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: 0.8142
- Nl2bash M: 0.7744
- Gen Len: 13.0248
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 | 121 | 1.3408 | 0.4894 | 12.2107 |
No log | 2.0 | 242 | 1.0982 | 0.6267 | 13.2562 |
No log | 3.0 | 363 | 1.0017 | 0.6973 | 13.0207 |
No log | 4.0 | 484 | 0.9301 | 0.7292 | 12.6818 |
1.3353 | 5.0 | 605 | 0.8890 | 0.749 | 12.9752 |
1.3353 | 6.0 | 726 | 0.8643 | 0.7611 | 12.9711 |
1.3353 | 7.0 | 847 | 0.8370 | 0.7749 | 12.8471 |
1.3353 | 8.0 | 968 | 0.8265 | 0.7701 | 12.9174 |
0.887 | 9.0 | 1089 | 0.8162 | 0.7768 | 13.0289 |
0.887 | 10.0 | 1210 | 0.8142 | 0.7744 | 13.0248 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.6.1
- Tokenizers 0.11.0