pszemraj's picture
Update README.md
d64c2c8
|
raw
history blame
2.13 kB
metadata
license: other
tags:
  - generated_from_trainer
  - text generation
  - stable diffusion
  - midjourney
  - text2image
  - text to image
datasets:
  - pszemraj/text2image-prompts-multi
widget:
  - text: morning sun over Jakarta
    example_title: morning sun
  - text: 'WARNING: pip is'
    example_title: pip
  - text: sentient cheese
    example_title: sentient cheese
  - text: cheeps are
    example_title: cheeps
  - text: avocado armchair
    example_title: creative prompt
  - text: Landscape of
    example_title: landscape
parameters:
  min_length: 16
  max_length: 96
  no_repeat_ngram_size: 1
  do_sample: true

OPT-350m-multiprompt-v1

This model is a fine-tuned version of facebook/opt-350m on the pszemraj/text2image-prompts-multi dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6669

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 256
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.04
  • num_epochs: 4.0

Training results

Training Loss Epoch Step Validation Loss
2.1677 1.0 990 2.0888
1.856 2.0 1980 1.8215
1.6864 3.0 2970 1.6935
1.6228 4.0 3960 1.6670

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.6.1
  • Tokenizers 0.13.1