metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: roberta-train
results: []
roberta-train
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2541
- Accuracy: 0.9062
- F1: 0.9372
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-06
- 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: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 190 | 0.4252 | 0.7312 | 0.8448 |
| No log | 2.0 | 380 | 0.2966 | 0.8688 | 0.9106 |
| 0.4762 | 3.0 | 570 | 0.2884 | 0.8875 | 0.9224 |
| 0.4762 | 4.0 | 760 | 0.2458 | 0.9125 | 0.9421 |
| 0.4762 | 5.0 | 950 | 0.2541 | 0.9062 | 0.9372 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1