|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: roberta-base-Roberta-Model |
|
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. --> |
|
|
|
# roberta-base-Roberta-Model |
|
|
|
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: 0.8450 |
|
- F1: 0.6468 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.916 | 0.5 | 500 | 0.8835 | 0.6218 | |
|
| 0.8783 | 1.0 | 1000 | 0.8467 | 0.6531 | |
|
| 0.8769 | 1.5 | 1500 | 0.8581 | 0.6487 | |
|
| 0.8499 | 2.01 | 2000 | 0.8651 | 0.6488 | |
|
| 0.8734 | 2.51 | 2500 | 0.8908 | 0.6409 | |
|
| 0.8597 | 3.01 | 3000 | 0.8923 | 0.6409 | |
|
| 0.8987 | 3.51 | 3500 | 0.8999 | 0.6215 | |
|
| 0.879 | 4.01 | 4000 | 0.9219 | 0.6220 | |
|
| 0.8892 | 4.51 | 4500 | 0.8936 | 0.6220 | |
|
| 0.8926 | 5.02 | 5000 | 0.8914 | 0.6226 | |
|
| 0.975 | 5.52 | 5500 | 0.8984 | 0.6405 | |
|
| 0.9387 | 6.02 | 6000 | 1.1061 | 0.2347 | |
|
| 0.9446 | 6.52 | 6500 | 0.8879 | 0.6436 | |
|
| 0.879 | 7.02 | 7000 | 0.9053 | 0.6216 | |
|
| 0.8657 | 7.52 | 7500 | 0.8552 | 0.6446 | |
|
| 0.8396 | 8.02 | 8000 | 0.8535 | 0.6475 | |
|
| 0.8264 | 8.53 | 8500 | 0.8476 | 0.6519 | |
|
| 0.8555 | 9.03 | 9000 | 0.8450 | 0.6468 | |
|
| 0.851 | 9.53 | 9500 | 0.8807 | 0.6404 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
