t5-large-t5large-English-to-BASH

This model is a fine-tuned version of t5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6448
• Nl2bash M: 0.7181
• Gen Len: 14.2079

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: 4e-05
• 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
1.8995	1.0	561	1.1364	0.5124	13.7261
1.1669	2.0	1122	0.9093	0.5966	13.9349
0.9508	3.0	1683	0.8024	0.645	13.7716
0.8426	4.0	2244	0.7366	0.6696	13.9492
0.7574	5.0	2805	0.6994	0.6888	14.099
0.6884	6.0	3366	0.6756	0.6946	14.2498
0.6301	7.0	3927	0.6573	0.7101	14.3782
0.6031	8.0	4488	0.6476	0.7165	14.1793
0.5536	9.0	5049	0.6465	0.7164	14.1989
0.5443	10.0	5610	0.6448	0.7181	14.2079

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2