training_metrics.json

{
  "wall_seconds": 232.53715324401855,
  "records_seen": 615,
  "requested_records": 615,
  "truncated_records": 0,
  "rejected_records": 0,
  "optimizer_steps": 80,
  "forward_tokens": 209595,
  "peak_device_bytes": 20358582784,
  "device": "cuda",
  "dtype": "bf16",
  "batch": 4,
  "peak_rss_bytes": 31542779904
}