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: 1.2679
- Accuracy: 0.6818
- F1: 0.6488
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 |
|---|---|---|---|---|---|
| 0.6412 | 3.5714 | 50 | 1.2351 | 0.3182 | 0.1536 |
| 0.2271 | 7.1429 | 100 | 0.9940 | 0.5455 | 0.4896 |
| 0.0176 | 10.7143 | 150 | 1.0287 | 0.6818 | 0.6313 |
| 0.0031 | 14.2857 | 200 | 1.1287 | 0.6818 | 0.6313 |
| 0.002 | 17.8571 | 250 | 1.1967 | 0.6818 | 0.6488 |
| 0.0015 | 21.4286 | 300 | 1.2596 | 0.6818 | 0.6488 |
| 0.0013 | 25.0 | 350 | 1.2666 | 0.6818 | 0.6488 |
| 0.0013 | 28.5714 | 400 | 1.2679 | 0.6818 | 0.6488 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1