<!-- 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. -->
vocab2-bert-base-multilingual-uncased-udm-tsa
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.8497
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: 1e-05
- train_batch_size: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.3112 | 1.0 | 6419 | 6.1814 |
| 5.8524 | 2.0 | 12838 | 5.4075 |
| 5.3392 | 3.0 | 19257 | 5.0810 |
| 5.0958 | 4.0 | 25676 | 4.9015 |
| 4.9897 | 5.0 | 32095 | 4.8497 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
