<!-- 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-Dep-second
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: 1.1600
- Accuracy: 0.8517
- F1: 0.9113
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
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 469 | 0.3551 | 0.86 | 0.9188 |
0.3676 | 2.0 | 938 | 0.4666 | 0.8617 | 0.9198 |
0.3042 | 3.0 | 1407 | 0.5818 | 0.86 | 0.9170 |
0.2651 | 4.0 | 1876 | 0.8291 | 0.865 | 0.9200 |
0.174 | 5.0 | 2345 | 0.8843 | 0.8567 | 0.9155 |
0.1363 | 6.0 | 2814 | 1.1669 | 0.8317 | 0.8968 |
0.075 | 7.0 | 3283 | 1.2803 | 0.8283 | 0.8952 |
0.0401 | 8.0 | 3752 | 1.0247 | 0.8617 | 0.9184 |
0.0301 | 9.0 | 4221 | 1.2848 | 0.83 | 0.8961 |
0.0281 | 10.0 | 4690 | 1.1600 | 0.8517 | 0.9113 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3