metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: mtl-xlmr-large-dsc
results: []
mtl-xlmr-large-dsc
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5877
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4037 | 1.0 | 3750 | 0.4181 |
| 0.3088 | 2.0 | 7500 | 0.3605 |
| 0.3528 | 3.0 | 11250 | 0.4657 |
| 0.172 | 4.0 | 15000 | 0.5288 |
| 0.005 | 5.0 | 18750 | 0.5877 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1
- Datasets 2.19.2
- Tokenizers 0.19.1