metadata
library_name: transformers
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: roberta-large-ToM2
results: []
roberta-large-ToM2
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2561
- Accuracy: 0.9540
- F1: 0.9604
- Precision: 0.97
- Recall: 0.9510
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: 2015
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6475 | 1.0 | 93 | 0.3671 | 0.9103 | 0.9195 | 0.8696 | 0.9756 |
| 0.3063 | 2.0 | 186 | 0.2410 | 0.9103 | 0.9176 | 0.8864 | 0.9512 |
| 0.1717 | 3.0 | 279 | 0.2763 | 0.9231 | 0.9302 | 0.8889 | 0.9756 |
| 0.1159 | 4.0 | 372 | 0.4473 | 0.9231 | 0.9318 | 0.8723 | 1.0 |
| 0.0568 | 5.0 | 465 | 0.4014 | 0.9359 | 0.9412 | 0.9091 | 0.9756 |
Framework versions
- Transformers 4.56.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0