ppo1 / README.md
vwxyzjn's picture
End of training
2bac670 verified
|
raw
history blame
1.11 kB
metadata
license: apache-2.0
base_model: EleutherAI/pythia-1b-deduped
tags:
  - generated_from_trainer
model-index:
  - name: ppo1
    results: []

ppo1

This model is a fine-tuned version of EleutherAI/pythia-1b-deduped on an unknown dataset.

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: 3e-06
  • train_batch_size: 32
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 512
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1