<!-- 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_synonym-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: 1.1196
- Accuracy: 0.75
- F1: 0.7413
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 |
|---|---|---|---|---|---|
| 1.04 | 1.0 | 88 | 0.8053 | 0.64 | 0.6127 |
| 0.7333 | 2.0 | 176 | 0.7600 | 0.71 | 0.7035 |
| 0.5406 | 3.0 | 264 | 0.6719 | 0.71 | 0.7080 |
| 0.4339 | 4.0 | 352 | 0.7426 | 0.75 | 0.7393 |
| 0.3085 | 5.0 | 440 | 0.9125 | 0.73 | 0.6985 |
| 0.23 | 6.0 | 528 | 0.9200 | 0.76 | 0.7527 |
| 0.1612 | 7.0 | 616 | 1.0423 | 0.74 | 0.7314 |
| 0.137 | 8.0 | 704 | 1.1196 | 0.75 | 0.7413 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
