t5-small-t5small-NL2BASH_testmetric

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

• Loss: 0.8419
• Nl2bash M metric score: 0.6705
• Gen Len: 14.1204

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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Nl2bash M metric score	Gen Len
1.9108	1.0	561	1.3959	0.4604	13.2667
1.4715	2.0	1122	1.1810	0.5367	14.2346
1.2636	3.0	1683	1.0533	0.5829	13.8903
1.1565	4.0	2244	0.9805	0.6189	14.0642
1.0652	5.0	2805	0.9298	0.6389	14.1401
0.9923	6.0	3366	0.8979	0.6479	14.0285
0.9259	7.0	3927	0.8678	0.6576	14.2453
0.8942	8.0	4488	0.8515	0.6648	14.1418
0.8456	9.0	5049	0.8452	0.6728	14.0714
0.8273	10.0	5610	0.8419	0.6705	14.1204

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.0
• Tokenizers 0.13.2