metadata
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 080524_epoch_1
results: []
080524_epoch_1
This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2-cased-te on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7794
- Accuracy: 0.7395
- Precision: 0.7816
- Recall: 0.7395
- F1: 0.7294
- Ratio: 0.6933
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: 10
- eval_batch_size: 2
- seed: 47
- gradient_accumulation_steps: 2
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- lr_scheduler_warmup_steps: 4
- num_epochs: 1
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
|---|---|---|---|---|---|---|---|---|
| 3.1579 | 0.1176 | 10 | 2.2074 | 0.5126 | 0.5335 | 0.5126 | 0.4225 | 0.8950 |
| 1.5576 | 0.2353 | 20 | 1.3600 | 0.5504 | 0.5760 | 0.5504 | 0.5092 | 0.2101 |
| 1.1011 | 0.3529 | 30 | 0.9525 | 0.5588 | 0.5625 | 0.5588 | 0.5522 | 0.6218 |
| 0.9083 | 0.4706 | 40 | 0.8505 | 0.6471 | 0.6471 | 0.6471 | 0.6470 | 0.5084 |
| 0.8014 | 0.5882 | 50 | 0.8729 | 0.6765 | 0.7659 | 0.6765 | 0.6468 | 0.7899 |
| 0.7514 | 0.7059 | 60 | 0.7322 | 0.7563 | 0.7610 | 0.7563 | 0.7552 | 0.5672 |
| 0.7259 | 0.8235 | 70 | 0.7631 | 0.7437 | 0.7730 | 0.7437 | 0.7366 | 0.6639 |
| 0.7605 | 0.9412 | 80 | 0.7794 | 0.7395 | 0.7816 | 0.7395 | 0.7294 | 0.6933 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1