metadata

tags:
  - generated_from_trainer
model-index:
  - name: pythia-70m-deduped-aid
    results: []

pythia-70m-deduped-aid

Model description

This model is a finetune of EleutherAI/pythia-70m-deduped (from when it was instead pythia-19m-deduped), on the text_adventures.txt dataset originally intended for AI Dungeon 2. Performance will be very poor, as expected by the small model, and generations may be offensive thanks to its training data.

This model was trained for testing purposes and was intended for use with KoboldAI. A temperature of 0.5 and a repetition penalty of 1.01 were tested.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.8.0
Tokenizers 0.13.2