xlm-roberta-base-Confusion-mlm-20230607
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.8736
- Loss: 0.5270
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 130 | 0.8677 | 0.6115 |
| No log | 2.0 | 260 | 0.9247 | 0.2752 |
| No log | 3.0 | 390 | 0.8571 | 0.6575 |
| 0.8615 | 4.0 | 520 | 0.8643 | 0.5735 |
| 0.8615 | 5.0 | 650 | 0.8911 | 0.3851 |
| 0.8615 | 6.0 | 780 | 0.8134 | 0.7165 |
| 0.8615 | 7.0 | 910 | 0.8413 | 0.6240 |
| 0.8129 | 8.0 | 1040 | 0.8861 | 0.4053 |
| 0.8129 | 9.0 | 1170 | 0.8606 | 0.5256 |
| 0.8129 | 10.0 | 1300 | 0.8776 | 0.5630 |
| 0.8129 | 11.0 | 1430 | 0.8784 | 0.5410 |
| 0.7179 | 12.0 | 1560 | 0.8807 | 0.5745 |
| 0.7179 | 13.0 | 1690 | 0.8889 | 0.4201 |
| 0.7179 | 14.0 | 1820 | 0.8785 | 0.4649 |
| 0.7179 | 15.0 | 1950 | 0.8859 | 0.4714 |
| 0.6857 | 16.0 | 2080 | 0.8453 | 0.5769 |
| 0.6857 | 17.0 | 2210 | 0.8407 | 0.5363 |
| 0.6857 | 18.0 | 2340 | 0.8724 | 0.5814 |
| 0.6857 | 19.0 | 2470 | 0.9098 | 0.3953 |
| 0.6107 | 20.0 | 2600 | 0.8736 | 0.5270 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3