metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-en-5
results: []
xlm-roberta-base-en-5
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: 0.3224
- F1: 0.8310
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: 15
- eval_batch_size: 15
- 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 | F1 |
|---|---|---|---|---|
| 0.4076 | 1.0 | 1334 | 0.3048 | 0.7838 |
| 0.2535 | 2.0 | 2668 | 0.2776 | 0.8028 |
| 0.1884 | 3.0 | 4002 | 0.2680 | 0.8187 |
| 0.1362 | 4.0 | 5336 | 0.3025 | 0.8293 |
| 0.0966 | 5.0 | 6670 | 0.3224 | 0.8310 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1