<!-- 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-Balance_Mixed-aug_insert_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: 0.9400
- Accuracy: 0.74
- F1: 0.7312
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 |
|---|---|---|---|---|---|
| 1.0846 | 1.0 | 68 | 0.9484 | 0.59 | 0.5066 |
| 0.8918 | 2.0 | 136 | 0.8377 | 0.69 | 0.6472 |
| 0.7005 | 3.0 | 204 | 0.6713 | 0.7 | 0.6792 |
| 0.5632 | 4.0 | 272 | 0.7028 | 0.74 | 0.7332 |
| 0.4355 | 5.0 | 340 | 0.7085 | 0.75 | 0.7394 |
| 0.3093 | 6.0 | 408 | 0.8062 | 0.74 | 0.7317 |
| 0.2411 | 7.0 | 476 | 0.9110 | 0.75 | 0.7402 |
| 0.2013 | 8.0 | 544 | 0.9400 | 0.74 | 0.7312 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
