metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
model-index:
- name: roberta-base-finetuned
results: []
roberta-base-finetuned
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2253
- F1: 0.9351
- Precision: 0.9356
- Recall: 0.935
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.426 | 1.0 | 1250 | 0.2329 | 0.9206 | 0.9218 | 0.92 |
| 0.6112 | 2.0 | 2500 | 0.3298 | 0.9212 | 0.9293 | 0.92 |
| 0.2796 | 3.0 | 3750 | 0.2613 | 0.9248 | 0.9267 | 0.926 |
| 0.0908 | 4.0 | 5000 | 0.1831 | 0.9419 | 0.9431 | 0.942 |
| 0.101 | 5.0 | 6250 | 0.2253 | 0.9351 | 0.9356 | 0.935 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1