{
  "event": "training_done",
  "status": "success",
  "phase": "sft",
  "base_model": "open-thoughts/OpenThinker-7B",
  "train_file": "datasets/TLDR_train_filtered_10k.jsonl",
  "output_dir": "outputs/reasoning_abort_sft/openthinker_7b/text/lr5e-05-run2/adapter",
  "task": "summarization",
  "learning_rate": 5e-05,
  "epochs": 1,
  "batch_size": 2,
  "gradient_accumulation_steps": 8,
  "effective_batch_size": 16,
  "max_length": 3000,
  "target_mode": "standard",
  "full_finetune": false,
  "kl_coefficient": 0.0,
  "kl_temperature": 1.0,
  "kl_mask_mode": "full",
  "last_checkpoint": null,
  "function_started_at": "2026-08-18T08:51:53.397627+00:00",
  "training_started_at": "2026-08-18T08:52:24.704136+00:00",
  "ended_at": "2026-08-18T09:07:51.257658+00:00",
  "wall_clock_seconds": 926.5535331210122,
  "seconds": 926.5535331210122,
  "end_to_end_seconds": 957.8600465520285,
  "trainer_train_runtime": 925.7075,
  "trainer_metrics": {
    "train_runtime": 925.7075,
    "train_samples_per_second": 10.803,
    "train_steps_per_second": 0.675,
    "total_flos": 4173075710189568.0,
    "train_loss": 2.5310071309407554,
    "epoch": 0.0192
  }
}