training_metadata.json

{
  "out_dir": "out-nanecho-ci",
  "eval_interval": 25,
  "log_interval": 5,
  "eval_iters": 10,
  "eval_only": false,
  "always_save_checkpoint": true,
  "init_from": "scratch",
  "wandb_log": false,
  "wandb_project": "nanecho",
  "wandb_run_name": "nanecho-1771761179.4450994",
  "dataset": "nanecho",
  "gradient_accumulation_steps": 2,
  "batch_size": 2,
  "block_size": 1024,
  "n_layer": 4,
  "n_head": 4,
  "n_embd": 256,
  "dropout": 0.1,
  "bias": true,
  "learning_rate": 0.0002,
  "max_iters": 200,
  "weight_decay": 0.01,
  "beta1": 0.9,
  "beta2": 0.95,
  "grad_clip": 1.0,
  "decay_lr": true,
  "warmup_iters": 20,
  "lr_decay_iters": 200,
  "min_lr": 2e-05,
  "backend": "nccl",
  "device": "cpu",
  "dtype": "float32",
  "compile": false
}