|
|
--- |
|
|
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: stocks |
|
|
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. --> |
|
|
|
|
|
# stocks |
|
|
|
|
|
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: 0.6553 |
|
|
- Accuracy: 0.8101 |
|
|
- Precision: 0.8111 |
|
|
- Recall: 0.8101 |
|
|
- F1: 0.8099 |
|
|
- Ratio: 0.5289 |
|
|
|
|
|
## 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: 2 |
|
|
- label_smoothing_factor: 0.1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:| |
|
|
| 3.5199 | 0.1626 | 10 | 1.7420 | 0.5530 | 0.5581 | 0.5530 | 0.5431 | 0.6477 | |
|
|
| 1.6995 | 0.3252 | 20 | 1.3228 | 0.5356 | 0.5554 | 0.5356 | 0.4899 | 0.2007 | |
|
|
| 1.1579 | 0.4878 | 30 | 0.9331 | 0.5785 | 0.5796 | 0.5785 | 0.5771 | 0.4423 | |
|
|
| 0.9588 | 0.6504 | 40 | 0.8592 | 0.6329 | 0.6340 | 0.6329 | 0.6321 | 0.5450 | |
|
|
| 0.91 | 0.8130 | 50 | 0.8239 | 0.6738 | 0.7473 | 0.6738 | 0.6477 | 0.7725 | |
|
|
| 0.8624 | 0.9756 | 60 | 0.8217 | 0.6 | 0.7217 | 0.6 | 0.5364 | 0.1295 | |
|
|
| 0.8238 | 1.1382 | 70 | 0.7594 | 0.7477 | 0.7802 | 0.7477 | 0.7401 | 0.6705 | |
|
|
| 0.7669 | 1.3008 | 80 | 0.6968 | 0.7913 | 0.7922 | 0.7913 | 0.7911 | 0.5289 | |
|
|
| 0.7648 | 1.4634 | 90 | 0.6744 | 0.8007 | 0.8015 | 0.8007 | 0.8005 | 0.4738 | |
|
|
| 0.691 | 1.6260 | 100 | 0.6739 | 0.7993 | 0.8029 | 0.7993 | 0.7987 | 0.5544 | |
|
|
| 0.6698 | 1.7886 | 110 | 0.6616 | 0.8067 | 0.8091 | 0.8067 | 0.8063 | 0.5443 | |
|
|
| 0.6985 | 1.9512 | 120 | 0.6553 | 0.8101 | 0.8111 | 0.8101 | 0.8099 | 0.5289 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.19.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
