metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xnli_en_adalora_alpha_64_drop_02_rank_32
results: []
xnli_en_adalora_alpha_64_drop_02_rank_32
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: 0.4404
- Accuracy: 0.8321
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5419 | 1.0 | 12272 | 0.5032 | 0.7968 |
| 0.5016 | 2.0 | 24544 | 0.4816 | 0.8096 |
| 0.4751 | 3.0 | 36816 | 0.5019 | 0.7952 |
| 0.4711 | 4.0 | 49088 | 0.4446 | 0.8241 |
| 0.4534 | 5.0 | 61360 | 0.4412 | 0.8305 |
| 0.4379 | 6.0 | 73632 | 0.4406 | 0.8325 |
| 0.414 | 7.0 | 85904 | 0.4484 | 0.8277 |
| 0.422 | 8.0 | 98176 | 0.4355 | 0.8369 |
| 0.4151 | 9.0 | 110448 | 0.4386 | 0.8345 |
| 0.4011 | 10.0 | 122720 | 0.4404 | 0.8321 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1