|
|
--- |
|
|
library_name: transformers |
|
|
base_model: UBC-NLP/MARBERT |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: task1 |
|
|
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. --> |
|
|
|
|
|
# task1 |
|
|
|
|
|
This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6486 |
|
|
- Accuracy: 0.7112 |
|
|
- Macro F1: 0.6883 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| |
|
|
| 0.773 | 1.0 | 345 | 0.6486 | 0.7112 | 0.6883 | |
|
|
| 0.5602 | 2.0 | 690 | 0.7584 | 0.6880 | 0.6497 | |
|
|
| 0.3315 | 3.0 | 1035 | 0.9695 | 0.6720 | 0.6594 | |
|
|
| 0.196 | 4.0 | 1380 | 1.4219 | 0.6647 | 0.6559 | |
|
|
| 0.1183 | 5.0 | 1725 | 1.6137 | 0.6655 | 0.6503 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.1 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 2.14.4 |
|
|
- Tokenizers 0.21.2 |
|
|
|
