{
  "job_id": "0a98a7d8fd4f",
  "tier": "500k",
  "label": "NanoDex-500k",
  "n_params": 492192,
  "target_tokens": 200000000,
  "tokens_seen": 199884800,
  "steps": 1525,
  "seq_len": 512,
  "final_loss": 3.817596435546875,
  "best_loss": 3.6255829334259033,
  "peak_lr": 0.004,
  "batch_tokens": 131072,
  "optimizer": "AdamW(0.9, 0.95) wd=0.1 clip=1.0",
  "schedule": "warmup 2% + cosine to 10%",
  "dataset": "HuggingFaceFW/fineweb-edu (sample-10BT)",
  "architecture": "LlamaForCausalLM (SiLU, RMSNorm, RoPE, GQA, tied embeddings)",
  "wall_time_s": 309.3608708381653,
  "trained_by": "DedeProGames"
}