metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: lora_fine_tuned_copa_XLMroberta
results: []
lora_fine_tuned_copa_XLMroberta
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: 0.6929
- Accuracy: 0.59
- F1: 0.5884
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6985 | 1.0 | 50 | 0.6928 | 0.57 | 0.5695 |
| 0.7012 | 2.0 | 100 | 0.6928 | 0.58 | 0.58 |
| 0.6935 | 3.0 | 150 | 0.6929 | 0.58 | 0.5790 |
| 0.6897 | 4.0 | 200 | 0.6929 | 0.58 | 0.5776 |
| 0.6973 | 5.0 | 250 | 0.6929 | 0.6 | 0.5990 |
| 0.6982 | 6.0 | 300 | 0.6929 | 0.59 | 0.5884 |
| 0.6981 | 7.0 | 350 | 0.6929 | 0.59 | 0.5884 |
| 0.6999 | 8.0 | 400 | 0.6929 | 0.59 | 0.5884 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.1.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1