SingSeqBERT-UCIRetail
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4882
- Accuracy: 0.7685
- F1: 0.7672
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 456 | 0.5482 | 0.7479 | 0.7425 |
0.6336 | 2.0 | 912 | 0.5108 | 0.7570 | 0.7569 |
0.5437 | 3.0 | 1368 | 0.4882 | 0.7685 | 0.7672 |
0.4872 | 4.0 | 1824 | 0.5918 | 0.7825 | 0.7825 |
0.4329 | 5.0 | 2280 | 0.6156 | 0.7652 | 0.7652 |
0.3957 | 6.0 | 2736 | 0.6598 | 0.7685 | 0.7683 |
0.3439 | 7.0 | 3192 | 0.7881 | 0.7768 | 0.7756 |
0.3068 | 8.0 | 3648 | 0.9189 | 0.7545 | 0.7536 |
0.2635 | 9.0 | 4104 | 1.0319 | 0.7619 | 0.7619 |
0.2305 | 10.0 | 4560 | 1.0976 | 0.7586 | 0.7586 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 2