appvoid commited on
Commit
7c4beda
·
verified ·
1 Parent(s): 36f5ce5

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790563279934888633-82973089/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 160000, "seed_holdout": {"answer_byte_loss": 0.2297240496374482, "teacher_forced_byte_accuracy": 0.9090909090909091, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9233456081814237, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
2
  {"step": 165000, "seed_holdout": {"answer_byte_loss": 0.404964976217393, "teacher_forced_byte_accuracy": 0.8461538461538461, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.278676266140408, "teacher_forced_byte_accuracy": 0.12222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
1
  {"step": 160000, "seed_holdout": {"answer_byte_loss": 0.2297240496374482, "teacher_forced_byte_accuracy": 0.9090909090909091, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9233456081814237, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
2
  {"step": 165000, "seed_holdout": {"answer_byte_loss": 0.404964976217393, "teacher_forced_byte_accuracy": 0.8461538461538461, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.278676266140408, "teacher_forced_byte_accuracy": 0.12222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
+ {"step": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 160000, "seed_holdout": {"answer_byte_loss": 0.2297240496374482, "teacher_forced_byte_accuracy": 0.9090909090909091, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9233456081814237, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_bfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_interval_overlap", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"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": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 16, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_cross_domain", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_context_operator", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 165000, "seed_holdout": {"answer_byte_loss": 0.404964976217393, "teacher_forced_byte_accuracy": 0.8461538461538461, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.278676266140408, "teacher_forced_byte_accuracy": 0.12222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_representation_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_compositional_holdout", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"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": "seed_holdout", "family": "gen_hidden_rule", "surface": "instruction_json", "exact": false, "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": 12, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_irreversible_action", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"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}]}
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": false, "generated_bytes": 17, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": false, "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": 58, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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}]}
 
 
1
  {"step": 160000, "seed_holdout": {"answer_byte_loss": 0.2297240496374482, "teacher_forced_byte_accuracy": 0.9090909090909091, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9233456081814237, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_bfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_interval_overlap", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"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": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 16, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_cross_domain", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_context_operator", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 165000, "seed_holdout": {"answer_byte_loss": 0.404964976217393, "teacher_forced_byte_accuracy": 0.8461538461538461, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.278676266140408, "teacher_forced_byte_accuracy": 0.12222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_representation_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_compositional_holdout", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"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": "seed_holdout", "family": "gen_hidden_rule", "surface": "instruction_json", "exact": false, "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": 12, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_irreversible_action", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"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}]}
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": false, "generated_bytes": 17, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": false, "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": 58, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"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": 11}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": 6, "target_bytes": 6}, {"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": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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}]}
runs/void-byte-v1/events.out.tfevents.1790563279.bdfa290c-aca9-4e96-a5d2-8425921a3278-d85hq.1304.0.1790563279934888633-82973089 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8248a3de7547370e9fd9555170efc99639010eddf86f27e77984cca8459d0e1c
3
- size 426114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea764a439441e76ffbc582372fca574fe6efff4a154cdec44958951b75a8397c
3
+ size 426897