t5-small-finetuned-English-to-BASH

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: 1.7624
• Bleu: 15.8119
• Gen Len: 7.75

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: 2e-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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	36	2.4759	9.4129	12.8472
No log	2.0	72	2.2581	14.8612	9.7639
No log	3.0	108	2.0998	16.1955	8.7222
No log	4.0	144	1.9945	14.576	8.4444
No log	5.0	180	1.9181	15.4464	8.1806
No log	6.0	216	1.8639	14.7446	7.9028
No log	7.0	252	1.8185	14.5825	8.0833
No log	8.0	288	1.7867	14.9773	7.9444
No log	9.0	324	1.7679	15.8119	7.75
No log	10.0	360	1.7624	15.8119	7.75

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2