|
|
--- |
|
|
license: mit |
|
|
base_model: roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: amazon_helpfulness_classification_on_base_no_pretraining |
|
|
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. --> |
|
|
|
|
|
# amazon_helpfulness_classification_on_base_no_pretraining |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4611 |
|
|
- Accuracy: 0.8664 |
|
|
- F1 Macro: 0.6902 |
|
|
|
|
|
## 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: 16 |
|
|
- seed: 42 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| |
|
|
| 0.3234 | 1.0 | 7204 | 0.3502 | 0.8658 | 0.5841 | |
|
|
| 0.3102 | 2.0 | 14408 | 0.3271 | 0.869 | 0.6652 | |
|
|
| 0.287 | 3.0 | 21612 | 0.3579 | 0.8692 | 0.6622 | |
|
|
| 0.2685 | 4.0 | 28816 | 0.3589 | 0.872 | 0.6662 | |
|
|
| 0.2437 | 5.0 | 36020 | 0.4797 | 0.8644 | 0.6926 | |
|
|
| 0.163 | 6.0 | 43224 | 0.5644 | 0.862 | 0.6610 | |
|
|
| 0.1475 | 7.0 | 50428 | 0.5918 | 0.8638 | 0.6611 | |
|
|
| 0.1175 | 8.0 | 57632 | 0.6703 | 0.8624 | 0.6685 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
