|
--- |
|
base_model: UBC-NLP/MARBERTv2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Model3_Marabertv2_T1_WOS |
|
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. --> |
|
|
|
# Model3_Marabertv2_T1_WOS |
|
|
|
This model is a fine-tuned version of [UBC-NLP/MARBERTv2](https://huggingface.co/UBC-NLP/MARBERTv2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2308 |
|
- F1: 0.8430 |
|
- F1 Macro: 0.7804 |
|
- Roc Auc: 0.9048 |
|
- Accuracy: 0.8142 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | F1 Macro | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:-------:|:--------:| |
|
| 0.2194 | 1.0 | 507 | 0.1556 | 0.8330 | 0.7507 | 0.8909 | 0.7947 | |
|
| 0.1166 | 2.0 | 1014 | 0.1850 | 0.8269 | 0.7439 | 0.8920 | 0.8010 | |
|
| 0.0747 | 3.0 | 1521 | 0.1915 | 0.8368 | 0.7724 | 0.8992 | 0.8115 | |
|
| 0.0445 | 4.0 | 2028 | 0.2034 | 0.8398 | 0.7695 | 0.9014 | 0.8149 | |
|
| 0.0301 | 5.0 | 2535 | 0.2308 | 0.8430 | 0.7804 | 0.9048 | 0.8142 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
