.8683 | 0.74 | 0.7300 |
| 0.3409 | 6.0 | 528 | 1.0337 | 0.7 | 0.6787 |
| 0.2964 | 7.0 | 616 | 0.9357 | 0.75 | 0.7459 |
| 0.2305 | 8.0 | 704 | 0.9737 | 0.72 | 0.7141 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
