{
  "started_at_brasilia": "2026-11-10T16:11:11.132132-03:00",
  "hardware": {
    "cpu": "Intel(R) Xeon(R) Processor",
    "logical_cpus": 8,
    "ram_total_gib": 15.627,
    "gpu_available": false
  },
  "versions": {
    "python": "3.13.5",
    "torch": "2.15.0+cpu",
    "transformers": "4.57.6",
    "peft": "0.21.2",
    "datasets": "5.0.1",
    "accelerate": "1.15.0"
  },
  "sources": {
    "model": {
      "id": "TucanoBR/Tucano-160m",
      "revision": "6331cbef9933c05d8d0c8ae5ee23ed2570f06571"
    },
    "dataset": {
      "id": "OpenAssistant/oasst2",
      "revision": "179dd21fc55192153d94adb0e0ce8f69e222bf75"
    }
  },
  "config": {
    "seed": 42,
    "threads": 6,
    "epochs": 6,
    "micro_batch_size": 4,
    "gradient_accumulation_steps": 4,
    "effective_batch_size": 16,
    "learning_rate": 0.0003,
    "weight_decay": 0.01,
    "warmup_ratio": 0.1,
    "max_grad_norm": 1.0,
    "rank": 16,
    "lora_alpha": 32,
    "lora_dropout": 0.05,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ],
    "max_length": 384,
    "precision": "CPU bfloat16 autocast; float32 base weights and trainable adapters",
    "loss": "completion-only token-weighted next-token negative log likelihood, including EOS"
  },
  "trainable_parameters": 3391488,
  "total_parameters_with_adapter": 165808896,
  "base_parameters": 162417408,
  "split_examples": {
    "train": 94,
    "validation": 12,
    "test": 12
  },
  "before": {
    "validation": {
      "loss": 2.356751855036902,
      "perplexity": 10.55660631600646,
      "response_tokens": 1522,
      "examples": 12,
      "seconds": 0.7319192210052279
    },
    "test": {
      "loss": 2.430188522578911,
      "perplexity": 11.361023687609077,
      "response_tokens": 1907,
      "examples": 12,
      "seconds": 0.6798040540015791
    }
  },
  "best_epoch": 2,
  "after": {
    "validation": {
      "loss": 2.2419521171066044,
      "perplexity": 9.411686079660129,
      "response_tokens": 1522,
      "examples": 12,
      "seconds": 0.5894143010009429
    },
    "test": {
      "loss": 2.3471716908678437,
      "perplexity": 10.455955191388183,
      "response_tokens": 1907,
      "examples": 12,
      "seconds": 0.6937924470039434
    }
  },
  "training_started_at_brasilia": "2026-11-10T16:11:25.463075-03:00",
  "training_finished_at_brasilia": "2026-11-10T16:14:04.097314-03:00",
  "training_seconds_excluding_evaluation": 154.74840372199833,
  "validation_seconds_during_training": 3.513742549010203,
  "optimizer_steps": 36,
  "supervised_tokens_across_epochs": 75084,
  "history": [
    {
      "event": "epoch",
      "epoch": 1,
      "optimizer_steps": 6,
      "train_loss": 2.2584660765231943,
      "train_seconds": 25.907004280001274,
      "validation": {
        "loss": 2.2768132312225764,
        "perplexity": 9.745573980476506,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.5419957140038605
      }
    },
    {
      "event": "epoch",
      "epoch": 2,
      "optimizer_steps": 12,
      "train_loss": 2.098645087989428,
      "train_seconds": 25.95503581200319,
      "validation": {
        "loss": 2.242185463416592,
        "perplexity": 9.413882518133018,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.5481375860035769
      }
    },
    {
      "event": "epoch",
      "epoch": 3,
      "optimizer_steps": 18,
      "train_loss": 1.981365356522283,
      "train_seconds": 24.54493858999922,
      "validation": {
        "loss": 2.243609419633462,
        "perplexity": 9.427297023236907,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.6372171650000382
      }
    },
    {
      "event": "epoch",
      "epoch": 4,
      "optimizer_steps": 24,
      "train_loss": 1.8920829225523852,
      "train_seconds": 25.12302869799896,
      "validation": {
        "loss": 2.24681126335134,
        "perplexity": 9.457530130000158,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.5965341569972225
      }
    },
    {
      "event": "epoch",
      "epoch": 5,
      "optimizer_steps": 30,
      "train_loss": 1.8361153760542404,
      "train_seconds": 26.84980382199865,
      "validation": {
        "loss": 2.248372650961055,
        "perplexity": 9.472308534770303,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.5754360380014987
      }
    },
    {
      "event": "epoch",
      "epoch": 6,
      "optimizer_steps": 36,
      "train_loss": 1.8106174533771444,
      "train_seconds": 26.368592519997037,
      "validation": {
        "loss": 2.2492608048129488,
        "perplexity": 9.48072513914832,
        "response_tokens": 1522,
        "examples": 12,
        "seconds": 0.6144218890040065
      }
    }
  ],
  "wall_seconds_including_baselines_and_generations": 187.06369254900346,
  "max_process_rss_gib": 5.4983062744140625,
  "finished_at_brasilia": "2026-11-10T16:14:17.906711-03:00"
}