roberta-finetune-open-question
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7613
- Balanced weighted accuracy: 0.7674
- Mcc: 0.7837
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced weighted accuracy | Mcc |
---|---|---|---|---|---|
0.7591 | 1.0 | 304 | 0.8721 | 0.6565 | 0.6915 |
0.802 | 2.0 | 608 | 0.8703 | 0.7387 | 0.7258 |
0.3863 | 3.0 | 912 | 0.7613 | 0.7674 | 0.7837 |
0.3088 | 4.0 | 1216 | 0.8113 | 0.7972 | 0.7879 |
0.4292 | 5.0 | 1520 | 0.9155 | 0.7923 | 0.7961 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0