<!-- 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. -->
MAL-10epoch-BertMul
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: 0.5565
- Accuracy: 0.6981
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 8 | 0.6892 | 0.6981 |
No log | 2.0 | 16 | 0.5771 | 0.6981 |
No log | 3.0 | 24 | 0.5698 | 0.6981 |
No log | 4.0 | 32 | 0.5714 | 0.6981 |
No log | 5.0 | 40 | 0.5835 | 0.6981 |
No log | 6.0 | 48 | 0.5631 | 0.6981 |
No log | 7.0 | 56 | 0.5678 | 0.6981 |
No log | 8.0 | 64 | 0.5646 | 0.6981 |
No log | 9.0 | 72 | 0.5539 | 0.6981 |
No log | 10.0 | 80 | 0.5565 | 0.6981 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 1.13.1
- Datasets 2.14.5
- Tokenizers 0.14.1