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_2
results: []
080524_epoch_2
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: 0.6633
- Accuracy: 0.7941
- Precision: 0.8018
- Recall: 0.7941
- F1: 0.7928
- Ratio: 0.5798
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 |
|---|---|---|---|---|---|---|---|---|
| 0.8337 | 0.1626 | 10 | 0.7759 | 0.7101 | 0.7126 | 0.7101 | 0.7092 | 0.4454 |
| 0.7644 | 0.3252 | 20 | 0.7252 | 0.7563 | 0.7654 | 0.7563 | 0.7542 | 0.5924 |
| 0.7339 | 0.4878 | 30 | 0.6925 | 0.7689 | 0.7732 | 0.7689 | 0.7680 | 0.5630 |
| 0.7102 | 0.6504 | 40 | 0.6907 | 0.7647 | 0.7802 | 0.7647 | 0.7614 | 0.6176 |
| 0.7758 | 0.8130 | 50 | 0.6682 | 0.7857 | 0.7917 | 0.7857 | 0.7846 | 0.5714 |
| 0.6621 | 0.9756 | 60 | 0.6632 | 0.7899 | 0.7967 | 0.7899 | 0.7887 | 0.5756 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1