mpt-mini-shakespeare

This model was trained from scratch on "tinyshakespeare" text file.

Model description

The configuration and code is adapted from mosaicml/mpt-7b-storywriter, with configuration parameters changed to make it a very tiny model.

Intended uses & limitations

Intended just to aid debugging efforts of a GGML port of mpt-7b-storywriter.

Training and evaluation data

https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt

Training procedure

Just used the single tinyshakespeare text file as both the training and validation set (split up into paragraphs). See:

https://colab.research.google.com/drive/19tKIegIr0IThbItQnY2m7Y7B6AKbz6Cw?usp=sharing

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0005
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 1

Training results

Mediocre, as expected.

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3