metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-large-phatic
results: []
roberta-large-phatic
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: 0.1899
- Accuracy: 0.9603
- Precision: 0.9467
- Recall: 0.9726
- F1: 0.9595
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3582 | 1.0 | 76 | 0.2311 | 0.9007 | 0.9028 | 0.8904 | 0.8966 |
| 0.1507 | 2.0 | 152 | 0.1862 | 0.9536 | 0.9853 | 0.9178 | 0.9504 |
| 0.1251 | 3.0 | 228 | 0.2490 | 0.9536 | 1.0 | 0.9041 | 0.9496 |
| 0.0834 | 4.0 | 304 | 0.3539 | 0.9470 | 0.9114 | 0.9863 | 0.9474 |
| 0.0004 | 5.0 | 380 | 0.1731 | 0.9603 | 0.9589 | 0.9589 | 0.9589 |
| 0.0003 | 6.0 | 456 | 0.1899 | 0.9603 | 0.9467 | 0.9726 | 0.9595 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.3.0+cu118
- Datasets 2.21.0
- Tokenizers 0.21.1