{
 "batch_size": 32,
 "boundary_every": 18080,
 "context": 512,
 "conversation_epochs": 3,
 "init": "normal-0.02-tied-v1",
 "model": {
  "attn_impl": "manual",
  "dropout": 0,
  "embed_dim": 384,
  "max_seq_len": 512,
  "num_heads": 6,
  "num_layers": 6,
  "vocab_size": 32000
 },
 "schedule": {
  "conversation": "0.0001",
  "floor": "0.00006",
  "peak": "0.0006",
  "warmup": 2000,
  "wikipedia_updates": 560177
 },
 "seed": 1234,
 "weight_decay": "0.01"
}