| { |
| "canonical_p_probe": { |
| "canonical_decode_accuracy": { |
| "entity": 1.0, |
| "metadata": 1.0, |
| "relation": 1.0, |
| "value": 1.0 |
| }, |
| "hard_negative_accuracy": { |
| "historical": 1.0, |
| "wrong_entity": 0.97265625, |
| "wrong_value": 1.0 |
| }, |
| "held_out_combinations": 256, |
| "p_only_state_recovery": 0.97265625, |
| "permutation_stability": 1.0, |
| "permutations_per_combination": 8, |
| "slot_width": 512, |
| "total_held_out_combinations": 519, |
| "train_combinations": 2073, |
| "training_loss_first": 7.440117835998535, |
| "training_loss_last": 0.04114125296473503 |
| }, |
| "completion_gate": "passed", |
| "diagnostic_variant": "final_layer", |
| "experiment": { |
| "base_frozen": true, |
| "causal_steps": 256, |
| "lora_used": false, |
| "phase_c_started": false, |
| "query_steps": 400, |
| "router_steps": 400, |
| "seed": 307, |
| "source_tokens_in_recent_kv": 0, |
| "value_steps": 400 |
| }, |
| "immutable_rejected_translator_baseline": { |
| "final_layer": { |
| "exact_generated_token_accuracy": 0.45000001788139343, |
| "global_20_fact_retrieval": 0.6500000357627869, |
| "p_to_model_value_accuracy": 1.0, |
| "rp_loss": 4.656857490539551, |
| "unseen_name_accuracy": 0.25, |
| "wrong_entity_gate": 0.5172024965286255 |
| }, |
| "upper_2_layers": { |
| "exact_generated_token_accuracy": 0.550000011920929, |
| "global_20_fact_retrieval": 0.6500000357627869, |
| "p_to_model_value_accuracy": 1.0, |
| "rp_loss": 6.086124897003174, |
| "unseen_name_accuracy": 0.0, |
| "wrong_entity_gate": 0.6912492662668228 |
| }, |
| "upper_4_layers": { |
| "exact_generated_token_accuracy": 0.6500000357627869, |
| "global_20_fact_retrieval": 0.699999988079071, |
| "p_to_model_value_accuracy": 1.0, |
| "rp_loss": 5.704916477203369, |
| "unseen_name_accuracy": 0.25, |
| "wrong_entity_gate": 0.7020304128527641 |
| } |
| }, |
| "layer_sweep": { |
| "final_layer": { |
| "ablations": { |
| "full_system_with_preservation": { |
| "full_token_accuracy": 1.0, |
| "gate_activation": 0.9820089340209961, |
| "state_candidate_accuracy": 1.0 |
| }, |
| "router_only": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.10144930460010074, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "router_plus_translator_plus_gate": { |
| "historical_state_kl": 9.595059236744419e-05, |
| "rp_kl": -3.993045538663864e-08, |
| "rp_loss": 5.583366870880127, |
| "state_candidate_accuracy": 1.0, |
| "state_loss": 1.8655489839147776e-05, |
| "wrong_state_kl": 9.595059236744419e-05 |
| }, |
| "router_plus_translator_without_gate": { |
| "state_candidate_accuracy": 1.0 |
| }, |
| "translator_only_oracle_routing": { |
| "state_candidate_accuracy": 1.0 |
| } |
| }, |
| "attachment_count": 1, |
| "attachment_layers": [ |
| 23 |
| ], |
| "base_parameters_with_grad": 0, |
| "causal_training_loss_first_last": [ |
| 9.884638786315918, |
| 5.081248218630208e-06 |
| ], |
| "counterfactual": { |
| "disabled": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p1_silver_alice": { |
| "alice_logit": 40.09375, |
| "alice_probability": 1.0, |
| "bob_logit": 14.3125, |
| "bob_probability": 6.3583643558629e-12, |
| "gate": 0.9964228272438049, |
| "generated": " Alice" |
| }, |
| "p2_silver_bob": { |
| "alice_logit": 13.0234375, |
| "alice_probability": 4.473376963992637e-12, |
| "bob_logit": 39.15625, |
| "bob_probability": 0.9999349117279053, |
| "gate": 0.9842994213104248, |
| "generated": " Bob" |
| }, |
| "p3_gold_alice": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_historical": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_invalidated": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| } |
| }, |
| "extra_prompt_tokens": 0, |
| "invalidated_logit_difference": 0.0, |
| "mutation_chain": { |
| "invalidated_max_logit_difference": 0.0, |
| "latest_state_accuracy": 1.0, |
| "source_tokens_in_recent_kv": 0 |
| }, |
| "natural_rp": { |
| "base_loss": 5.583366870880127, |
| "conditions": { |
| "base": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "invalidated": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "irrelevant": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "wrong_entity": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| } |
| }, |
| "relevant_state_generation_sample": " Alice" |
| }, |
| "package_parameters": 2707464, |
| "package_path": "artifacts/pythia-1.4b-split-final_layer.translate", |
| "package_roundtrip_max_difference": 0.0, |
| "query_projector": { |
| "byte_surface_anchor_approach": { |
| "entity_accuracy": 1.0, |
| "entity_cosine": 1.0, |
| "metadata_accuracy": 1.0, |
| "oracle_slot_assignments": 0, |
| "relation_accuracy": 1.0, |
| "tokenizer_independent": true |
| }, |
| "frozen_lexical_anchor_approach": { |
| "entity_accuracy": 0.78125, |
| "entity_cosine": 0.7632350921630859 |
| }, |
| "heldout_names": 64, |
| "hidden_to_byte_reconstruction_ablation": { |
| "entity_accuracy": 0.125, |
| "entity_cosine": 0.2643434405326843, |
| "metadata_accuracy": 1.0, |
| "relation_accuracy": 1.0 |
| }, |
| "loss_first_last": [ |
| 6.364231586456299, |
| 0.23614102602005005 |
| ], |
| "training_names": 256 |
| }, |
| "router": { |
| "acceptance_threshold": 5.495710372924805, |
| "calibration_balanced_accuracy": 1.0, |
| "hard_negative_metrics": { |
| "historical_false_positive_rate": 0.0, |
| "invalidated_false_positive_rate": 0.0, |
| "irrelevant_false_positive_rate": 0.0, |
| "top1_accuracy": 1.0, |
| "wrong_entity_false_positive_rate": 0.0, |
| "wrong_relation_false_positive_rate": 0.0 |
| }, |
| "loss_first_last": [ |
| 7.388868808746338, |
| 1.7992397546768188 |
| ], |
| "model_hidden_dimensions": 0, |
| "scaling": { |
| "128": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.10144930460010074, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "20": { |
| "active_vram_overhead_bytes": 10861996, |
| "hidden_only_top1_accuracy": 0.20000000298023224, |
| "latency_seconds": 0.08669143320003059, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "256": { |
| "active_vram_overhead_bytes": 11241012, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.11810561999955098, |
| "mrr": 0.9505556225776672, |
| "oracle_query_mrr": 0.9505556225776672, |
| "oracle_query_top1_accuracy": 0.949999988079071, |
| "oracle_query_top4_recall": 0.949999988079071, |
| "state_generation_accuracy": 0.949999988079071, |
| "top1_accuracy": 0.949999988079071, |
| "top2_recall": 0.949999988079071, |
| "top4_recall": 0.949999988079071 |
| }, |
| "4": { |
| "active_vram_overhead_bytes": 10836300, |
| "hidden_only_top1_accuracy": 0.75, |
| "latency_seconds": 0.02663025279980502, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "512": { |
| "active_vram_overhead_bytes": 11652148, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.16455349219977505, |
| "mrr": 0.8524776697158813, |
| "oracle_query_mrr": 0.8524776697158813, |
| "oracle_query_top1_accuracy": 0.8500000238418579, |
| "oracle_query_top4_recall": 0.8500000238418579, |
| "state_generation_accuracy": 0.8500000238418579, |
| "top1_accuracy": 0.8500000238418579, |
| "top2_recall": 0.8500000238418579, |
| "top4_recall": 0.8500000238418579 |
| }, |
| "64": { |
| "active_vram_overhead_bytes": 10932660, |
| "hidden_only_top1_accuracy": 0.05000000074505806, |
| "latency_seconds": 0.09232893199950923, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| } |
| } |
| }, |
| "router_parameters": 5, |
| "router_path": "artifacts/canonical-final_layer.router", |
| "router_roundtrip_max_difference": 0.0, |
| "source_tokens_in_recent_kv": 0, |
| "value_translator": { |
| "loss_first_last": [ |
| 4.713489055633545, |
| 0.00027370601310394704 |
| ], |
| "oracle_selected_metrics": { |
| "accuracy": 1.0, |
| "cosine": 0.9998512268066406 |
| } |
| } |
| }, |
| "upper_2_layers": { |
| "ablations": { |
| "full_system_with_preservation": { |
| "full_token_accuracy": 1.0, |
| "gate_activation": 0.8225321769714355, |
| "state_candidate_accuracy": 1.0 |
| }, |
| "router_only": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.10514904640003805, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "router_plus_translator_plus_gate": { |
| "historical_state_kl": 9.595059236744419e-05, |
| "rp_kl": -3.993045538663864e-08, |
| "rp_loss": 5.583366870880127, |
| "state_candidate_accuracy": 1.0, |
| "state_loss": 5.1855395213351585e-06, |
| "wrong_state_kl": 9.595059236744419e-05 |
| }, |
| "router_plus_translator_without_gate": { |
| "state_candidate_accuracy": 1.0 |
| }, |
| "translator_only_oracle_routing": { |
| "state_candidate_accuracy": 1.0 |
| } |
| }, |
| "attachment_count": 2, |
| "attachment_layers": [ |
| 22, |
| 23 |
| ], |
| "base_parameters_with_grad": 0, |
| "causal_training_loss_first_last": [ |
| 9.555724143981934, |
| 1.2963974995727767e-06 |
| ], |
| "counterfactual": { |
| "disabled": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p1_silver_alice": { |
| "alice_logit": 58.59375, |
| "alice_probability": 1.0, |
| "bob_logit": 18.5, |
| "bob_probability": 3.868170754671019e-18, |
| "gate": 0.941794216632843, |
| "generated": " Alice" |
| }, |
| "p2_silver_bob": { |
| "alice_logit": 16.078125, |
| "alice_probability": 6.54239844304198e-17, |
| "bob_logit": 53.34375, |
| "bob_probability": 0.9999822378158569, |
| "gate": 0.8498331308364868, |
| "generated": " Bob" |
| }, |
| "p3_gold_alice": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_historical": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_invalidated": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| } |
| }, |
| "extra_prompt_tokens": 0, |
| "invalidated_logit_difference": 0.0, |
| "mutation_chain": { |
| "invalidated_max_logit_difference": 0.0, |
| "latest_state_accuracy": 1.0, |
| "source_tokens_in_recent_kv": 0 |
| }, |
| "natural_rp": { |
| "base_loss": 5.583366870880127, |
| "conditions": { |
| "base": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "invalidated": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "irrelevant": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "wrong_entity": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| } |
| }, |
| "relevant_state_generation_sample": " Alice" |
| }, |
| "package_parameters": 2707464, |
| "package_path": "artifacts/pythia-1.4b-split-upper_2_layers.translate", |
| "package_roundtrip_max_difference": 0.0, |
| "query_projector": { |
| "byte_surface_anchor_approach": { |
| "entity_accuracy": 1.0, |
| "entity_cosine": 1.0, |
| "metadata_accuracy": 1.0, |
| "oracle_slot_assignments": 0, |
| "relation_accuracy": 1.0, |
| "tokenizer_independent": true |
| }, |
| "frozen_lexical_anchor_approach": { |
| "entity_accuracy": 0.78125, |
| "entity_cosine": 0.7632350921630859 |
| }, |
| "heldout_names": 64, |
| "hidden_to_byte_reconstruction_ablation": { |
| "entity_accuracy": 0.046875, |
| "entity_cosine": 0.281654953956604, |
| "metadata_accuracy": 1.0, |
| "relation_accuracy": 1.0 |
| }, |
| "loss_first_last": [ |
| 6.3322367668151855, |
| 0.24513374269008636 |
| ], |
| "training_names": 256 |
| }, |
| "router": { |
| "acceptance_threshold": 5.495710372924805, |
| "calibration_balanced_accuracy": 1.0, |
| "hard_negative_metrics": { |
| "historical_false_positive_rate": 0.0, |
| "invalidated_false_positive_rate": 0.0, |
| "irrelevant_false_positive_rate": 0.0, |
| "top1_accuracy": 1.0, |
| "wrong_entity_false_positive_rate": 0.0, |
| "wrong_relation_false_positive_rate": 0.0 |
| }, |
| "loss_first_last": [ |
| 7.388868808746338, |
| 1.7992397546768188 |
| ], |
| "model_hidden_dimensions": 0, |
| "scaling": { |
| "128": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.10514904640003805, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "20": { |
| "active_vram_overhead_bytes": 10861996, |
| "hidden_only_top1_accuracy": 0.10000000149011612, |
| "latency_seconds": 0.08956059680058388, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "256": { |
| "active_vram_overhead_bytes": 11241012, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.12291700120040332, |
| "mrr": 0.9505556225776672, |
| "oracle_query_mrr": 0.9505556225776672, |
| "oracle_query_top1_accuracy": 0.949999988079071, |
| "oracle_query_top4_recall": 0.949999988079071, |
| "state_generation_accuracy": 0.949999988079071, |
| "top1_accuracy": 0.949999988079071, |
| "top2_recall": 0.949999988079071, |
| "top4_recall": 0.949999988079071 |
| }, |
| "4": { |
| "active_vram_overhead_bytes": 10836300, |
| "hidden_only_top1_accuracy": 0.5, |
| "latency_seconds": 0.028453471799730325, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "512": { |
| "active_vram_overhead_bytes": 11652148, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.17295584960011184, |
| "mrr": 0.8524776697158813, |
| "oracle_query_mrr": 0.8524776697158813, |
| "oracle_query_top1_accuracy": 0.8500000238418579, |
| "oracle_query_top4_recall": 0.8500000238418579, |
| "state_generation_accuracy": 0.8500000238418579, |
| "top1_accuracy": 0.8500000238418579, |
| "top2_recall": 0.8500000238418579, |
| "top4_recall": 0.8500000238418579 |
| }, |
| "64": { |
| "active_vram_overhead_bytes": 10932660, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.09586576699948637, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| } |
| } |
| }, |
| "router_parameters": 5, |
| "router_path": "artifacts/canonical-upper_2_layers.router", |
| "router_roundtrip_max_difference": 0.0, |
| "source_tokens_in_recent_kv": 0, |
| "value_translator": { |
| "loss_first_last": [ |
| 4.713489055633545, |
| 0.00027370601310394704 |
| ], |
| "oracle_selected_metrics": { |
| "accuracy": 1.0, |
| "cosine": 0.9998512268066406 |
| } |
| } |
| }, |
| "upper_4_layers": { |
| "ablations": { |
| "full_system_with_preservation": { |
| "full_token_accuracy": 1.0, |
| "gate_activation": 0.6373323798179626, |
| "state_candidate_accuracy": 1.0 |
| }, |
| "router_only": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.11078032340010395, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "router_plus_translator_plus_gate": { |
| "historical_state_kl": 9.595059236744419e-05, |
| "rp_kl": -3.993045538663864e-08, |
| "rp_loss": 5.583366870880127, |
| "state_candidate_accuracy": 1.0, |
| "state_loss": 1.4752099559700582e-06, |
| "wrong_state_kl": 9.595059236744419e-05 |
| }, |
| "router_plus_translator_without_gate": { |
| "state_candidate_accuracy": 1.0 |
| }, |
| "translator_only_oracle_routing": { |
| "state_candidate_accuracy": 1.0 |
| } |
| }, |
| "attachment_count": 4, |
| "attachment_layers": [ |
| 20, |
| 21, |
| 22, |
| 23 |
| ], |
| "base_parameters_with_grad": 0, |
| "causal_training_loss_first_last": [ |
| 8.895807266235352, |
| 6.407490786841663e-07 |
| ], |
| "counterfactual": { |
| "disabled": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p1_silver_alice": { |
| "alice_logit": 72.5625, |
| "alice_probability": 1.0, |
| "bob_logit": 20.375, |
| "bob_probability": 2.1639972398594e-23, |
| "gate": 0.8317975997924805, |
| "generated": " Alice" |
| }, |
| "p2_silver_bob": { |
| "alice_logit": 17.796875, |
| "alice_probability": 7.510040636028562e-22, |
| "bob_logit": 66.4375, |
| "bob_probability": 0.9999938011169434, |
| "gate": 0.6602288484573364, |
| "generated": " Bob" |
| }, |
| "p3_gold_alice": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_historical": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| }, |
| "p4_silver_invalidated": { |
| "alice_logit": 5.515625, |
| "alice_probability": 3.538730743457563e-05, |
| "bob_logit": 6.2734375, |
| "bob_probability": 7.55025030230172e-05, |
| "gate": 0.0, |
| "generated": " a" |
| } |
| }, |
| "extra_prompt_tokens": 0, |
| "invalidated_logit_difference": 0.0, |
| "mutation_chain": { |
| "invalidated_max_logit_difference": 0.0, |
| "latest_state_accuracy": 1.0, |
| "source_tokens_in_recent_kv": 0 |
| }, |
| "natural_rp": { |
| "base_loss": 5.583366870880127, |
| "conditions": { |
| "base": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "invalidated": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "irrelevant": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| }, |
| "wrong_entity": { |
| "kl": -3.993045538663864e-08, |
| "loss": 5.583366870880127, |
| "samples": [ |
| "\n\n\"I'm not", |
| "\n\n\"I'm going" |
| ] |
| } |
| }, |
| "relevant_state_generation_sample": " Alice" |
| }, |
| "package_parameters": 2707464, |
| "package_path": "artifacts/pythia-1.4b-split-upper_4_layers.translate", |
| "package_roundtrip_max_difference": 0.0, |
| "query_projector": { |
| "byte_surface_anchor_approach": { |
| "entity_accuracy": 1.0, |
| "entity_cosine": 1.0, |
| "metadata_accuracy": 1.0, |
| "oracle_slot_assignments": 0, |
| "relation_accuracy": 1.0, |
| "tokenizer_independent": true |
| }, |
| "frozen_lexical_anchor_approach": { |
| "entity_accuracy": 0.78125, |
| "entity_cosine": 0.7632350921630859 |
| }, |
| "heldout_names": 64, |
| "hidden_to_byte_reconstruction_ablation": { |
| "entity_accuracy": 0.078125, |
| "entity_cosine": 0.28708386421203613, |
| "metadata_accuracy": 1.0, |
| "relation_accuracy": 1.0 |
| }, |
| "loss_first_last": [ |
| 6.471477031707764, |
| 0.2573241889476776 |
| ], |
| "training_names": 256 |
| }, |
| "router": { |
| "acceptance_threshold": 5.495710372924805, |
| "calibration_balanced_accuracy": 1.0, |
| "hard_negative_metrics": { |
| "historical_false_positive_rate": 0.0, |
| "invalidated_false_positive_rate": 0.0, |
| "irrelevant_false_positive_rate": 0.0, |
| "top1_accuracy": 1.0, |
| "wrong_entity_false_positive_rate": 0.0, |
| "wrong_relation_false_positive_rate": 0.0 |
| }, |
| "loss_first_last": [ |
| 7.388868808746338, |
| 1.7992397546768188 |
| ], |
| "model_hidden_dimensions": 0, |
| "scaling": { |
| "128": { |
| "active_vram_overhead_bytes": 11035444, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.11078032340010395, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "20": { |
| "active_vram_overhead_bytes": 10861996, |
| "hidden_only_top1_accuracy": 0.10000000149011612, |
| "latency_seconds": 0.09917421240024851, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "256": { |
| "active_vram_overhead_bytes": 11241012, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.1296995702003187, |
| "mrr": 0.9505556225776672, |
| "oracle_query_mrr": 0.9505556225776672, |
| "oracle_query_top1_accuracy": 0.949999988079071, |
| "oracle_query_top4_recall": 0.949999988079071, |
| "state_generation_accuracy": 0.949999988079071, |
| "top1_accuracy": 0.949999988079071, |
| "top2_recall": 0.949999988079071, |
| "top4_recall": 0.949999988079071 |
| }, |
| "4": { |
| "active_vram_overhead_bytes": 10836300, |
| "hidden_only_top1_accuracy": 0.25, |
| "latency_seconds": 0.031837903400446524, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| }, |
| "512": { |
| "active_vram_overhead_bytes": 11652148, |
| "hidden_only_top1_accuracy": 0.0, |
| "latency_seconds": 0.18178108020001674, |
| "mrr": 0.8524776697158813, |
| "oracle_query_mrr": 0.8524776697158813, |
| "oracle_query_top1_accuracy": 0.8500000238418579, |
| "oracle_query_top4_recall": 0.8500000238418579, |
| "state_generation_accuracy": 0.8500000238418579, |
| "top1_accuracy": 0.8500000238418579, |
| "top2_recall": 0.8500000238418579, |
| "top4_recall": 0.8500000238418579 |
| }, |
| "64": { |
| "active_vram_overhead_bytes": 10932660, |
| "hidden_only_top1_accuracy": 0.05000000074505806, |
| "latency_seconds": 0.10435858960045152, |
| "mrr": 1.0, |
| "oracle_query_mrr": 1.0, |
| "oracle_query_top1_accuracy": 1.0, |
| "oracle_query_top4_recall": 1.0, |
| "state_generation_accuracy": 1.0, |
| "top1_accuracy": 1.0, |
| "top2_recall": 1.0, |
| "top4_recall": 1.0 |
| } |
| } |
| }, |
| "router_parameters": 5, |
| "router_path": "artifacts/canonical-upper_4_layers.router", |
| "router_roundtrip_max_difference": 0.0, |
| "source_tokens_in_recent_kv": 0, |
| "value_translator": { |
| "loss_first_last": [ |
| 4.713489055633545, |
| 0.00027370601310394704 |
| ], |
| "oracle_selected_metrics": { |
| "accuracy": 1.0, |
| "cosine": 0.9998512268066406 |
| } |
| } |
| } |
| }, |
| "selected_variant": "final_layer" |
| } |
|
|