|
--- |
|
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: 2504v2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# 2504v2 |
|
|
|
This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6769 |
|
- Accuracy: 0.8655 |
|
- Precision: 0.8660 |
|
- Recall: 0.8655 |
|
- F1: 0.8655 |
|
- Ratio: 0.5168 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 3 |
|
- total_train_batch_size: 48 |
|
- 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: 10 |
|
- label_smoothing_factor: 0.2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:| |
|
| 4.1824 | 0.3896 | 10 | 2.4179 | 0.5084 | 0.3727 | 0.3389 | 0.3212 | 0.7479 | |
|
| 1.997 | 0.7792 | 20 | 1.6877 | 0.5462 | 0.5489 | 0.5462 | 0.5398 | 0.3824 | |
|
| 1.4096 | 1.1688 | 30 | 1.2832 | 0.5924 | 0.5939 | 0.5924 | 0.5908 | 0.5630 | |
|
| 1.1296 | 1.5584 | 40 | 1.1040 | 0.6176 | 0.6187 | 0.6176 | 0.6168 | 0.5462 | |
|
| 1.0408 | 1.9481 | 50 | 0.9666 | 0.7227 | 0.7292 | 0.7227 | 0.7207 | 0.5840 | |
|
| 0.9242 | 2.3377 | 60 | 0.8829 | 0.7815 | 0.7816 | 0.7815 | 0.7815 | 0.4916 | |
|
| 0.8948 | 2.7273 | 70 | 0.8146 | 0.7899 | 0.7940 | 0.7899 | 0.7892 | 0.4412 | |
|
| 0.842 | 3.1169 | 80 | 0.7745 | 0.7941 | 0.8101 | 0.7941 | 0.7914 | 0.6134 | |
|
| 0.7715 | 3.5065 | 90 | 0.7244 | 0.8277 | 0.8279 | 0.8277 | 0.8277 | 0.4874 | |
|
| 0.7361 | 3.8961 | 100 | 0.7224 | 0.8151 | 0.8243 | 0.8151 | 0.8138 | 0.5840 | |
|
| 0.7115 | 4.2857 | 110 | 0.7004 | 0.8403 | 0.8407 | 0.8403 | 0.8403 | 0.5168 | |
|
| 0.7076 | 4.6753 | 120 | 0.6940 | 0.8403 | 0.8407 | 0.8403 | 0.8403 | 0.4832 | |
|
| 0.7026 | 5.0649 | 130 | 0.6936 | 0.8487 | 0.8491 | 0.8487 | 0.8487 | 0.5168 | |
|
| 0.6717 | 5.4545 | 140 | 0.6912 | 0.8571 | 0.8581 | 0.8571 | 0.8571 | 0.4748 | |
|
| 0.7166 | 5.8442 | 150 | 0.6867 | 0.8571 | 0.8575 | 0.8571 | 0.8571 | 0.5168 | |
|
| 0.6606 | 6.2338 | 160 | 0.6812 | 0.8613 | 0.8616 | 0.8613 | 0.8613 | 0.4874 | |
|
| 0.6939 | 6.6234 | 170 | 0.6747 | 0.8613 | 0.8614 | 0.8613 | 0.8613 | 0.4958 | |
|
| 0.6609 | 7.0130 | 180 | 0.6744 | 0.8613 | 0.8616 | 0.8613 | 0.8613 | 0.5126 | |
|
| 0.6388 | 7.4026 | 190 | 0.6790 | 0.8529 | 0.8532 | 0.8529 | 0.8529 | 0.5126 | |
|
| 0.6435 | 7.7922 | 200 | 0.6840 | 0.8571 | 0.8572 | 0.8571 | 0.8571 | 0.5084 | |
|
| 0.6534 | 8.1818 | 210 | 0.6828 | 0.8571 | 0.8571 | 0.8571 | 0.8571 | 0.5 | |
|
| 0.6552 | 8.5714 | 220 | 0.6818 | 0.8655 | 0.8660 | 0.8655 | 0.8655 | 0.5168 | |
|
| 0.646 | 8.9610 | 230 | 0.6788 | 0.8655 | 0.8660 | 0.8655 | 0.8655 | 0.5168 | |
|
| 0.6443 | 9.3506 | 240 | 0.6770 | 0.8655 | 0.8660 | 0.8655 | 0.8655 | 0.5168 | |
|
| 0.6418 | 9.7403 | 250 | 0.6769 | 0.8655 | 0.8660 | 0.8655 | 0.8655 | 0.5168 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
