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_3
results: []
080524_epoch_3
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: 0.6181
- Accuracy: 0.8403
- Precision: 0.8404
- Recall: 0.8403
- F1: 0.8403
- Ratio: 0.5084
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 |
|---|---|---|---|---|---|---|---|---|
| 0.6062 | 0.1626 | 10 | 0.6718 | 0.7857 | 0.7892 | 0.7857 | 0.7851 | 0.4454 |
| 0.6043 | 0.3252 | 20 | 0.6672 | 0.8067 | 0.8075 | 0.8067 | 0.8066 | 0.5252 |
| 0.5636 | 0.4878 | 30 | 0.6729 | 0.8025 | 0.8043 | 0.8025 | 0.8022 | 0.4622 |
| 0.6299 | 0.6504 | 40 | 0.6506 | 0.8151 | 0.8184 | 0.8151 | 0.8147 | 0.5504 |
| 0.7213 | 0.8130 | 50 | 0.6245 | 0.8277 | 0.8278 | 0.8277 | 0.8277 | 0.4958 |
| 0.6419 | 0.9756 | 60 | 0.6181 | 0.8403 | 0.8404 | 0.8403 | 0.8403 | 0.5084 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1