topic-classification-tweet-7
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: 0.9993
- Balanced Accuracy: 0.5638
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: 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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy |
---|---|---|---|---|
0.8952 | 1.0 | 500 | 0.8052 | 0.4868 |
0.548 | 2.0 | 1000 | 0.7854 | 0.4925 |
0.3339 | 3.0 | 1500 | 0.9993 | 0.5638 |
0.1951 | 4.0 | 2000 | 1.1828 | 0.5524 |
0.1377 | 5.0 | 2500 | 1.2954 | 0.5301 |
0.0961 | 6.0 | 3000 | 1.2534 | 0.5575 |
0.0688 | 7.0 | 3500 | 1.2715 | 0.5591 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1