metadata
license: cc-by-4.0
base_model: EMBEDDIA/crosloengual-bert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine_tuned_cb_croslo
results: []
fine_tuned_cb_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: 0.5829
- Accuracy: 0.8636
- F1: 0.8452
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 |
|---|---|---|---|---|---|
| 0.5945 | 3.5714 | 50 | 0.9554 | 0.4091 | 0.3208 |
| 0.1464 | 7.1429 | 100 | 0.5574 | 0.8182 | 0.8024 |
| 0.0128 | 10.7143 | 150 | 0.5869 | 0.8182 | 0.8024 |
| 0.0036 | 14.2857 | 200 | 0.5764 | 0.8636 | 0.8452 |
| 0.0024 | 17.8571 | 250 | 0.5659 | 0.8636 | 0.8452 |
| 0.0018 | 21.4286 | 300 | 0.5763 | 0.8636 | 0.8452 |
| 0.0015 | 25.0 | 350 | 0.5791 | 0.8636 | 0.8452 |
| 0.0014 | 28.5714 | 400 | 0.5829 | 0.8636 | 0.8452 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1