metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-small-finetuned-NL2BASH-customv3
results: []
t5-small-finetuned-NL2BASH-customv3
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: 1.2677
- Nl2bash M: 0.6643
- Gen Len: 13.1786
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: 0.0001
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Nl2bash M | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 126 | 2.4842 | 0.3006 | 12.6508 |
No log | 2.0 | 252 | 1.9796 | 0.4956 | 12.6468 |
No log | 3.0 | 378 | 1.7191 | 0.5892 | 12.9365 |
2.3246 | 4.0 | 504 | 1.5621 | 0.6191 | 12.7063 |
2.3246 | 5.0 | 630 | 1.4458 | 0.6451 | 13.0714 |
2.3246 | 6.0 | 756 | 1.3707 | 0.6633 | 12.9524 |
2.3246 | 7.0 | 882 | 1.3228 | 0.6695 | 12.9048 |
1.415 | 8.0 | 1008 | 1.2921 | 0.6661 | 13.0357 |
1.415 | 9.0 | 1134 | 1.2737 | 0.6648 | 13.1905 |
1.415 | 10.0 | 1260 | 1.2677 | 0.6643 | 13.1786 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.6.1
- Tokenizers 0.11.0