{
  "OUT_DIR": "/content/van_fast_transformer",
  "TOKENIZER_NAME": "gpt2",
  "DATASET_NAME": "HuggingFaceFW/fineweb-edu",
  "DATASET_CONFIG": "sample-10BT",
  "DATASET_SPLIT": "train",
  "TEXT_KEY": "text",
  "VOCAB_SIZE": 50257,
  "BLOCK_SIZE": 1024,
  "D_MODEL": 1024,
  "N_LAYER": 18,
  "N_HEAD": 16,
  "N_KV_HEAD": 4,
  "D_FF": 4096,
  "DROPOUT": 0.0,
  "USE_QK_NORM": true,
  "MAX_STEPS": 5000,
  "BATCH_SIZE": 1,
  "GRAD_ACCUM": 4,
  "LR": 0.0003,
  "MIN_LR": 3e-05,
  "WARMUP_STEPS": 300,
  "WEIGHT_DECAY": 0.1,
  "BETA1": 0.9,
  "BETA2": 0.95,
  "MAX_GRAD_NORM": 1.0,
  "EARLY_STOP_LOSS": 0.0001,
  "EARLY_STOP_PATIENCE": 1,
  "EARLY_STOP_SAVE": true,
  "EARLY_STOP_ON_EVAL": false,
  "EARLY_STOP_EVAL_LOSS": 0.0001,
  "EARLY_STOP_EVAL_PATIENCE": 2,
  "LOG_EVERY": 10,
  "EVAL_EVERY": 1000,
  "SAVE_EVERY": 1000,
  "EVAL_BATCHES": 4,
  "GEN_MAX_NEW_TOKENS": 160,
  "GEN_TEMPERATURE": 0.8,
  "GEN_TOP_K": 50,
  "GEN_TOP_P": 0.95,
  "SEED": 42,
  "DTYPE": "bf16",
  "TF32": true,
  "COMPILE": true,
  "GRADIENT_CHECKPOINTING": false,
  "NUM_WORKERS": 2,
  "PIN_MEMORY": true,
  "DEBUG_SMALL": false
}