metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine-tune-xlm-roberta-PAF-split-headline1
results: []
fine-tune-xlm-roberta-PAF-split-headline1
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0692
- Accuracy: 0.4737
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0874 | 1.0 | 5 | 1.0736 | 0.4737 |
| 1.085 | 2.0 | 10 | 1.0629 | 0.4737 |
| 1.1053 | 3.0 | 15 | 1.0657 | 0.4737 |
| 1.1114 | 4.0 | 20 | 1.0692 | 0.4737 |
| 1.0836 | 5.0 | 25 | 1.0697 | 0.4737 |
| 1.08 | 6.0 | 30 | 1.0692 | 0.4737 |
| 1.0731 | 7.0 | 35 | 1.0692 | 0.4737 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1