multi_balanced_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1478
- Precision: 0.7360
- Recall: 0.8434
- F1: 0.7861
- Accuracy: 0.8974
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 48 | 0.1606 | 0.6667 | 0.7829 | 0.7201 | 0.8609 |
No log | 2.0 | 96 | 0.1518 | 0.6646 | 0.7758 | 0.7159 | 0.8574 |
No log | 3.0 | 144 | 0.1535 | 0.6152 | 0.7509 | 0.6763 | 0.8417 |
No log | 4.0 | 192 | 0.1510 | 0.6747 | 0.7972 | 0.7308 | 0.8626 |
No log | 5.0 | 240 | 0.1562 | 0.7547 | 0.8541 | 0.8013 | 0.9061 |
No log | 6.0 | 288 | 0.1436 | 0.7205 | 0.8256 | 0.7695 | 0.8974 |
No log | 7.0 | 336 | 0.1466 | 0.7484 | 0.8363 | 0.7899 | 0.9026 |
No log | 8.0 | 384 | 0.1450 | 0.7690 | 0.8648 | 0.8141 | 0.9130 |
No log | 9.0 | 432 | 0.1474 | 0.7453 | 0.8541 | 0.7960 | 0.9043 |
No log | 10.0 | 480 | 0.1478 | 0.7360 | 0.8434 | 0.7861 | 0.8974 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7