bert-base-multilingual-cased-Confusion-mlm-20230603
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.5723
- Loss: 1.7609
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 |
|---|---|---|---|---|
| 3.2882 | 1.0 | 130 | 0.3554 | 2.9429 |
| 2.8803 | 2.0 | 260 | 0.3761 | 2.6740 |
| 2.6044 | 3.0 | 390 | 0.4656 | 2.2735 |
| 2.3907 | 4.0 | 520 | 0.4721 | 2.3350 |
| 2.2612 | 5.0 | 650 | 0.5242 | 2.0715 |
| 2.1133 | 6.0 | 780 | 0.4984 | 2.1209 |
| 2.1048 | 7.0 | 910 | 0.4960 | 2.0021 |
| 1.9521 | 8.0 | 1040 | 0.5224 | 2.2426 |
| 1.9255 | 9.0 | 1170 | 0.5472 | 1.8786 |
| 1.8923 | 10.0 | 1300 | 0.5364 | 1.9918 |
| 1.8296 | 11.0 | 1430 | 0.4738 | 2.2351 |
| 1.7689 | 12.0 | 1560 | 0.5028 | 2.0691 |
| 1.736 | 13.0 | 1690 | 0.5794 | 1.9221 |
| 1.7639 | 14.0 | 1820 | 0.5252 | 2.0188 |
| 1.6555 | 15.0 | 1950 | 0.6012 | 1.6560 |
| 1.6019 | 16.0 | 2080 | 0.5935 | 1.6369 |
| 1.5524 | 17.0 | 2210 | 0.6226 | 1.6262 |
| 1.5182 | 18.0 | 2340 | 0.6211 | 1.7780 |
| 1.5537 | 19.0 | 2470 | 0.5616 | 1.9577 |
| 1.5651 | 20.0 | 2600 | 0.5723 | 1.7609 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3