metadata
library_name: peft
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: emotion-model11_1
results: []
emotion-model11_1
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0558
- Accuracy: 0.5583
- F1: 0.4543
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 41 | 1.3448 | 0.3313 | 0.1649 |
| 1.336 | 2.0 | 82 | 1.2580 | 0.3865 | 0.2723 |
| 1.2494 | 3.0 | 123 | 1.1684 | 0.4785 | 0.3854 |
| 1.1693 | 4.0 | 164 | 1.1654 | 0.4969 | 0.3632 |
| 1.1183 | 5.0 | 205 | 1.1241 | 0.5337 | 0.4448 |
| 1.1183 | 6.0 | 246 | 1.0662 | 0.5521 | 0.4496 |
| 1.1033 | 7.0 | 287 | 1.0558 | 0.5583 | 0.4543 |
| 1.0765 | 8.0 | 328 | 1.0642 | 0.5521 | 0.4466 |
| 1.0701 | 9.0 | 369 | 1.0509 | 0.5583 | 0.4513 |
| 1.037 | 10.0 | 410 | 1.0526 | 0.5583 | 0.4511 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1