Michelvh's picture
update model card README.md
b82054e
|
raw
history blame
1.81 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: flan-t5-end2end-question-generation
    results: []

flan-t5-end2end-question-generation

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

  • Loss: 1.6214

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7

Training results

Training Loss Epoch Step Validation Loss
2.6935 0.68 100 1.9503
2.0864 1.35 200 1.8105
1.9497 2.03 300 1.7440
1.8739 2.71 400 1.6970
1.8173 3.39 500 1.6763
1.7876 4.06 600 1.6613
1.7596 4.74 700 1.6343
1.7368 5.42 800 1.6326
1.7225 6.1 900 1.6207
1.7138 6.77 1000 1.6214

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.0
  • Datasets 2.1.0
  • Tokenizers 0.13.2