<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-large-first
This model is a fine-tuned version of rafalposwiata/deproberta-large-depression on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2025
- Accuracy: 0.8483
- F1: 0.9100
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-06
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 469 | 0.3694 | 0.8783 | 0.9312 |
0.3984 | 2.0 | 938 | 0.4488 | 0.87 | 0.9257 |
0.3366 | 3.0 | 1407 | 0.5764 | 0.855 | 0.9141 |
0.295 | 4.0 | 1876 | 0.7716 | 0.8533 | 0.9132 |
0.1876 | 5.0 | 2345 | 0.8724 | 0.855 | 0.9148 |
0.1378 | 6.0 | 2814 | 1.1717 | 0.825 | 0.8921 |
0.0836 | 7.0 | 3283 | 1.0711 | 0.8367 | 0.9028 |
0.043 | 8.0 | 3752 | 1.0807 | 0.8633 | 0.9202 |
0.0402 | 9.0 | 4221 | 1.2285 | 0.8367 | 0.9024 |
0.035 | 10.0 | 4690 | 1.2025 | 0.8483 | 0.9100 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3