Edit model card

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
Downloads last month
9