{ "schema": 1, "method": "cloze_pmi_to_first_token_kl", "model": "mii-llm/zagreus-0.4B-ita", "requested_revision": "f463a5beabf054809ee3cc702c711215a5fde690", "resolved_revision": "f463a5beabf054809ee3cc702c711215a5fde690", "data": "kl", "data_sha256": { "train": "ad9f071607f8f17e0bd624dfa1fdd30158f6a1eae8f243aeeed47f5212094b21", "heldout": "ca81ef92405c7ab895f00cac27a4a5d69b2c550db782f90780882a0f7a84cd99" }, "hyperparameters": { "tau": 1.0, "lambda_gold_ce": 1.0, "mu_letter_mass": 0.1, "learning_rate": 0.0001, "epochs": 5, "batch_size": 16, "zero_shot": true, "max_question_tokens": 256, "seed": 42, "weight_decay": 0.01 }, "counts_after_length_filter": { "train_records": 9294, "heldout_records": 924, "optimizer_steps": 2905 }, "heldout_history": [ { "epoch": 0, "p_eq_q_cloze": 0.2564935064935065, "letter_accuracy_vs_gold": 0.2510822510822511, "letter_mass": 0.12870299325876938 }, { "epoch": 1, "p_eq_q_cloze": 0.2694805194805195, "letter_accuracy_vs_gold": 0.26731601731601734, "letter_mass": 0.9791770796755176 }, { "epoch": 2, "p_eq_q_cloze": 0.2911255411255411, "letter_accuracy_vs_gold": 0.27164502164502163, "letter_mass": 0.9890340902072526 }, { "epoch": 3, "p_eq_q_cloze": 0.43398268398268397, "letter_accuracy_vs_gold": 0.5227272727272727, "letter_mass": 0.9932343846275693 }, { "epoch": 4, "p_eq_q_cloze": 0.525974025974026, "letter_accuracy_vs_gold": 0.6071428571428571, "letter_mass": 0.9928273122548025 }, { "epoch": 5, "p_eq_q_cloze": 0.5292207792207793, "letter_accuracy_vs_gold": 0.6190476190476191, "letter_mass": 0.9943214587835006 } ], "wall_seconds": 393.98932337760925, "environment": { "python": "3.12.3", "torch": "2.13.0+cu129", "transformers": "5.13.0", "device": "cuda" } }