gpt2-dzongkha-romanization
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2720
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: 32
- 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: 126
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 16 | 7.3217 |
| No log | 2.0 | 32 | 5.7643 |
| No log | 3.0 | 48 | 4.6550 |
| 6.7417 | 4.0 | 64 | 3.6417 |
| 6.7417 | 5.0 | 80 | 2.9877 |
| 6.7417 | 6.0 | 96 | 2.6377 |
| 3.707 | 7.0 | 112 | 2.4576 |
| 3.707 | 8.0 | 128 | 2.3539 |
| 3.707 | 9.0 | 144 | 2.2833 |
| 2.6959 | 10.0 | 160 | 2.2720 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2