metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: outputs
results: []
outputs
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: 0.1489
- F1 Micro: 0.8209
- Precision Micro: 0.8209
- Recall Micro: 0.8209
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
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | Precision Micro | Recall Micro |
|---|---|---|---|---|---|---|
| 0.4507 | 0.7782 | 200 | 0.3227 | 0.0 | 0.0 | 0.0 |
| 0.263 | 1.5564 | 400 | 0.2081 | 0.5201 | 0.8744 | 0.3701 |
| 0.1789 | 2.3346 | 600 | 0.1686 | 0.7489 | 0.8231 | 0.6870 |
| 0.13 | 3.1128 | 800 | 0.1555 | 0.7691 | 0.8074 | 0.7343 |
| 0.1063 | 3.8911 | 1000 | 0.1416 | 0.7974 | 0.7649 | 0.8327 |
| 0.0844 | 4.6693 | 1200 | 0.1492 | 0.8 | 0.8008 | 0.7992 |
| 0.0617 | 5.4475 | 1400 | 0.1449 | 0.8268 | 0.8268 | 0.8268 |
| 0.0534 | 6.2257 | 1600 | 0.1388 | 0.8283 | 0.8258 | 0.8307 |
| 0.0352 | 7.0039 | 1800 | 0.1471 | 0.8272 | 0.8297 | 0.8248 |
| 0.0296 | 7.7821 | 2000 | 0.1489 | 0.8209 | 0.8209 | 0.8209 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.0.post100
- Datasets 2.19.0
- Tokenizers 0.19.1