|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: citation_intent_classification_roberta |
|
|
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. --> |
|
|
|
|
|
# citation_intent_classification_roberta |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.9427 |
|
|
- Accuracy: 0.7986 |
|
|
- F1 Macro: 0.6913 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.06 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| |
|
|
| 1.4059 | 1.0 | 105 | 1.0585 | 0.6491 | 0.2714 | |
|
|
| 1.0405 | 2.0 | 211 | 0.9258 | 0.6842 | 0.3254 | |
|
|
| 0.8144 | 3.0 | 316 | 0.7686 | 0.7281 | 0.4907 | |
|
|
| 0.5887 | 4.0 | 422 | 0.7906 | 0.7456 | 0.5518 | |
|
|
| 0.404 | 5.0 | 527 | 0.6946 | 0.7719 | 0.7045 | |
|
|
| 0.3302 | 6.0 | 633 | 0.8840 | 0.7719 | 0.6330 | |
|
|
| 0.225 | 7.0 | 738 | 0.8200 | 0.8070 | 0.7258 | |
|
|
| 0.1843 | 8.0 | 844 | 0.8336 | 0.8070 | 0.7533 | |
|
|
| 0.16 | 9.0 | 949 | 0.8221 | 0.8246 | 0.7641 | |
|
|
| 0.0977 | 9.95 | 1050 | 0.8798 | 0.8246 | 0.7649 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 1.13.1+cu117 |
|
|
- Datasets 2.13.2 |
|
|
- Tokenizers 0.13.3 |
|
|
|
