metadata
license: cc-by-4.0
library_name: peft
tags:
- generated_from_trainer
base_model: EMBEDDIA/crosloengual-bert
metrics:
- accuracy
- f1
model-index:
- name: prompt_fine_tuned_rte_croslo
results: []
prompt_fine_tuned_rte_croslo
This model is a fine-tuned version of EMBEDDIA/crosloengual-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6858
- Accuracy: 0.5517
- F1: 0.5215
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 |
|---|---|---|---|---|---|
| 0.7003 | 1.7241 | 50 | 0.6844 | 0.5862 | 0.5483 |
| 0.682 | 3.4483 | 100 | 0.6833 | 0.6207 | 0.5750 |
| 0.6937 | 5.1724 | 150 | 0.6850 | 0.5517 | 0.5215 |
| 0.7036 | 6.8966 | 200 | 0.6860 | 0.5517 | 0.5215 |
| 0.6974 | 8.6207 | 250 | 0.6859 | 0.5517 | 0.5215 |
| 0.7117 | 10.3448 | 300 | 0.6859 | 0.5517 | 0.5215 |
| 0.7073 | 12.0690 | 350 | 0.6857 | 0.5517 | 0.5215 |
| 0.7038 | 13.7931 | 400 | 0.6858 | 0.5517 | 0.5215 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1