appvoid commited on
Commit
524cb42
·
verified ·
1 Parent(s): 5e63647

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790738827394728502-c744ae20/eval.jsonl CHANGED
@@ -4,3 +4,4 @@
4
  {"step": 335000, "seed_holdout": {"answer_byte_loss": 0.09113579246183952, "teacher_forced_byte_accuracy": 0.961864406779661, "generation_exact_match": 0.5833333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.92978761461046, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
5
  {"step": 340000, "seed_holdout": {"answer_byte_loss": 0.291204613689174, "teacher_forced_byte_accuracy": 0.8632478632478633, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.759388732910156, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 345000, "seed_holdout": {"answer_byte_loss": 0.28353690005661475, "teacher_forced_byte_accuracy": 0.9047619047619048, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.526573265923394, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
4
  {"step": 335000, "seed_holdout": {"answer_byte_loss": 0.09113579246183952, "teacher_forced_byte_accuracy": 0.961864406779661, "generation_exact_match": 0.5833333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.92978761461046, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
5
  {"step": 340000, "seed_holdout": {"answer_byte_loss": 0.291204613689174, "teacher_forced_byte_accuracy": 0.8632478632478633, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.759388732910156, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 345000, "seed_holdout": {"answer_byte_loss": 0.28353690005661475, "teacher_forced_byte_accuracy": 0.9047619047619048, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.526573265923394, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
7
+ {"step": 350000, "seed_holdout": {"answer_byte_loss": 0.15095117895609952, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5468843248155384, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -4,3 +4,4 @@
4
  {"step": 335000, "seed_holdout": {"answer_byte_loss": 0.09113579246183952, "teacher_forced_byte_accuracy": 0.961864406779661, "generation_exact_match": 0.5833333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.92978761461046, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_causal_intervention", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_causal_abduction", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_rule_change", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_anomaly_cause", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 72, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"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": 10, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_string_match", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": 14, "target_bytes": 14}, {"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": 13, "target_bytes": 16}]}
5
  {"step": 340000, "seed_holdout": {"answer_byte_loss": 0.291204613689174, "teacher_forced_byte_accuracy": 0.8632478632478633, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.759388732910156, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_topo_sort", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 6, "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": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": false, "generated_bytes": 16, "target_bytes": 16}, {"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": 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": "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": 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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
6
  {"step": 345000, "seed_holdout": {"answer_byte_loss": 0.28353690005661475, "teacher_forced_byte_accuracy": 0.9047619047619048, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.526573265923394, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": true, "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": 12}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"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": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_explore_infer_exploit", "surface": "instruction_json", "exact": false, "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": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 11, "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": 335000, "seed_holdout": {"answer_byte_loss": 0.09113579246183952, "teacher_forced_byte_accuracy": 0.961864406779661, "generation_exact_match": 0.5833333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.92978761461046, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_causal_intervention", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_causal_abduction", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_rule_change", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_anomaly_cause", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 72, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"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": 10, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_string_match", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": 14, "target_bytes": 14}, {"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": 13, "target_bytes": 16}]}
5
  {"step": 340000, "seed_holdout": {"answer_byte_loss": 0.291204613689174, "teacher_forced_byte_accuracy": 0.8632478632478633, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.759388732910156, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_topo_sort", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 6, "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": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": false, "generated_bytes": 16, "target_bytes": 16}, {"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": 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": "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": 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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
6
  {"step": 345000, "seed_holdout": {"answer_byte_loss": 0.28353690005661475, "teacher_forced_byte_accuracy": 0.9047619047619048, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.526573265923394, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": true, "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": 12}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"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": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_explore_infer_exploit", "surface": "instruction_json", "exact": false, "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": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 11, "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": 350000, "seed_holdout": {"answer_byte_loss": 0.15095117895609952, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5468843248155384, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_goal_switch", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 32, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": false, "generated_bytes": 38, "target_bytes": 38}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_scope_shadowing", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_relational_join", "surface": "instruction_json", "exact": false, "generated_bytes": 34, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"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": "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": 10, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1790738827.1a46e860-412e-40b5-8c01-42d24543f8c9-dfnph.319.0.1790738827394728502-c744ae20 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2805347b6cdd667f4bbe282700fec9a8a123aec693239cc67e63a12bfc26a12d
3
- size 746163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b68b38b5d61dbac65cdd4618e48c1db1ccbc57d75138fd561f4ee3189ee29692
3
+ size 746946