metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: prompt_fine_tuned_CB_XLMroberta
results: []
prompt_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: 1.4733
- 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: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|---|---|
| 0.9542 | 0.4545 | 50 | 1.1060 | 0.3182 | 0.1536 |
| 0.8627 | 0.9091 | 100 | 1.1621 | 0.3182 | 0.1536 |
| 0.6647 | 1.3636 | 150 | 1.2304 | 0.3182 | 0.1536 |
| 0.8065 | 1.8182 | 200 | 1.3215 | 0.3182 | 0.1536 |
| 0.7675 | 2.2727 | 250 | 1.3718 | 0.3182 | 0.1536 |
| 0.8203 | 2.7273 | 300 | 1.4238 | 0.3182 | 0.1536 |
| 0.7817 | 3.1818 | 350 | 1.4576 | 0.3182 | 0.1536 |
| 0.7012 | 3.6364 | 400 | 1.4733 | 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