|
|
--- |
|
|
license: mit |
|
|
base_model: roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: micro_base_help_class_no_pre_seed_3 |
|
|
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. --> |
|
|
|
|
|
# micro_base_help_class_no_pre_seed_3 |
|
|
|
|
|
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: 0.3318 |
|
|
- Accuracy: 0.8454 |
|
|
- F1 Macro: 0.6580 |
|
|
|
|
|
## 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: 3 |
|
|
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| |
|
|
| 0.3515 | 1.0 | 313 | 0.3439 | 0.8536 | 0.6099 | |
|
|
| 0.3166 | 2.0 | 626 | 0.3352 | 0.8598 | 0.5733 | |
|
|
| 0.2622 | 3.0 | 939 | 0.3453 | 0.8458 | 0.6676 | |
|
|
| 0.2173 | 4.0 | 1252 | 0.5821 | 0.8618 | 0.5924 | |
|
|
| 0.1634 | 5.0 | 1565 | 0.7321 | 0.8542 | 0.6490 | |
|
|
| 0.126 | 6.0 | 1878 | 0.8761 | 0.8264 | 0.6615 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.19.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
