|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- ag_news |
|
model-index: |
|
- name: roberta-base_ag_news |
|
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_ag_news |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the ag_news dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3583 |
|
|
|
## 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 |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.3692 | 1.0 | 7500 | 0.4305 | |
|
| 1.6035 | 2.0 | 15000 | 1.8071 | |
|
| 0.6766 | 3.0 | 22500 | 0.4494 | |
|
| 0.3733 | 4.0 | 30000 | 0.3943 | |
|
| 0.2483 | 5.0 | 37500 | 0.3583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.3 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
