{
 "manifest_version": "opencodifier.e1-train/5",
 "resume": null,
 "ckpt_every": 100,
 "loss_mode": "hard-verdict-ce",
 "base": "/home/mkinney/oc-model-eval/models/hf/Qwen3.5-2B",
 "data": {
  "path": "/home/mkinney/oc-model-eval/corpora/merged-v6-full/e1-sft-v1.rows.jsonl",
  "sha256": "d4aeca494955fa1531ccc3681af0763e6c21a1e7b4e2ff6d02e698033c3331df",
  "rows": 306999,
  "train": 304936,
  "val": 1999,
  "loud_skipped_over_maxlen_train": 63,
  "loud_skipped_over_maxlen_val": 1,
  "soft_bad_slotprobs_train": 0,
  "soft_bad_slotprobs_val": 0
 },
 "row_weight": {
  "field": "",
  "train_rows": 304936,
  "train_nonunit": 0,
  "train_mean": 1.0,
  "val_nonunit": 0
 },
 "knobs": {
  "epochs": 1.0,
  "lr": 0.0001,
  "lora_r": 16,
  "lora_alpha": 32,
  "lora_dropout": 0.05,
  "target_modules": [
   "q_proj",
   "k_proj",
   "v_proj",
   "o_proj"
  ],
  "batch": 2,
  "accum": 8,
  "max_len": 2048,
  "dtype": "fp16",
  "attn": "sdpa",
  "warmup": 0.03,
  "seed": 42,
  "torch_seeded": true,
  "val_frac": 0.01,
  "val_cap": 2000,
  "val_every": 500,
  "family_weight": {},
  "length_bucket": false,
  "grad_checkpoint": true,
  "soft_labels": false,
  "teacher_temp": 1.0,
  "stop_weight": 1.0
 },
 "optimizer": {
  "name": "AdamW",
  "weight_decay": 0.01,
  "betas": [
   0.9,
   0.999
  ],
  "eps": 1e-08
 },
 "versions": {
  "python": "3.12.15",
  "torch": "2.14.0+cu130",
  "transformers": "5.17.0",
  "peft": "0.21.0"
 },
 "steps": 19058,
 "final_loss_token_weighted": 0.0648,
 "tokens_per_second_wall": 44,
 "peak_memory_bytes": 4989219328,
 "loss_surface": "verdict tokens only (y=1 segments + EOS)",
 "val_history": [
  {
   "step": 500,
   "loss": 0.1197,
   "tok_acc": 0.952,
   "entropy": 0.0788,
   "per_family": {
    "choice": 0.1605,
    "noul": 0.0704,
    "relational_compositional": 0.0171,
    "score": 0.1543
   }
  },
  {
   "step": 1000,
   "loss": 0.0912,
   "tok_acc": 0.9624,
   "entropy": 0.0972,
   "per_family": {
    "choice": 0.1188,
    "noul": 0.0587,
    "relational_compositional": 0.0102,
    "score": 0.1209
   }
  },
  {
   "step": 1500,
   "loss": 0.0808,
   "tok_acc": 0.9652,
   "entropy": 0.0745,
   "per_family": {
    "choice": 0.1158,
    "noul": 0.0652,
    "relational_compositional": 0.0036,
    "score": 0.0915
   }
  },
  {
   "step": 2000,
   "loss": 0.0901,
   "tok_acc": 0.9644,
   "entropy": 0.0551,
   "per_family": {
    "choice": 0.1182,
    "noul": 0.0577,
    "relational_compositional": 0.0098,
    "score": 0.1189
   }
  },
  {
   "step": 2500,
   "loss": 0.0716,
   "tok_acc": 0.9702,
   "entropy": 0.0695,
   "per_family": {
    "choice": 0.1068,
    "noul": 0.0509,
    "relational_compositional": 0.0031,
    "score": 0.0797
   }
  },
  {
   "step": 3000,
   "loss": 0.0655,
   "tok_acc": 0.9742,
   "entropy": 0.0522,
   "per_family": {
    "choice": 0.0959,
    "noul": 0.0372,
    "relational_compositional": 0.0019,
    "score": 0.0797
   }
  },
  {
   "step": 3500,
   "loss": 0.0613,
   "tok_acc": 0.975,
   "entropy": 0.0545,
   "per_family": {
    "choice": 0.0862,
    "noul": 0.046,
    "relational_compositional": 0.0036,
    "score": 0.0726
   }
  },
  {
   "step": 4000,
   "loss": 0.0644,
   "tok_acc": 0.9734,
   "entropy": 0.0569,
   "per_family": {
    "choice": 0.0908,
    "noul": 0.0462,
    "relational_compositional": 0.0012,
    "score": 0.0785
   }
  },
  {
   "step": 4500,
   "loss": 0.0635,
   "tok_acc": 0.9759,
   "entropy": 0.051,
   "per_family": {
    "choice": 0.0868,
    "noul": 0.0527,
    "relational_compositional": 0.0004,
    "score": 0.0777
   }
  },
  {
   "step": 5000,
   "loss": 0.062,
   "tok_acc": 0.9757,
   "entropy": 0.051,
   "per_family": {
    "choice": 0.085,
    "noul": 0.0507,
    "relational_compositional": 0.0022,
    "score": 0.075
   }
  },
  {
   "step": 5500,
   "loss": 0.0587,
   "tok_acc": 0.9768,
   "entropy": 0.0495,
   "per_family": {
    "choice": 0.0811,
    "noul": 0.0516,
    "relational_compositional": 0.004,
    "score": 0.0672
   }
  },
  {
   "step": 6000,
   "loss": 0.0553,
   "tok_acc": 0.9784,
   "entropy": 0.0571,
   "per_family": {
    "choice": 0.0778,
    "noul": 0.0375,
    "relational_compositional": 0.0013,
    "score": 0.0685
   }
  },
  {
   "step": 6500,
   "loss": 0.0554,
   "tok_acc": 0.979,
   "entropy": 0.0463,
   "per_family": {
    "choice": 0.0808,
    "noul": 0.0349,
    "relational_compositional": 0.0005,
    "score": 0.0671
   }
  },
  {
   "step": 7000,
   "loss": 0.0563,
   "tok_acc": 0.977,
   "entropy": 0.0443,
   "per_family": {
    "choice": 0.0804,
    "noul": 0.0426,
    "relational_compositional": 0.0083,
    "score": 0.0621
   }
  },
  {
   "step": 7500,
   "loss": 0.0506,
   "tok_acc": 0.9797,
   "entropy": 0.0564,
   "per_family": {
    "choice": 0.0698,
    "noul": 0.0373,
    "relational_compositional": 0.0006,
    "score": 0.0633
   }
  },
  {
   "step": 8000,
   "loss": 0.0511,
   "tok_acc": 0.979,
   "entropy": 0.0506,
   "per_family": {
    "choice": 0.0722,
    "noul": 0.0344,
    "relational_compositional": 0.0005,
    "score": 0.0633
   }
  },
  {
   "step": 8500,
   "loss": 0.0509,
   "tok_acc": 0.9787,
   "entropy": 0.0451,
   "per_family": {
    "choice": 0.0731,
    "noul": 0.035,
    "relational_compositional": 0.0006,
    "score": 0.0613
   }
  },
  {
   "step": 9000,
   "loss": 0.051,
   "tok_acc": 0.9798,
   "entropy": 0.0456,
   "per_family": {
    "choice": 0.0703,
    "noul": 0.0399,
    "relational_compositional": 0.0007,
    "score": 0.0626
   }
  },
  {
   "step": 9500,
   "loss": 0.0497,
   "tok_acc": 0.9802,
   "entropy": 0.0427,
   "per_family": {
    "choice": 0.0749,
    "noul": 0.0319,
    "relational_compositional": 0.0003,
    "score": 0.0567
   }
  },
  {
   "step": 10000,
   "loss": 0.0502,
   "tok_acc": 0.9799,
   "entropy": 0.038,
   "per_family": {
    "choice": 0.0699,
    "noul": 0.0339,
    "relational_compositional": 0.0004,
    "score": 0.0637
   }
  },
  {
   "step": 10500,
   "loss": 0.048,
   "tok_acc": 0.9808,
   "entropy": 0.0361,
   "per_family": {
    "choice": 0.0664,
    "noul": 0.0295,
    "relational_compositional": 0.0019,
    "score": 0.062
   }
  },
  {
   "step": 11000,
   "loss": 0.0471,
   "tok_acc": 0.9815,
   "entropy": 0.0378,
   "per_family": {
    "choice": 0.0621,
    "noul": 0.034,
    "relational_compositional": 0.0014,
    "score": 0.0623
   }
  },
  {
   "step": 11500,
   "loss": 0.0463,
   "tok_acc": 0.9811,
   "entropy": 0.037,
   "per_family": {
    "choice": 0.0644,
    "noul": 0.037,
    "relational_compositional": 0.0009,
    "score": 0.0558
   }
  },
  {
   "step": 12000,
   "loss": 0.045,
   "tok_acc": 0.9821,
   "entropy": 0.0387,
   "per_family": {
    "choice": 0.0621,
    "noul": 0.0309,
    "relational_compositional": 0.0007,
    "score": 0.0572
   }
  },
  {
   "step": 12500,
   "loss": 0.0466,
   "tok_acc": 0.9815,
   "entropy": 0.0341,
   "per_family": {
    "choice": 0.0667,
    "noul": 0.0298,
    "relational_compositional": 0.0007,
    "score": 0.0574
   }
  },
  {
   "step": 13000,
   "loss": 0.0444,
   "tok_acc": 0.9829,
   "entropy": 0.037,
   "per_family": {
    "choice": 0.0633,
    "noul": 0.0292,
    "relational_compositional": 0.0009,
    "score": 0.0543
   }
  },
  {
   "step": 13500,
   "loss": 0.0438,
   "tok_acc": 0.982,
   "entropy": 0.0383,
   "per_family": {
    "choice": 0.0607,
    "noul": 0.0311,
    "relational_compositional": 0.0011,
    "score": 0.0545
   }
  },
  {
   "step": 14000,
   "loss": 0.042,
   "tok_acc": 0.9832,
   "entropy": 0.0357,
   "per_family": {
    "choice": 0.0589,
    "noul": 0.0298,
    "relational_compositional": 0.0006,
    "score": 0.0519
   }
  },
  {
   "step": 14500,
   "loss": 0.0408,
   "tok_acc": 0.9838,
   "entropy": 0.0375,
   "per_family": {
    "choice": 0.0569,
    "noul": 0.0309,
    "relational_compositional": 0.0002,
    "score": 0.05
   }
  },
  {
   "step": 15000,
   "loss": 0.0398,
   "tok_acc": 0.9852,
   "entropy": 0.0374,
   "per_family": {
    "choice": 0.0551,
    "noul": 0.0297,
    "relational_compositional": 0.0001,
    "score": 0.0495
   }
  },
  {
   "step": 15500,
   "loss": 0.0401,
   "tok_acc": 0.9848,
   "entropy": 0.0327,
   "per_family": {
    "choice": 0.0542,
    "noul": 0.0291,
    "relational_compositional": 0.0003,
    "score": 0.0518
   }
  },
  {
   "step": 16000,
   "loss": 0.0385,
   "tok_acc": 0.9855,
   "entropy": 0.0356,
   "per_family": {
    "choice": 0.0529,
    "noul": 0.0279,
    "relational_compositional": 0.0006,
    "score": 0.0487
   }
  },
  {
   "step": 16500,
   "loss": 0.0383,
   "tok_acc": 0.9853,
   "entropy": 0.035,
   "per_family": {
    "choice": 0.0531,
    "noul": 0.0271,
    "relational_compositional": 0.0006,
    "score": 0.0482
   }
  },
  {
   "step": 17000,
   "loss": 0.0386,
   "tok_acc": 0.9849,
   "entropy": 0.0345,
   "per_family": {
    "choice": 0.0532,
    "noul": 0.0279,
    "relational_compositional": 0.0004,
    "score": 0.0486
   }
  },
  {
   "step": 17500,
   "loss": 0.0384,
   "tok_acc": 0.9848,
   "entropy": 0.035,
   "per_family": {
    "choice": 0.0533,
    "noul": 0.0282,
    "relational_compositional": 0.0004,
    "score": 0.0477
   }
  },
  {
   "step": 18000,
   "loss": 0.0384,
   "tok_acc": 0.9848,
   "entropy": 0.034,
   "per_family": {
    "choice": 0.0532,
    "noul": 0.028,
    "relational_compositional": 0.0004,
    "score": 0.0481
   }
  },
  {
   "step": 18500,
   "loss": 0.0385,
   "tok_acc": 0.9853,
   "entropy": 0.0342,
   "per_family": {
    "choice": 0.0533,
    "noul": 0.0281,
    "relational_compositional": 0.0004,
    "score": 0.0481
   }
  },
  {
   "step": 19000,
   "loss": 0.0385,
   "tok_acc": 0.9853,
   "entropy": 0.0341,
   "per_family": {
    "choice": 0.0533,
    "noul": 0.028,
    "relational_compositional": 0.0004,
    "score": 0.0481
   }
  },
  {
   "step": 19058,
   "loss": 0.0385,
   "tok_acc": 0.9853,
   "entropy": 0.0341,
   "per_family": {
    "choice": 0.0533,
    "noul": 0.0281,
    "relational_compositional": 0.0004,
    "score": 0.048
   }
  }
 ],
 "best_checkpoint": {
  "step": 16500,
  "val_loss": 0.0383
 }
}