appvoid commited on
Commit
5168781
·
verified ·
1 Parent(s): ab2a5b3

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790782192342215557-281f6532/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 365000, "seed_holdout": {"answer_byte_loss": 1.0691073274070566, "teacher_forced_byte_accuracy": 0.7454545454545455, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5350076463487414, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 370000, "seed_holdout": {"answer_byte_loss": 0.688515025026658, "teacher_forced_byte_accuracy": 0.7843137254901961, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.751869879828559, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
4
  {"step": 375000, "seed_holdout": {"answer_byte_loss": 0.46299286156892777, "teacher_forced_byte_accuracy": 0.87, "generation_exact_match": 0.16666666666666666, "generation_truncated": 5, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4262516021728517, "teacher_forced_byte_accuracy": 0.3, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
 
 
2
  {"step": 365000, "seed_holdout": {"answer_byte_loss": 1.0691073274070566, "teacher_forced_byte_accuracy": 0.7454545454545455, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5350076463487414, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 370000, "seed_holdout": {"answer_byte_loss": 0.688515025026658, "teacher_forced_byte_accuracy": 0.7843137254901961, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.751869879828559, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
4
  {"step": 375000, "seed_holdout": {"answer_byte_loss": 0.46299286156892777, "teacher_forced_byte_accuracy": 0.87, "generation_exact_match": 0.16666666666666666, "generation_truncated": 5, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4262516021728517, "teacher_forced_byte_accuracy": 0.3, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
+ {"step": 380000, "seed_holdout": {"answer_byte_loss": 1.0303300115568885, "teacher_forced_byte_accuracy": 0.6551724137931034, "generation_exact_match": 0.25, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4179815504286024, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 365000, "seed_holdout": {"answer_byte_loss": 1.0691073274070566, "teacher_forced_byte_accuracy": 0.7454545454545455, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5350076463487414, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 65}, {"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": 192, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 8}, {"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": 7, "target_bytes": 8}, {"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": 4, "target_bytes": 4}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "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}]}
3
  {"step": 370000, "seed_holdout": {"answer_byte_loss": 0.688515025026658, "teacher_forced_byte_accuracy": 0.7843137254901961, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.751869879828559, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 18, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 49, "target_bytes": 49}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "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": 8, "target_bytes": 16}]}
4
  {"step": 375000, "seed_holdout": {"answer_byte_loss": 0.46299286156892777, "teacher_forced_byte_accuracy": 0.87, "generation_exact_match": 0.16666666666666666, "generation_truncated": 5, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4262516021728517, "teacher_forced_byte_accuracy": 0.3, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 36}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 51, "target_bytes": 56}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 9}, {"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": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "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": 15, "target_bytes": 16}]}
 
 
2
  {"step": 365000, "seed_holdout": {"answer_byte_loss": 1.0691073274070566, "teacher_forced_byte_accuracy": 0.7454545454545455, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5350076463487414, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 65}, {"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": 192, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 8}, {"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": 7, "target_bytes": 8}, {"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": 4, "target_bytes": 4}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "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}]}
3
  {"step": 370000, "seed_holdout": {"answer_byte_loss": 0.688515025026658, "teacher_forced_byte_accuracy": 0.7843137254901961, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.751869879828559, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 18, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 49, "target_bytes": 49}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "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": 8, "target_bytes": 16}]}
4
  {"step": 375000, "seed_holdout": {"answer_byte_loss": 0.46299286156892777, "teacher_forced_byte_accuracy": 0.87, "generation_exact_match": 0.16666666666666666, "generation_truncated": 5, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4262516021728517, "teacher_forced_byte_accuracy": 0.3, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 36}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 51, "target_bytes": 56}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 9}, {"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": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "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": 15, "target_bytes": 16}]}
5
+ {"step": 380000, "seed_holdout": {"answer_byte_loss": 1.0303300115568885, "teacher_forced_byte_accuracy": 0.6551724137931034, "generation_exact_match": 0.25, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.4179815504286024, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": true, "generated_bytes": 2, "target_bytes": 2}, {"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "generated_bytes": 12, "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": 3, "target_bytes": 4}, {"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": false, "generated_bytes": 192, "target_bytes": 4}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 10, "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.1790782192.062ccfe6-664f-43fe-9e0e-62f43f0c4870-64tpq.429.0.1790782192342215557-281f6532 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a006d423a4c7fa2d619a0d2ca1ec4868afc49f4e8c6bab38314f1607b49335e6
3
- size 532797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1574e29d847fd36517b981709061584b340ca148d65d46b98c49745ef977d7d5
3
+ size 533580