metadata

license: apache-2.0
base_model: t5-base
tags:
  - generated_from_trainer
  - art
model-index:
  - name: t5-base-description-prompt
    results: []
datasets:
  - gokaygokay/prompt_description_stable_diffusion_3k
language:
  - en
pipeline_tag: text2text-generation

t5-base-description-prompt

This model is a fine-tuned version of t5-base

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
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

Framework versions

Transformers 4.37.1
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1