pszemraj's picture
Update README.md
4724ac1
metadata
base_model: roneneldan/TinyStories-33M
tags:
  - generated_from_trainer
metrics:
  - accuracy
inference:
  parameters:
    max_new_tokens: 64
    do_sample: true
    repetition_penalty: 1.1
    no_repeat_ngram_size: 5
    guidance_scale: 1.01
    eta_cutoff: 0.001
widget:
  - text: My name is El Microondas the Wise and
    example_title: El Microondas
  - text: A meme is
    example_title: meme
  - text: >-
      Barack Obama nominated Hilary Clinton as his secretary of state on Monday.
      He chose her because she had
    example_title: Coreference resolution
  - text: >-
      On a shelf, there are five books: a gray book, a red book, a purple book,
      a blue book, and a black book
    example_title: Logic puzzles
  - text: >-
      The two men running to become New York City's next mayor will face off in
      their first debate Wednesday night
    example_title: Reading comprehension
pipeline_tag: text-generation
datasets:
  - pszemraj/simple_wikipedia_LM
license: apache-2.0
language:
  - en

GPT-Neo-33M-simplewiki-2048-scratch

Initialized from random weights based on config from roneneldan/TinyStories-33M, 3 epochs bf16.

It achieves the following results on the evaluation set:

  • Loss: 3.9511
  • Accuracy: 0.3843

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: 0.0005
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 80085
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
  • lr_scheduler_type: inverse_sqrt
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
5.4676 0.45 100 5.0139 0.2811
5.1729 0.89 200 4.6737 0.3050
4.8702 1.34 300 4.4922 0.3170
4.5538 1.79 400 4.3026 0.3348
4.4818 2.23 500 4.0908 0.3649
4.4583 2.68 600 3.9511 0.3843

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.2.0.dev20230907+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3