t5base / README.md
AathifMohammed's picture
Update README.md
179743a verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
metrics:
  - rouge
base_model: google-t5/t5-base
model-index:
  - name: t5base-ILC
    results: []

t5base-ILC

This model is a fine-tuned version of google-t5/t5-base on ILC dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1984
  • Rouge1: 8.381
  • Rouge2: 3.916
  • Rougel: 7.0243
  • Rougelsum: 7.8617
  • Gen Len: 18.9833

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: 2
  • 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 Rouge1 Rouge2 Rougel Rougelsum Gen Len
10.5936 0.49 500 4.4985 7.204 2.8587 5.9813 6.774 18.9665
3.9459 0.97 1000 3.1984 8.381 3.916 7.0243 7.8617 18.9833

Framework versions

  • PEFT 0.8.2
  • Transformers 4.39.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2