Hugging Face's logo

Marcoz
/
lora

PEFT
Safetensors
Generated from Trainer
Model card Files Community
lora / README.md
Marcoz's picture
Marcoz
End of training
9211e7f verified
preview code
|
raw
history blame
1.74 kB
metadata
base_model: google-t5/t5-small
library_name: peft
tags:
  - generated_from_trainer
model-index:
  - name: ft-t5-small-on-airlineDB
    results: []

Visualize in Weights & Biases

ft-t5-small-on-airlineDB

This model is a fine-tuned version of [google t5-small](https://huggingface.co/google t5-small) on the custom airlineDB dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0992
  • Sql Em: 0.0815
  • Record Em: 0.1996
  • Record F1: 0.1996

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: 0.001
  • train_batch_size: 4
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Sql Em Record Em Record F1
0.1751 1.0 1057 0.0992 0.0815 0.1996 0.1996

Framework versions

  • PEFT 0.12.0
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1