metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: reberta
results: []
reberta
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3429
- Accuracy: 0.9408
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2089 | 1.0 | 1250 | 0.1942 | 0.9408 |
| 0.1623 | 2.0 | 2500 | 0.1801 | 0.9428 |
| 0.1364 | 3.0 | 3750 | 0.1934 | 0.9466 |
| 0.1051 | 4.0 | 5000 | 0.2134 | 0.9456 |
| 0.0737 | 5.0 | 6250 | 0.2472 | 0.9446 |
| 0.062 | 6.0 | 7500 | 0.2751 | 0.944 |
| 0.0441 | 7.0 | 8750 | 0.2992 | 0.9422 |
| 0.0342 | 8.0 | 10000 | 0.3116 | 0.9432 |
| 0.026 | 9.0 | 11250 | 0.3360 | 0.943 |
| 0.0179 | 10.0 | 12500 | 0.3429 | 0.9408 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2