t5-small-transferLearning-NL2BASH_seqTrain
This model is a fine-tuned version of kevinum/t5-small-finetuned-English-to-BASH on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6524
- Bleu: 48.0701
- Gen Len: 8.9028
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 36 | 0.6524 | 48.0701 | 8.9028 |
| No log | 2.0 | 72 | 0.6524 | 48.0701 | 8.9028 |
| No log | 3.0 | 108 | 0.6524 | 48.0701 | 8.9028 |
| No log | 4.0 | 144 | 0.6524 | 48.0701 | 8.9028 |
| No log | 5.0 | 180 | 0.6524 | 48.0701 | 8.9028 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2