<!-- 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-1
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: 0.8547
- Accuracy: 0.76
- F1: 0.7549
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: 41
- 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 |
---|---|---|---|---|---|
1.0214 | 1.0 | 86 | 0.8603 | 0.61 | 0.5159 |
0.7951 | 2.0 | 172 | 0.7137 | 0.67 | 0.6356 |
0.6325 | 3.0 | 258 | 0.6746 | 0.8 | 0.7977 |
0.5227 | 4.0 | 344 | 0.6696 | 0.77 | 0.7634 |
0.3798 | 5.0 | 430 | 0.6741 | 0.78 | 0.7755 |
0.2942 | 6.0 | 516 | 0.6962 | 0.79 | 0.7850 |
0.2249 | 7.0 | 602 | 0.8669 | 0.75 | 0.7457 |
0.1814 | 8.0 | 688 | 0.8547 | 0.76 | 0.7549 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3