metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: roberta
results: []
roberta
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0480
- F1: 0.6518
- Precision: 0.6478
- Recall: 0.6755
- Accuracy: 0.6755
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: 4e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.1301 | 1.0 | 4409 | 1.0908 | 0.6331 | 0.6205 | 0.6767 | 0.6767 |
| 0.9143 | 2.0 | 8818 | 1.0480 | 0.6518 | 0.6478 | 0.6755 | 0.6755 |
| 0.7126 | 3.0 | 13227 | 1.2204 | 0.6456 | 0.6351 | 0.6609 | 0.6609 |
| 0.5437 | 4.0 | 17636 | 1.3307 | 0.6394 | 0.6304 | 0.6515 | 0.6515 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0