sentiment-pt-pl10-2
This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3248
- Accuracy: 0.8872
- Precision: 0.8672
- Recall: 0.8577
- F1: 0.8622
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: 5e-05
- train_batch_size: 30
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.5533 | 1.0 | 122 | 0.5134 | 0.7268 | 0.6606 | 0.6242 | 0.6327 |
0.4779 | 2.0 | 244 | 0.4950 | 0.7419 | 0.7054 | 0.7349 | 0.7122 |
0.4097 | 3.0 | 366 | 0.3772 | 0.8246 | 0.8093 | 0.7459 | 0.7665 |
0.3451 | 4.0 | 488 | 0.3511 | 0.8446 | 0.8105 | 0.8251 | 0.8170 |
0.2959 | 5.0 | 610 | 0.3201 | 0.8546 | 0.8239 | 0.8272 | 0.8255 |
0.2727 | 6.0 | 732 | 0.3176 | 0.8647 | 0.8325 | 0.8642 | 0.8447 |
0.2595 | 7.0 | 854 | 0.2959 | 0.8747 | 0.8451 | 0.8613 | 0.8524 |
0.2409 | 8.0 | 976 | 0.2833 | 0.8897 | 0.8710 | 0.8595 | 0.8649 |
0.2298 | 9.0 | 1098 | 0.2894 | 0.8772 | 0.8535 | 0.8481 | 0.8507 |
0.2221 | 10.0 | 1220 | 0.2884 | 0.8872 | 0.8687 | 0.8552 | 0.8615 |
0.1986 | 11.0 | 1342 | 0.2855 | 0.8847 | 0.8648 | 0.8534 | 0.8588 |
0.1964 | 12.0 | 1464 | 0.2921 | 0.8822 | 0.8694 | 0.8392 | 0.8521 |
0.1783 | 13.0 | 1586 | 0.3104 | 0.8897 | 0.8710 | 0.8595 | 0.8649 |
0.1788 | 14.0 | 1708 | 0.3015 | 0.8897 | 0.8640 | 0.8745 | 0.8689 |
0.172 | 15.0 | 1830 | 0.3012 | 0.8847 | 0.8634 | 0.8559 | 0.8595 |
0.1563 | 16.0 | 1952 | 0.3159 | 0.8897 | 0.8632 | 0.8770 | 0.8695 |
0.1512 | 17.0 | 2074 | 0.3249 | 0.8847 | 0.8679 | 0.8484 | 0.8573 |
0.151 | 18.0 | 2196 | 0.3245 | 0.8822 | 0.8624 | 0.8492 | 0.8553 |
0.1461 | 19.0 | 2318 | 0.3282 | 0.8872 | 0.8687 | 0.8552 | 0.8615 |
0.1555 | 20.0 | 2440 | 0.3248 | 0.8872 | 0.8672 | 0.8577 | 0.8622 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2
Model tree for apwic/sentiment-pt-pl10-2
Base model
indolem/indobert-base-uncased
Finetuned
this model