lora_fine_tuned_copa_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: 0.6871
- Accuracy: 0.52
- F1: 0.5212
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 |
|---|---|---|---|---|---|
| 0.6985 | 1.0 | 50 | 0.6889 | 0.52 | 0.5212 |
| 0.7039 | 2.0 | 100 | 0.6885 | 0.52 | 0.5212 |
| 0.7019 | 3.0 | 150 | 0.6879 | 0.52 | 0.5212 |
| 0.6908 | 4.0 | 200 | 0.6875 | 0.52 | 0.5212 |
| 0.6922 | 5.0 | 250 | 0.6872 | 0.52 | 0.5212 |
| 0.6978 | 6.0 | 300 | 0.6871 | 0.52 | 0.5212 |
| 0.6884 | 7.0 | 350 | 0.6871 | 0.52 | 0.5212 |
| 0.6972 | 8.0 | 400 | 0.6871 | 0.52 | 0.5212 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.1.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for anzeo/lora_fine_tuned_copa_croslo
Base model
EMBEDDIA/crosloengual-bert