{
  "event": "training_done",
  "status": "success",
  "phase": "sft",
  "base_model": "open-thoughts/OpenThinker-7B",
  "train_file": "datasets/training_set_filtered_code_max.jsonl",
  "output_dir": "outputs/reasoning_abort_sft/openthinker_7b/rust/lr5e-05/adapter",
  "task": "rust",
  "learning_rate": 5e-05,
  "epochs": 5,
  "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": "2026-08-18T08:51:53.366275+00:00",
  "training_started_at": "2026-08-18T08:52:24.570008+00:00",
  "ended_at": "2026-08-18T08:58:09.164781+00:00",
  "wall_clock_seconds": 344.59478535997914,
  "seconds": 344.59478535997914,
  "end_to_end_seconds": 375.7985213450156,
  "trainer_train_runtime": 343.6113,
  "trainer_metrics": {
    "train_runtime": 343.6113,
    "train_samples_per_second": 98.382,
    "train_steps_per_second": 6.155,
    "total_flos": 3752575772295168.0,
    "train_loss": 1.2751911828915279,
    "epoch": 0.02839396628216504
  }
}