metadata
license: cc-by-4.0
library_name: peft
tags:
- generated_from_trainer
base_model: EMBEDDIA/crosloengual-bert
metrics:
- accuracy
- f1
model-index:
- name: lora_fine_tuned_cb
results: []
lora_fine_tuned_cb
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: 3.7255
- Accuracy: 0.5
- F1: 0.4690
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: 0.003
- 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 |
|---|---|---|---|---|---|
| 0.7 | 3.5714 | 50 | 1.2589 | 0.4091 | 0.3098 |
| 0.2825 | 7.1429 | 100 | 2.2071 | 0.4091 | 0.3573 |
| 0.0229 | 10.7143 | 150 | 2.0270 | 0.6364 | 0.5916 |
| 0.0153 | 14.2857 | 200 | 2.2568 | 0.5455 | 0.5181 |
| 0.0017 | 17.8571 | 250 | 3.8454 | 0.4091 | 0.3573 |
| 0.0001 | 21.4286 | 300 | 3.8920 | 0.4091 | 0.3573 |
| 0.0 | 25.0 | 350 | 3.7418 | 0.5 | 0.4690 |
| 0.0 | 28.5714 | 400 | 3.7255 | 0.5 | 0.4690 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1