configs/sampling.yml

# Data paths and options when using EleutherAI cluster
{
  "data-path": "/mnt/ssd-1/data/enron/enron_text_document",
  # or for weighted datasets: 
  # "train-data-paths": ["/mnt/ssd-1/data/enron/enron_text_document", "/mnt/ssd-cluster/data/enron/enron_text_document"],
  # "test-data-paths": ["/mnt/ssd-1/data/enron/enron_text_document", "/mnt/ssd-cluster/data/enron/enron_text_document"],
  # "valid-data-paths": ["/mnt/ssd-1/data/enron/enron_text_document", "/mnt/ssd-cluster/data/enron/enron_text_document"],
  # "train-data-weights": [1., 2.],
  # "test-data-weights": [2., 1.],
  # "valid-data-weights": [0.5, 0.4],

  "vocab-file": "/mnt/ssd-1/data/gpt2-vocab.json",
  "merge-file": "/mnt/ssd-1/data/gpt2-merges.txt",
  "save": "/mnt/ssd-1/neox_checkpoints/dense_small_checkpoints",
  "load": "/mnt/ssd-1/neox_checkpoints/dense_small_checkpoints",
  "tensorboard-dir": "/mnt/ssd-1/tensorboard",
  "log-dir": "/mnt/ssd-1/logs",
  "wandb_team": "eleutherai",
  "sample-input-file":"/home/mchorse/gpt-neox/samplefile.txt",
  "sample-output-file":"/home/mchorse/gpt-neox/sampleoutput.txt",
  "text-gen-type": "unconditional",
  "maximum_tokens": 256,
  "temperature": 1.0,
  "top_p": 0.0,
  "top_k": 0,
  "recompute": false,
}