|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilgpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: tiny-gpt2-br |
|
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. --> |
|
|
|
# tiny-gpt2-br |
|
|
|
This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.3565 |
|
|
|
## 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: 8e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 32 |
|
- 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 6.6049 | 0.21 | 1000 | 5.6029 | |
|
| 5.4429 | 0.42 | 2000 | 5.1985 | |
|
| 5.1379 | 0.63 | 3000 | 4.9480 | |
|
| 4.9697 | 0.84 | 4000 | 4.8117 | |
|
| 4.82 | 1.05 | 5000 | 4.7015 | |
|
| 4.7219 | 1.26 | 6000 | 4.6272 | |
|
| 4.648 | 1.47 | 7000 | 4.5548 | |
|
| 4.6005 | 1.68 | 8000 | 4.5024 | |
|
| 4.5511 | 1.89 | 9000 | 4.4625 | |
|
| 4.4843 | 2.1 | 10000 | 4.4290 | |
|
| 4.4343 | 2.31 | 11000 | 4.4026 | |
|
| 4.4215 | 2.52 | 12000 | 4.3810 | |
|
| 4.4033 | 2.73 | 13000 | 4.3652 | |
|
| 4.3886 | 2.94 | 14000 | 4.3565 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
