metadata
license: cc-by-sa-4.0
library_name: peft
tags:
- generated_from_trainer
base_model: EMBEDDIA/sloberta
metrics:
- accuracy
- f1
model-index:
- name: loha_fine_tuned_cb_sloberta
results: []
loha_fine_tuned_cb_sloberta
This model is a fine-tuned version of EMBEDDIA/sloberta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2669
- Accuracy: 0.6364
- F1: 0.5977
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: 0.002
- 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 |
|---|---|---|---|---|---|
| 0.8405 | 3.5714 | 50 | 2.1784 | 0.3182 | 0.1536 |
| 0.7138 | 7.1429 | 100 | 1.1353 | 0.5909 | 0.5636 |
| 0.1766 | 10.7143 | 150 | 3.0435 | 0.5 | 0.4690 |
| 0.0445 | 14.2857 | 200 | 2.1500 | 0.5909 | 0.5545 |
| 0.0038 | 17.8571 | 250 | 1.7987 | 0.6364 | 0.5916 |
| 0.001 | 21.4286 | 300 | 2.2097 | 0.6364 | 0.5977 |
| 0.001 | 25.0 | 350 | 2.2794 | 0.6364 | 0.5977 |
| 0.0016 | 28.5714 | 400 | 2.2669 | 0.6364 | 0.5977 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.1.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1