appvoid commited on
Commit
6ad38db
·
verified ·
1 Parent(s): d5c1e5d

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790868774355361490-de221e1d/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
5
+ {"step": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"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": false, "generated_bytes": 26, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "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": 192, "target_bytes": 45}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": 5, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 7}, {"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": true, "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": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
4
  {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"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": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"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": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"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": false, "generated_bytes": 26, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "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": 192, "target_bytes": 45}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": 5, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 7}, {"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": true, "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": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
4
  {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"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": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"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": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
+ {"step": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 51, "target_bytes": 51}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 25}, {"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": 6}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "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": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 23, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "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.1790868774.f92f6aaf-743a-4c24-a54a-850bd75954cb-8js8b.612.0.1790868774355361490-de221e1d CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87c48e401f9b5c9b963eeb3f097aace0f60f41e12aeffecf6bca2995407452ee
3
- size 528561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f38e82c601b78d0a9792ab7a163d3a7d884063593066d6dabaeff7e25957e4a
3
+ size 529344