<!-- 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. -->
mlm-20230427-mBERT-001
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2986
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 | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 456 | 1.6870 |
| 1.9828 | 2.0 | 912 | 1.5792 |
| 1.6989 | 3.0 | 1368 | 1.5310 |
| 1.5799 | 4.0 | 1824 | 1.4767 |
| 1.5121 | 5.0 | 2280 | 1.4764 |
| 1.4296 | 6.0 | 2736 | 1.4229 |
| 1.4003 | 7.0 | 3192 | 1.4218 |
| 1.3362 | 8.0 | 3648 | 1.3958 |
| 1.2939 | 9.0 | 4104 | 1.3676 |
| 1.2728 | 10.0 | 4560 | 1.3148 |
| 1.2287 | 11.0 | 5016 | 1.3248 |
| 1.2287 | 12.0 | 5472 | 1.3261 |
| 1.1992 | 13.0 | 5928 | 1.3410 |
| 1.1848 | 14.0 | 6384 | 1.3363 |
| 1.1732 | 15.0 | 6840 | 1.2992 |
| 1.1355 | 16.0 | 7296 | 1.2697 |
| 1.1391 | 17.0 | 7752 | 1.3066 |
| 1.1258 | 18.0 | 8208 | 1.2765 |
| 1.1088 | 19.0 | 8664 | 1.2974 |
| 1.0953 | 20.0 | 9120 | 1.2935 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
