{ "note": "Rust-compatible hashed-logreg student distilled from V7 fastText. Metrics are proxy-only unless compared to human labels.", "args": { "data": "classified_v4_transformer_data_hardneg", "teacher": "classified_v7_fasttext_v5b_120k\\model.bin", "init_model": "classified_accuracy_v2\\text_classifier.json", "output": "classified_v7r_fasttext_student_410k", "train_sample": 0, "eval_sample": 0, "epochs": 3, "learning_rate": 0.04, "seed": 777, "teacher_batch_size": 8192, "crypto_threshold": 0.45, "tech_threshold": 0.36 }, "teacher": { "model": "classified_v7_fasttext_v5b_120k\\model.bin", "thresholds": { "crypto": 0.45, "tech": 0.36 }, "train_seconds": 88.16688129999966, "eval_seconds": 10.310907999999472 }, "student": { "model_version": "hashed-logreg-v7-fasttext-student", "train_rows": 410292, "eval_rows": 50413, "train_seconds": 13.258047600000282, "default_thresholds": { "post_crypto": 0.5, "post_tech": 0.5, "profile_crypto": 0.5, "profile_tech": 0.5 }, "tuned_thresholds": { "post_crypto": 0.58, "post_tech": 0.44, "profile_crypto": 0.34, "profile_tech": 0.38 }, "threshold_report": { "post_crypto": { "threshold": 0.58, "precision": 0.9671687073355727, "recall": 0.980232813529541, "fscore": 0.9736569402781566 }, "post_tech": { "threshold": 0.44, "precision": 0.9377788213195586, "recall": 0.9484682973165519, "fscore": 0.9430932703659975 }, "profile_crypto": { "threshold": 0.34, "precision": 0.9304776241959765, "recall": 0.711490163248221, "fscore": 0.806380833778094 }, "profile_tech": { "threshold": 0.38, "precision": 0.940460947503201, "recall": 0.8883289659342875, "fscore": 0.9136519125116617 } } }, "default_student_vs_teacher": { "overall": { "exact_match_accuracy": 0.9002836569932359, "micro_precision": 0.9620242848993562, "micro_recall": 0.8482431558525544, "micro_f1": 0.9015579654803727, "macro_precision": 0.9595827241171908, "macro_recall": 0.8617410508785691, "macro_f1": 0.9073573249366726, "crypto": { "precision": 0.9679515487981831, "recall": 0.8221519665630693, "f1": 0.8891142468055515, "support": 18662 }, "tech": { "precision": 0.9512138994361984, "recall": 0.9013301351940689, "f1": 0.9256004030677938, "support": 9172 }, "pred_counts": { "crypto": 15851, "tech": 8691, "negative": 26168 } }, "posts_only": { "exact_match_accuracy": 0.9610693606012073, "micro_precision": 0.9562995333678986, "micro_recall": 0.969512652999925, "micro_f1": 0.9628607651577299, "macro_precision": 0.9522663599218083, "macro_recall": 0.9618777142458361, "macro_f1": 0.9570222958759071, "crypto": { "precision": 0.9629789065863108, "recall": 0.9826488029870415, "f1": 0.9727144254810306, "support": 9106 }, "tech": { "precision": 0.9415538132573058, "recall": 0.9411066255046308, "f1": 0.9413301662707838, "support": 4211 }, "pred_counts": { "crypto": 9292, "tech": 4209, "negative": 11015 } }, "profiles_only": { "exact_match_accuracy": 0.8434886040979204, "micro_precision": 0.9690245448781813, "micro_recall": 0.7369980023420817, "micro_f1": 0.8372329603255341, "macro_precision": 0.9676408876174856, "macro_recall": 0.7683900413176734, "macro_f1": 0.852622602377825, "crypto": { "precision": 0.9749961884433602, "recall": 0.6692130598576811, "f1": 0.7936704933291964, "support": 9556 }, "tech": { "precision": 0.9602855867916109, "recall": 0.8675670227776658, "f1": 0.9115747114264534, "support": 4961 }, "pred_counts": { "crypto": 6559, "tech": 4482, "negative": 15153 } } }, "tuned_student_vs_teacher": { "overall": { "exact_match_accuracy": 0.9031003907722215, "micro_precision": 0.9468231231113379, "micro_recall": 0.866781633972839, "micro_f1": 0.905036106161493, "macro_precision": 0.9450696963354239, "macro_recall": 0.8792805932309817, "macro_f1": 0.910466457987787, "crypto": { "precision": 0.9509554910498307, "recall": 0.8426213696281213, "f1": 0.8935166770839252, "support": 18662 }, "tech": { "precision": 0.9391839016210173, "recall": 0.9159398168338422, "f1": 0.9274162388916487, "support": 9172 }, "pred_counts": { "crypto": 16536, "tech": 8945, "negative": 25288 } }, "posts_only": { "exact_match_accuracy": 0.9622602767853476, "micro_precision": 0.9578884934756821, "micro_recall": 0.9701884808890892, "micro_f1": 0.9639992538705465, "macro_precision": 0.9524737643275656, "macro_recall": 0.9643505554230465, "macro_f1": 0.958375105322077, "crypto": { "precision": 0.9671687073355727, "recall": 0.980232813529541, "f1": 0.9736569402781565, "support": 9106 }, "tech": { "precision": 0.9377788213195586, "recall": 0.9484682973165519, "f1": 0.9430932703659977, "support": 4211 }, "pred_counts": { "crypto": 9229, "tech": 4259, "negative": 11022 } }, "profiles_only": { "exact_match_accuracy": 0.8478244186938838, "micro_precision": 0.9343783873926457, "micro_recall": 0.7719225735344768, "micro_f1": 0.8454168238400603, "macro_precision": 0.9354692858495888, "macro_recall": 0.7999095645912542, "macro_f1": 0.8600163731448778, "crypto": { "precision": 0.9304776241959765, "recall": 0.711490163248221, "f1": 0.806380833778094, "support": 9556 }, "tech": { "precision": 0.940460947503201, "recall": 0.8883289659342875, "f1": 0.9136519125116617, "support": 4961 }, "pred_counts": { "crypto": 7307, "tech": 4686, "negative": 14266 } } }, "tuned_student_vs_weak_labels": { "overall": { "exact_match_accuracy": 0.8832840735524567, "micro_precision": 0.9655429535732507, "micro_recall": 0.8161823248407644, "micro_f1": 0.8846022471910112, "macro_precision": 0.965574214755928, "macro_recall": 0.811794173017184, "macro_f1": 0.8819491541016604, "crypto": { "precision": 0.9654692791485244, "recall": 0.8274593137763036, "f1": 0.8911526653642199, "support": 19294 }, "tech": { "precision": 0.9656791503633315, "recall": 0.7961290322580645, "f1": 0.8727456428391008, "support": 10850 }, "pred_counts": { "crypto": 16536, "tech": 8945, "negative": 25288 } }, "posts_only": { "exact_match_accuracy": 0.9659151574883988, "micro_precision": 0.9944395017793595, "micro_recall": 0.9453097469871027, "micro_f1": 0.9692524478809119, "macro_precision": 0.9942297434119423, "macro_recall": 0.936574113553416, "macro_f1": 0.9643727674837768, "crypto": { "precision": 0.994799003142269, "recall": 0.9618648507071765, "f1": 0.9780547565782465, "support": 9545 }, "tech": { "precision": 0.9936604836816154, "recall": 0.9112833763996555, "f1": 0.9506907783893069, "support": 4644 }, "pred_counts": { "crypto": 9229, "tech": 4259, "negative": 11022 } }, "profiles_only": { "exact_match_accuracy": 0.8060778144424833, "micro_precision": 0.9330442758275661, "micro_recall": 0.7013475399561266, "micro_f1": 0.8007728638900816, "macro_precision": 0.9343361720100598, "macro_recall": 0.7029121738755889, "macro_f1": 0.8022656696241247, "crypto": { "precision": 0.928424798138771, "recall": 0.6958662426915581, "f1": 0.7954971857410882, "support": 9749 }, "tech": { "precision": 0.9402475458813487, "recall": 0.7099581050596198, "f1": 0.8090341535071612, "support": 6206 }, "pred_counts": { "crypto": 7307, "tech": 4686, "negative": 14266 } } }, "teacher_vs_weak_labels": { "overall": { "exact_match_accuracy": 0.9257929502310912, "micro_precision": 0.9578932241143925, "micro_recall": 0.8844877919320594, "micro_f1": 0.919728172755183, "macro_precision": 0.9586196156540225, "macro_recall": 0.8686619894248541, "macro_f1": 0.9103972509783973, "crypto": { "precision": 0.9564891222805701, "recall": 0.9251580802321966, "f1": 0.9405627568763831, "support": 19294 }, "tech": { "precision": 0.9607501090274749, "recall": 0.8121658986175115, "f1": 0.8802317450804116, "support": 10850 }, "pred_counts": { "crypto": 18662, "tech": 9172, "negative": 22927 } }, "posts_only": { "exact_match_accuracy": 0.945423185906123, "micro_precision": 0.9804009912142374, "micro_recall": 0.9201494115159631, "micro_f1": 0.9493201483312732, "macro_precision": 0.9776264881654799, "macro_recall": 0.9097467163339348, "macro_f1": 0.9423142636561663, "crypto": { "precision": 0.9851746101471557, "recall": 0.9398638030382399, "f1": 0.9619859524958447, "support": 9545 }, "tech": { "precision": 0.9700783661838043, "recall": 0.8796296296296297, "f1": 0.9226425748164878, "support": 4644 }, "pred_counts": { "crypto": 9106, "tech": 4211, "negative": 11202 } }, "profiles_only": { "exact_match_accuracy": 0.9074514618985496, "micro_precision": 0.9372459874629745, "micro_recall": 0.8527734252585396, "micro_f1": 0.8930165397742189, "macro_precision": 0.9409932741182816, "macro_recall": 0.8362211604736839, "macro_f1": 0.8832334569237945, "crypto": { "precision": 0.9291544579321892, "recall": 0.9107600779567135, "f1": 0.9198653198653198, "support": 9749 }, "tech": { "precision": 0.9528320903043741, "recall": 0.7616822429906542, "f1": 0.8466015939822692, "support": 6206 }, "pred_counts": { "crypto": 9556, "tech": 4961, "negative": 11725 } } } }