metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-small-ENG2BASH-custom-v1
results: []
t5-small-ENG2BASH-custom-v1
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3310
- Bleu: 70.3128
- Gen Len: 6.9231
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 63 | 0.8398 | 27.5197 | 7.359 |
| No log | 2.0 | 126 | 0.6711 | 41.7615 | 7.5385 |
| No log | 3.0 | 189 | 0.5641 | 48.7739 | 7.4872 |
| No log | 4.0 | 252 | 0.4450 | 64.3927 | 7.5641 |
| No log | 5.0 | 315 | 0.4014 | 57.3713 | 7.4359 |
| No log | 6.0 | 378 | 0.3782 | 70.692 | 7.1795 |
| No log | 7.0 | 441 | 0.3501 | 72.8414 | 7.2051 |
| 0.5299 | 8.0 | 504 | 0.3378 | 68.7268 | 7.0769 |
| 0.5299 | 9.0 | 567 | 0.3361 | 70.3128 | 6.9231 |
| 0.5299 | 10.0 | 630 | 0.3310 | 70.3128 | 6.9231 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2