16_combo_bert_1409_v1_plus_othergreen
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: 0.6527
- Accuracy: 0.8328
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 270 | 1.6861 | 0.4075 |
| 1.5192 | 2.0 | 540 | 1.1399 | 0.6591 |
| 1.5192 | 3.0 | 810 | 1.0636 | 0.6672 |
| 0.6636 | 4.0 | 1080 | 0.8126 | 0.7841 |
| 0.6636 | 5.0 | 1350 | 0.7421 | 0.8019 |
| 0.3933 | 6.0 | 1620 | 0.7070 | 0.8101 |
| 0.3933 | 7.0 | 1890 | 0.6786 | 0.8214 |
| 0.2737 | 8.0 | 2160 | 0.6527 | 0.8328 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3