<!-- 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_BERT
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: 0.7663
- Accuracy: 0.79
- F1: 0.7874
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 |
---|---|---|---|---|---|
1.0302 | 1.0 | 88 | 0.7777 | 0.65 | 0.5577 |
0.8613 | 2.0 | 176 | 0.8306 | 0.64 | 0.5873 |
0.749 | 3.0 | 264 | 0.6579 | 0.78 | 0.7786 |
0.651 | 4.0 | 352 | 0.5910 | 0.8 | 0.7940 |
0.5433 | 5.0 | 440 | 0.6380 | 0.8 | 0.7990 |
0.4788 | 6.0 | 528 | 0.6970 | 0.8 | 0.7980 |
0.382 | 7.0 | 616 | 0.7462 | 0.79 | 0.7874 |
0.3708 | 8.0 | 704 | 0.7663 | 0.79 | 0.7874 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3