metadata

license: mit
base_model: EleutherAI/gpt-neo-125m
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: neox_125m_storytelling
    results: []

neox_125m_storytelling

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None 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: 4e-05
train_batch_size: 1
eval_batch_size: 8
seed: 8675309
distributed_type: multi-GPU
num_devices: 7
gradient_accumulation_steps: 4
total_train_batch_size: 28
total_eval_batch_size: 56
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
num_epochs: 1

Training results

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.19.2
Tokenizers 0.19.1