appvoid commited on
Commit
cab87c5
·
verified ·
1 Parent(s): 85f36ed

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791254470898546162-7724d9f6/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 775000, "seed_holdout": {"answer_byte_loss": 0.09891445325840985, "teacher_forced_byte_accuracy": 0.9545454545454546, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5814612494574654, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
4
  {"step": 780000, "seed_holdout": {"answer_byte_loss": 0.029550980931449693, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.697406874762641, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
5
  {"step": 785000, "seed_holdout": {"answer_byte_loss": 0.03759662822848222, "teacher_forced_byte_accuracy": 0.9844961240310077, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.571707026163737, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
 
 
3
  {"step": 775000, "seed_holdout": {"answer_byte_loss": 0.09891445325840985, "teacher_forced_byte_accuracy": 0.9545454545454546, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5814612494574654, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
4
  {"step": 780000, "seed_holdout": {"answer_byte_loss": 0.029550980931449693, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.697406874762641, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
5
  {"step": 785000, "seed_holdout": {"answer_byte_loss": 0.03759662822848222, "teacher_forced_byte_accuracy": 0.9844961240310077, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.571707026163737, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
6
+ {"step": 790000, "seed_holdout": {"answer_byte_loss": 0.11763821709497153, "teacher_forced_byte_accuracy": 0.9396551724137931, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6582793977525498, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 775000, "seed_holdout": {"answer_byte_loss": 0.09891445325840985, "teacher_forced_byte_accuracy": 0.9545454545454546, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5814612494574654, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_difference", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_linear", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_affine", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_unit_conversion", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_coords", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_line_of_sight", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_containment", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_collision", "surface": "instruction_json", "exact": true, "generated_bytes": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_toroidal", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_falling", "surface": "instruction_json", "exact": true, "generated_bytes": 34, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_obstacle_motion", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_path_keys", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "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": 17, "target_bytes": 16}]}
4
  {"step": 780000, "seed_holdout": {"answer_byte_loss": 0.029550980931449693, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.697406874762641, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_dynamic_plan", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_direct_cause", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_confounding", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_competing_hypotheses", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_noisy_evidence", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_active_disambiguation", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_qual_bayes", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"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": 21, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 16}]}
5
  {"step": 785000, "seed_holdout": {"answer_byte_loss": 0.03759662822848222, "teacher_forced_byte_accuracy": 0.9844961240310077, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.571707026163737, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"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": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_binary_search", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "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": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"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": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 16}]}
 
 
3
  {"step": 775000, "seed_holdout": {"answer_byte_loss": 0.09891445325840985, "teacher_forced_byte_accuracy": 0.9545454545454546, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5814612494574654, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_difference", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_linear", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_affine", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_unit_conversion", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_coords", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_line_of_sight", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_containment", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_collision", "surface": "instruction_json", "exact": true, "generated_bytes": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_toroidal", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_falling", "surface": "instruction_json", "exact": true, "generated_bytes": 34, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_obstacle_motion", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_path_keys", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "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": 17, "target_bytes": 16}]}
4
  {"step": 780000, "seed_holdout": {"answer_byte_loss": 0.029550980931449693, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.697406874762641, "teacher_forced_byte_accuracy": 0.4666666666666667, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_dynamic_plan", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_direct_cause", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_confounding", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_competing_hypotheses", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_noisy_evidence", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_active_disambiguation", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_qual_bayes", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"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": 21, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 16}]}
5
  {"step": 785000, "seed_holdout": {"answer_byte_loss": 0.03759662822848222, "teacher_forced_byte_accuracy": 0.9844961240310077, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.571707026163737, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"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": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_binary_search", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "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": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"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": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 16}]}
6
+ {"step": 790000, "seed_holdout": {"answer_byte_loss": 0.11763821709497153, "teacher_forced_byte_accuracy": 0.9396551724137931, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6582793977525498, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"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": 18, "target_bytes": 18}, {"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": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_representation_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"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": true, "generated_bytes": 10, "target_bytes": 10}, {"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": "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": 16, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1791254470.1e0c9aa3-e42e-441e-9e17-2e25895f438d-9bhv5.366.0.1791254470898546162-7724d9f6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:809679e661f603e28bb9e3abb9fa5c8b5b547e5968ca1a6683ffa73d13619690
3
- size 639480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d14a68185d17ecd922990237f078c3a0fff34a900e4547918dcfa9c3c0b73cf
3
+ size 640263