{
  "timestamp": "2026-10-07 23:46:47",
  "device": {
    "python": "3.14.7",
    "torch": "2.14.1+cu130",
    "cuda_build": "13.0",
    "cudnn": 92400,
    "device": "NVIDIA GeForce RTX 3090 Ti",
    "sm": "8.6",
    "vram_gib": 23.6,
    "bf16": true,
    "free_gib": 21.52
  },
  "alloc_conf": "expandable_segments:True",
  "baseline_device_used_gib": 2.08,
  "model_config": {
    "vocab_size": 32768,
    "max_seq_len": 512,
    "d_model": 1024,
    "n_layers": 24,
    "n_heads": 16,
    "d_ff": 4096,
    "dropout": 0.1,
    "attention_dropout": 0.1,
    "layer_norm_eps": 1e-05,
    "pad_token_id": 0,
    "tie_mlm_head": true,
    "grad_checkpointing": false,
    "num_labels": 2
  },
  "param_counts": {
    "mlm": {
      "total": 337476608,
      "trainable": 337476608,
      "embeddings": 34080768,
      "encoder_layers": 302309376,
      "final_norm": 2048,
      "head": 1084416
    },
    "classifier": {
      "total": 337443842,
      "trainable": 337443842,
      "embeddings": 34080768,
      "encoder_layers": 302309376,
      "final_norm": 2048,
      "head": 1051650
    }
  },
  "data": {
    "source": "real",
    "detail": "3000 docs (6,139,250 chars) -> 1,592,926 tokens -> 3111 packed x 512",
    "n_sequences": 3111,
    "seq_len": 512,
    "mlm_probability": 0.15,
    "mask_replace_probs": [
      0.8,
      0.1,
      0.1
    ]
  },
  "vram_policy": {
    "target_gb_low": 14,
    "target_gb_high": 18,
    "hard_cap_gb": 20,
    "alloc_conf": "expandable_segments:True",
    "log_peak_every_steps": 20
  },
  "vram_policy_unit": "config vram.*_gb values are read as GiB and compared with torch.cuda.max_memory_reserved() / 2**30",
  "finder": {
    "candidates": [
      16,
      24,
      12,
      8
    ],
    "ckpt_candidates": [
      16,
      24,
      12,
      8
    ],
    "probe_steps": 3,
    "micro_steps_per_probe_step": 2,
    "no_ckpt": [
      {
        "micro_batch": 16,
        "grad_checkpointing": false,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 13.524,
        "max_reserved_gib": 13.654,
        "device_used_after_gib": 15.802,
        "ms_per_micro_step": 346.5,
        "tokens_per_s": 23642,
        "error": null
      },
      {
        "micro_batch": 24,
        "grad_checkpointing": false,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 17.44,
        "max_reserved_gib": 17.65,
        "device_used_after_gib": 19.796,
        "ms_per_micro_step": 487.1,
        "tokens_per_s": 25227,
        "error": null
      },
      {
        "micro_batch": 12,
        "grad_checkpointing": false,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 11.571,
        "max_reserved_gib": 11.775,
        "device_used_after_gib": 13.921,
        "ms_per_micro_step": 261.6,
        "tokens_per_s": 23487,
        "error": null
      },
      {
        "micro_batch": 8,
        "grad_checkpointing": false,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 9.593,
        "max_reserved_gib": 9.705,
        "device_used_after_gib": 11.851,
        "ms_per_micro_step": 190.6,
        "tokens_per_s": 21493,
        "error": null
      }
    ],
    "ckpt": [
      {
        "micro_batch": 16,
        "grad_checkpointing": true,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 6.82,
        "max_reserved_gib": 7.381,
        "device_used_after_gib": 9.526,
        "ms_per_micro_step": 457.6,
        "tokens_per_s": 17901,
        "error": null
      },
      {
        "micro_batch": 24,
        "grad_checkpointing": true,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 7.396,
        "max_reserved_gib": 8.064,
        "device_used_after_gib": 10.21,
        "ms_per_micro_step": 641.5,
        "tokens_per_s": 19156,
        "error": null
      },
      {
        "micro_batch": 12,
        "grad_checkpointing": true,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 6.538,
        "max_reserved_gib": 6.932,
        "device_used_after_gib": 9.077,
        "ms_per_micro_step": 342.9,
        "tokens_per_s": 17916,
        "error": null
      },
      {
        "micro_batch": 8,
        "grad_checkpointing": true,
        "ok": true,
        "steps": 3,
        "micro_steps": 2,
        "max_allocated_gib": 6.256,
        "max_reserved_gib": 6.58,
        "device_used_after_gib": 8.728,
        "ms_per_micro_step": 247.2,
        "tokens_per_s": 16573,
        "error": null
      }
    ],
    "chosen_micro_batch": 24,
    "reason": "largest candidate with reserved peak in [14, 18] GiB (17.65 GiB)",
    "chosen_micro_batch_ckpt": 24,
    "reason_ckpt": "no candidate reached 14 GiB; largest under 18 GiB (8.064 GiB)",
    "throughput_peak_reserved_gib": 17.65,
    "throughput_within_hard_cap": true,
    "throughput_in_target_band": true
  },
  "throughput": {
    "micro_batch": 24,
    "grad_accumulation": 11,
    "effective_batch": 264,
    "effective_batch_target": 256,
    "effective_batch_matches_target": false,
    "peak_reserved_gib": 17.65,
    "peak_allocated_gib": 17.448,
    "timed_micro_steps": 20,
    "warmup_micro_steps": 3,
    "ms_per_micro_step_raw": 487.15,
    "ms_fwd_bwd": 486.26,
    "ms_optimizer_step": 17.78,
    "ms_per_optimizer_step_total": 5366.7,
    "tokens_per_s_raw": 25224,
    "tokens_per_s_effective": 25187,
    "epoch_tokens": 105836752.22169875,
    "optimizer_steps_per_epoch": 783,
    "hours_per_epoch": 1.17,
    "hours_3_epochs": 3.5,
    "vram": {
      "allocated_gb": 3.799478054046631,
      "reserved_gb": 4.177734375,
      "max_allocated_gb": 17.447842597961426,
      "max_reserved_gb": 17.650390625
    },
    "epoch_tokens_source": "splits_manifest.json 407,902,364 chars x 0.2595 tok/char"
  },
  "sdpa_backends": {
    "flash_no_mask": "ran",
    "efficient_bool_mask": "ran",
    "flash_bool_mask_expected_fail": "unavailable: No available kernel. Aborting execution.",
    "flags": {
      "flash_sdp_enabled": true,
      "mem_efficient_sdp_enabled": true,
      "math_sdp_enabled": true
    }
  },
  "convergence": {
    "micro_batch": 24,
    "steps": 30,
    "lr": 0.0001,
    "warmup_steps": 10,
    "ln_vocab": 10.3972,
    "first_loss": 10.5846,
    "last_loss": 7.6686,
    "drop": 2.916,
    "losses": [
      [
        1,
        10.5846
      ],
      [
        5,
        9.6535
      ],
      [
        10,
        8.9505
      ],
      [
        15,
        8.6266
      ],
      [
        20,
        8.1493
      ],
      [
        25,
        7.9209
      ],
      [
        30,
        7.6686
      ]
    ],
    "data": "real",
    "vram": {
      "allocated_gb": 3.799478054046631,
      "reserved_gb": 4.19921875,
      "max_allocated_gb": 17.447842597961426,
      "max_reserved_gb": 17.650390625
    }
  },
  "latency": {
    "instructor_benchmark_ms": 74.0,
    "params": 337443842,
    "gpu_bf16_512_no_mask": {
      "n": 100,
      "avg_ms": 10.7,
      "p50_ms": 10.71,
      "max_ms": 11.27
    },
    "gpu_bf16_512_bool_mask": {
      "n": 100,
      "avg_ms": 11.53,
      "p50_ms": 11.51,
      "max_ms": 12.14
    },
    "cpu_threads": 16,
    "cpu_fp32_512": {
      "n": 10,
      "avg_ms": 698.8,
      "p50_ms": 695.6,
      "max_ms": 753.9
    },
    "cpu_fp32_128": {
      "n": 10,
      "avg_ms": 319.0,
      "p50_ms": 320.6,
      "max_ms": 345.1
    }
  },
  "runtime_s": 76.1,
  "report_path": "/home/nathank/BITS/dev/Phishing Model/reports/smoke_test.json"
}