|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: verdict-classifier |
|
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. --> |
|
|
|
# verdict-classifier |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1573 |
|
- F1 Macro: 0.0550 |
|
- F1 Misinformation: 0.0 |
|
- F1 Factual: 0.1650 |
|
- F1 Other: 0.0 |
|
- Prec Macro: 0.0300 |
|
- Prec Misinformation: 0.0 |
|
- Prec Factual: 0.0899 |
|
- Prec Other: 0.0 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 162525 |
|
- num_epochs: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Misinformation | F1 Factual | F1 Other | Prec Macro | Prec Misinformation | Prec Factual | Prec Other | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:----------:|:--------:|:----------:|:-------------------:|:------------:|:----------:| |
|
| 1.2021 | 0.0 | 50 | 1.1573 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1948 | 0.0 | 100 | 1.1569 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1968 | 0.01 | 150 | 1.1563 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1925 | 0.01 | 200 | 1.1554 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.2055 | 0.01 | 250 | 1.1544 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1927 | 0.01 | 300 | 1.1531 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1923 | 0.02 | 350 | 1.1515 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1929 | 0.02 | 400 | 1.1496 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1924 | 0.02 | 450 | 1.1476 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1862 | 0.02 | 500 | 1.1454 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
| 1.1781 | 0.03 | 550 | 1.1432 | 0.0550 | 0.0 | 0.1650 | 0.0 | 0.0300 | 0.0 | 0.0899 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.11.3 |
|
- Pytorch 1.9.0+cu102 |
|
- Datasets 1.9.0 |
|
- Tokenizers 0.10.2 |
|
|
