training_run.json

{
  "job_id": "af8716cd65b1",
  "tier": "1m",
  "label": "NanoDex-1M",
  "n_params": 1000224,
  "target_tokens": 300000000,
  "tokens_seen": 299892736,
  "steps": 2288,
  "seq_len": 512,
  "final_loss": 3.5412068367004395,
  "best_loss": 3.448490619659424,
  "peak_lr": 0.003,
  "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": 883.4180929660797,
  "trained_by": "GGUFGuy"
}