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: 060524_epoch_1
results: []
060524_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: 0.8543
- Accuracy: 0.6261
- Precision: 0.6293
- Recall: 0.6261
- F1: 0.6237
- 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: 42
- 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 |
|---|---|---|---|---|---|---|---|---|
| 3.74 | 0.1626 | 10 | 1.8200 | 0.5126 | 0.5133 | 0.5126 | 0.5058 | 0.6176 |
| 1.3496 | 0.3252 | 20 | 1.1848 | 0.5210 | 0.5213 | 0.5210 | 0.5193 | 0.4412 |
| 1.1148 | 0.4878 | 30 | 1.0206 | 0.5336 | 0.5398 | 0.5336 | 0.5147 | 0.6975 |
| 0.9521 | 0.6504 | 40 | 0.9135 | 0.5756 | 0.5804 | 0.5756 | 0.5692 | 0.3782 |
| 0.9059 | 0.8130 | 50 | 0.8922 | 0.5924 | 0.6200 | 0.5924 | 0.5676 | 0.7395 |
| 0.9092 | 0.9756 | 60 | 0.8547 | 0.6261 | 0.6301 | 0.6261 | 0.6231 | 0.5882 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1