spb/wpai0002_uqo

1{2  "name": "HTR-Tiny-pilot-rc0",3  "text_meta_prefix": false,4  "style_classes": null,5  "run": "pilot_m1_tiny_denoiseinit",6  "version": "0.1.0",7  "exported_at": "2026-11-09T19:25:42Z",8  "arch": "m1",9  "n_params": 27394945,10  "source_checkpoint": "artifacts/runs/pilot_m1_tiny_denoiseinit/best",11  "checkpoint_meta": {12    "created_at": "2026-11-09T19:08:19Z",13    "git": {14      "commit": null,15      "branch": null,16      "dirty": false17    },18    "libraries": {19      "python": "3.14.5",20      "torch": "2.15.0",21      "numpy": "2.5.4",22      "anthropic": null,23      "transformers": null,24      "sentencepiece": "0.2.3",25      "lxml": "6.1.3",26      "pyarrow": "26.0.1",27      "sacrebleu": "2.6.0",28      "datasketch": "2.0.0",29      "rapidfuzz": "3.14.6"30    },31    "hardware": {32      "platform": "macOS-26.6-arm64-arm-64bit-Mach-O",33      "machine": "arm64",34      "cpu_count": 28,35      "chip": "Apple M3 Ultra",36      "ram_gb": 96.0,37      "torch_mps": true,38      "torch_cuda": false39    },40    "step": 250,41    "tokens_seen": 2152249,42    "accel_seconds": 45.8,43    "train_config": {44      "lr": 0.0002,45      "weight_decay": 0.01,46      "betas": [47        0.9,48        0.9849      ],50      "warmup_steps": 100,51      "max_steps": 4000,52      "accum": 1,53      "clip": 1.0,54      "eval_every": 250,55      "log_every": 25,56      "patience": 6,57      "amp": "auto",58      "seed": 1,59      "max_tokens": 6144,60      "max_batch": 48,61      "loss": {62        "ce": 1.0,63        "fact": 0.0,64        "style": 0.0,65        "adv": 0.0,66        "con": 0.0,67        "sem": 0.0,68        "orth": 0.0,69        "label_smoothing": 0.1,70        "temperature": 0.0771      },72      "device": "auto",73      "keep_last": 274    },75    "eval": {76      "val_ce": 1.6078313916623073,77      "val_ppl": 4.99197384495966,78      "val_tokens": 11989179    }80  },81  "metrics": {82    "chrf": {83      "mean": 63.6045,84      "ci": [85        62.1976,86        64.86187      ]88    },89    "edit_sim": {90      "mean": 0.5777,91      "ci": [92        0.5582,93        0.595594      ]95    },96    "rougeL": {97      "mean": 0.5996,98      "ci": [99        0.5795,100        0.6169101      ]102    },103    "exact_match": {104      "mean": 0.0,105      "ci": [106        0.0,107        0.0108      ]109    },110    "number_recall": {111      "mean": 0.9308,112      "ci": [113        0.912,114        0.9503115      ]116    },117    "placeholders_exact": {118      "mean": 0.8845,119      "ci": [120        0.8303,121        0.9381122      ]123    },124    "_baseline_B0_identity": {125      "chrf": 71.2394,126      "edit_sim": 0.6665,127      "rougeL": 0.6898,128      "exact_match": 0.0,129      "number_recall": 1.0,130      "placeholders_exact": 1.0131    }132  },133  "training_data": "Pilot: 5 383 validated Claude Opus 5.5 rewrite pairs of 974 PMC Open Access passages (CC0/CC BY/CC BY-NC/CC BY-NC-SA/public domain), after denoising pretraining on 17 k train-split PMC passages; research candidate, NOT the release model"134}135