indo_sentiment_indobertweet
This model is a fine-tuned version of indolem/indobertweet-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1509
- Accuracy: 0.9620
- Precision: 0.9610
- Recall: 0.9565
- F1: 0.9586
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1722 | 1.0 | 248 | 0.1118 | 0.9611 | 0.9608 | 0.9547 | 0.9576 |
| 0.0746 | 2.0 | 496 | 0.1346 | 0.9638 | 0.9619 | 0.9594 | 0.9607 |
| 0.0269 | 3.0 | 744 | 0.1509 | 0.9620 | 0.9610 | 0.9565 | 0.9586 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for AnwarKar/indo_sentiment_indobertweet
Base model
indolem/indobertweet-base-uncased