<!-- 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_replace_w2v
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: 0.9706
- Accuracy: 0.74
- F1: 0.7367
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: 42
- 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 |
|---|---|---|---|---|---|
| 1.05 | 1.0 | 86 | 0.8140 | 0.67 | 0.6300 |
| 0.857 | 2.0 | 172 | 0.6946 | 0.71 | 0.6754 |
| 0.6629 | 3.0 | 258 | 0.7705 | 0.73 | 0.7242 |
| 0.5325 | 4.0 | 344 | 0.8127 | 0.71 | 0.6986 |
| 0.4073 | 5.0 | 430 | 0.7205 | 0.72 | 0.7185 |
| 0.3112 | 6.0 | 516 | 0.8922 | 0.72 | 0.7187 |
| 0.247 | 7.0 | 602 | 0.9664 | 0.73 | 0.7236 |
| 0.1797 | 8.0 | 688 | 0.9706 | 0.74 | 0.7367 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
