metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base-xlmberttest
results: []
xlm-roberta-base-xlmberttest
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: 0.7300
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9566 | 1.0 | 282 | 0.8288 |
| 0.8483 | 2.0 | 564 | 0.7726 |
| 0.8033 | 3.0 | 846 | 0.7617 |
| 0.7691 | 4.0 | 1128 | 0.7387 |
| 0.7464 | 5.0 | 1410 | 0.7300 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 1.10.3.dev0
- Tokenizers 0.12.1