roberta_large-chunking_0728_v2
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5270
- Precision: 0.6228
- Recall: 0.6467
- F1: 0.6345
- Accuracy: 0.8153
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 125 | 0.5667 | 0.4931 | 0.5415 | 0.5162 | 0.7397 |
| No log | 2.0 | 250 | 0.4839 | 0.5484 | 0.5894 | 0.5682 | 0.7874 |
| No log | 3.0 | 375 | 0.4822 | 0.5997 | 0.6341 | 0.6164 | 0.8085 |
| 0.4673 | 4.0 | 500 | 0.5117 | 0.6023 | 0.6373 | 0.6193 | 0.8120 |
| 0.4673 | 5.0 | 625 | 0.5270 | 0.6228 | 0.6467 | 0.6345 | 0.8153 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1