appvoid commited on
Commit
450bc8e
·
verified ·
1 Parent(s): d8b42b3

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791083219122319327-61ae60ac/eval.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 650000, "seed_holdout": {"answer_byte_loss": 0.5136761161964387, "teacher_forced_byte_accuracy": 0.8666666666666667, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6567129558987088, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -1,9 +1 @@
1
- {"step": 605000, "seed_holdout": {"answer_byte_loss": 0.09305128062313253, "teacher_forced_byte_accuracy": 0.9696969696969697, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.073719745212131, "teacher_forced_byte_accuracy": 0.3, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_anomaly_cause", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 20, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_binary_search", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_string_match", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_bfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_topo_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_union_find", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 8}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
- {"step": 610000, "seed_holdout": {"answer_byte_loss": 0.18407397395052963, "teacher_forced_byte_accuracy": 0.9035087719298246, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7967514673868814, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_interval_overlap", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_novel_primitive", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modifier_comp", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_cross_domain", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_context_operator", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_representation_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_compositional_holdout", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_recursive_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_instruction_comp", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_rule_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
3
- {"step": 615000, "seed_holdout": {"answer_byte_loss": 0.3875823506012542, "teacher_forced_byte_accuracy": 0.8333333333333334, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.664536836412218, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_hidden_rule", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_unknown_goal", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_door_key", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_irreversible_action", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_explore_infer_exploit", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_rule_switch", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_goal_switch", "surface": "instruction_json", "exact": true, "generated_bytes": 21, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 32, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 16}]}
4
- {"step": 620000, "seed_holdout": {"answer_byte_loss": 0.15380744816682315, "teacher_forced_byte_accuracy": 0.9352941176470588, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.9755938212076822, "teacher_forced_byte_accuracy": 0.3333333333333333, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": false, "generated_bytes": 44, "target_bytes": 44}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_scope_shadowing", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relational_join", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_nested_substitution", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"group": "seed_holdout", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
- {"step": 625000, "seed_holdout": {"answer_byte_loss": 0.010244488215010445, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6547412448459202, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_instruction_override", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_output_schema", "surface": "instruction_json", "exact": true, "generated_bytes": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_bounded_arithmetic", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_text_span_extract", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_counterfactual_state", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": true, "generated_bytes": 15, "target_bytes": 15}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
6
- {"step": 630000, "seed_holdout": {"answer_byte_loss": 0.32024522115073234, "teacher_forced_byte_accuracy": 0.9186991869918699, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5781940460205077, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_missing_information", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_successor_chain", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 49, "target_bytes": 52}, {"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
7
- {"step": 635000, "seed_holdout": {"answer_byte_loss": 1.8977707848426397, "teacher_forced_byte_accuracy": 0.3559322033898305, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6516090816921658, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 28, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
8
- {"step": 640000, "seed_holdout": {"answer_byte_loss": 0.5603683034578959, "teacher_forced_byte_accuracy": 0.8208333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5666661156548394, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_nested_binding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 15, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 49, "target_bytes": 49}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 53, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
9
- {"step": 645000, "seed_holdout": {"answer_byte_loss": 0.6703144366382271, "teacher_forced_byte_accuracy": 0.7204301075268817, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8775389353434244, "teacher_forced_byte_accuracy": 0.37777777777777777, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_relational_analogy", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_first_principles_chain", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
1
+ {"step": 650000, "seed_holdout": {"answer_byte_loss": 0.5136761161964387, "teacher_forced_byte_accuracy": 0.8666666666666667, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6567129558987088, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
 
 
 
 
 
 
runs/void-byte-v1/events.out.tfevents.1791083219.1a73f132-ede3-4b51-9e4f-0cafff989449-8p4r7.435.0.1791083219122319327-61ae60ac CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18adc23abf65a81e94fcfad8333927fe5abfa4cff3b940b683d6b86fd448c3c6
3
- size 106065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a25436dafc382da8c5a9d880131a7e2cea67fa868b851887ac9de03c2bc4b9
3
+ size 106848