metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: roberta-large-finetuned-augmentation-LUNAR-TAPT-macro
results: []
roberta-large-finetuned-augmentation-LUNAR-TAPT-macro
This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2832
- F1: 0.8635
- Roc Auc: 0.8937
- Accuracy: 0.7150
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2744 | 1.0 | 421 | 0.2710 | 0.7932 | 0.8326 | 0.5754 |
| 0.2287 | 2.0 | 842 | 0.2281 | 0.8454 | 0.8815 | 0.6758 |
| 0.1678 | 3.0 | 1263 | 0.2293 | 0.8563 | 0.8879 | 0.7049 |
| 0.1287 | 4.0 | 1684 | 0.2491 | 0.8619 | 0.8918 | 0.7126 |
| 0.1298 | 5.0 | 2105 | 0.2591 | 0.8633 | 0.8936 | 0.7173 |
| 0.0788 | 6.0 | 2526 | 0.2703 | 0.8612 | 0.8914 | 0.7138 |
| 0.0883 | 7.0 | 2947 | 0.2679 | 0.8605 | 0.8905 | 0.7203 |
| 0.0821 | 8.0 | 3368 | 0.2832 | 0.8635 | 0.8937 | 0.7150 |
| 0.0739 | 9.0 | 3789 | 0.2998 | 0.8601 | 0.8963 | 0.7156 |
| 0.0538 | 10.0 | 4210 | 0.2951 | 0.8615 | 0.8957 | 0.7167 |
| 0.0466 | 11.0 | 4631 | 0.2999 | 0.8626 | 0.8976 | 0.7126 |
| 0.0657 | 12.0 | 5052 | 0.3060 | 0.8608 | 0.8976 | 0.7203 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0