metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: lora_fine_tuned_cb_XLMroberta
results: []
lora_fine_tuned_cb_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: 1.4225
- Accuracy: 0.3182
- F1: 0.1536
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 |
|---|---|---|---|---|---|
| 0.9083 | 3.5714 | 50 | 1.2624 | 0.3182 | 0.1536 |
| 0.7455 | 7.1429 | 100 | 1.4585 | 0.3182 | 0.1536 |
| 0.7714 | 10.7143 | 150 | 1.4354 | 0.3182 | 0.1536 |
| 0.721 | 14.2857 | 200 | 1.3749 | 0.3182 | 0.1536 |
| 0.7302 | 17.8571 | 250 | 1.4032 | 0.3182 | 0.1536 |
| 0.7313 | 21.4286 | 300 | 1.4237 | 0.3182 | 0.1536 |
| 0.6958 | 25.0 | 350 | 1.4302 | 0.3182 | 0.1536 |
| 0.7295 | 28.5714 | 400 | 1.4225 | 0.3182 | 0.1536 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1