metadata
license: apache-2.0
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
model-index:
- name: tiny-gpt2-br
results: []
tiny-gpt2-br
This model is a fine-tuned version of distilbert/distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8488
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: 0.0002
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.2132 | 0.21 | 1000 | 5.2772 |
| 5.0485 | 0.42 | 2000 | 4.7982 |
| 4.7238 | 0.63 | 3000 | 4.5621 |
| 4.5529 | 0.84 | 4000 | 4.4206 |
| 4.4022 | 1.05 | 5000 | 4.3098 |
| 4.2349 | 1.26 | 6000 | 4.2299 |
| 4.1795 | 1.47 | 7000 | 4.1560 |
| 4.1286 | 1.68 | 8000 | 4.0875 |
| 4.0866 | 1.89 | 9000 | 4.0361 |
| 3.9584 | 2.1 | 10000 | 4.0204 |
| 3.8666 | 2.31 | 11000 | 3.9785 |
| 3.8471 | 2.52 | 12000 | 3.9498 |
| 3.8463 | 2.73 | 13000 | 3.9202 |
| 3.8116 | 2.94 | 14000 | 3.8936 |
| 3.697 | 3.15 | 15000 | 3.8964 |
| 3.6553 | 3.36 | 16000 | 3.8825 |
| 3.6525 | 3.56 | 17000 | 3.8660 |
| 3.6494 | 3.77 | 18000 | 3.8522 |
| 3.6542 | 3.98 | 19000 | 3.8488 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2