<!-- 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-base-finetuned-OIG-mod-3
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3807
- F1: 0.8758
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.7135 | 0.36 | 5000 | 0.7030 | 0.6948 |
| 0.6783 | 0.71 | 10000 | 0.6782 | 0.7053 |
| 0.6073 | 1.07 | 15000 | 0.6356 | 0.7350 |
| 0.5827 | 1.42 | 20000 | 0.6089 | 0.7382 |
| 0.5701 | 1.78 | 25000 | 0.5778 | 0.7595 |
| 0.4856 | 2.13 | 30000 | 0.5742 | 0.7718 |
| 0.4651 | 2.49 | 35000 | 0.5368 | 0.7869 |
| 0.4634 | 2.84 | 40000 | 0.5049 | 0.8024 |
| 0.3913 | 3.2 | 45000 | 0.4973 | 0.8103 |
| 0.3877 | 3.55 | 50000 | 0.4655 | 0.8237 |
| 0.364 | 3.91 | 55000 | 0.4406 | 0.8411 |
| 0.3198 | 4.26 | 60000 | 0.4429 | 0.8456 |
| 0.3047 | 4.62 | 65000 | 0.4108 | 0.8595 |
| 0.2821 | 4.97 | 70000 | 0.3979 | 0.8653 |
| 0.2548 | 5.33 | 75000 | 0.3903 | 0.8713 |
| 0.2475 | 5.68 | 80000 | 0.3807 | 0.8758 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
