appvoid commited on
Commit
0143e88
·
verified ·
1 Parent(s): 55f7d8e

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791083219122319327-61ae60ac/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 670000, "seed_holdout": {"answer_byte_loss": 0.02670619720233577, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.895165040757921, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 675000, "seed_holdout": {"answer_byte_loss": 0.07665733331128818, "teacher_forced_byte_accuracy": 0.979381443298969, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8684353298611112, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
7
  {"step": 680000, "seed_holdout": {"answer_byte_loss": 0.18728329127964874, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.827804438273112, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
 
 
5
  {"step": 670000, "seed_holdout": {"answer_byte_loss": 0.02670619720233577, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.895165040757921, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 675000, "seed_holdout": {"answer_byte_loss": 0.07665733331128818, "teacher_forced_byte_accuracy": 0.979381443298969, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8684353298611112, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
7
  {"step": 680000, "seed_holdout": {"answer_byte_loss": 0.18728329127964874, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.827804438273112, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
8
+ {"step": 685000, "seed_holdout": {"answer_byte_loss": 0.08726937352700836, "teacher_forced_byte_accuracy": 0.9727272727272728, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.1581334008110895, "teacher_forced_byte_accuracy": 0.32222222222222224, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 670000, "seed_holdout": {"answer_byte_loss": 0.02670619720233577, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.895165040757921, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_temporal_order", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_rank", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relation_comp", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_exactly_one", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_at_least", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_at_most", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_quantifier", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_ordering_csp", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assignment_matching", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_small_sat", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_contradiction", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_kv_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
6
  {"step": 675000, "seed_holdout": {"answer_byte_loss": 0.07665733331128818, "teacher_forced_byte_accuracy": 0.979381443298969, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8684353298611112, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_role_filler", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assoc_distractors", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_mutable_dictionary", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_queue", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_deque", "surface": "instruction_json", "exact": true, "generated_bytes": 21, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_delayed_recall", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_register_swap", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_register_update", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_conditional_branch", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_loop_counter", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_multi_register", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 16}]}
7
  {"step": 680000, "seed_holdout": {"answer_byte_loss": 0.18728329127964874, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.827804438273112, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_program_trace", "surface": "instruction_json", "exact": true, "generated_bytes": 34, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_stack_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_prefix_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_postfix_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_bracket_balance", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_bracket_depth", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multiply", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_divide", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_remainder", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modular", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_magnitude", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_ratio", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 105, "target_bytes": 16}]}
 
 
5
  {"step": 670000, "seed_holdout": {"answer_byte_loss": 0.02670619720233577, "teacher_forced_byte_accuracy": 1.0, "generation_exact_match": 1.0, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.895165040757921, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_temporal_order", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_rank", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relation_comp", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_exactly_one", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_at_least", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_at_most", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_quantifier", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_ordering_csp", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assignment_matching", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_small_sat", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_contradiction", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_kv_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
6
  {"step": 675000, "seed_holdout": {"answer_byte_loss": 0.07665733331128818, "teacher_forced_byte_accuracy": 0.979381443298969, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8684353298611112, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_role_filler", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assoc_distractors", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_mutable_dictionary", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_queue", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_deque", "surface": "instruction_json", "exact": true, "generated_bytes": 21, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_delayed_recall", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_register_swap", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_register_update", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_conditional_branch", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_loop_counter", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_multi_register", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 16}]}
7
  {"step": 680000, "seed_holdout": {"answer_byte_loss": 0.18728329127964874, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.827804438273112, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_program_trace", "surface": "instruction_json", "exact": true, "generated_bytes": 34, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_stack_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_prefix_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_postfix_expr", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_bracket_balance", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_bracket_depth", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multiply", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_divide", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_remainder", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modular", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_magnitude", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_ratio", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 105, "target_bytes": 16}]}
8
+ {"step": 685000, "seed_holdout": {"answer_byte_loss": 0.08726937352700836, "teacher_forced_byte_accuracy": 0.9727272727272728, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.1581334008110895, "teacher_forced_byte_accuracy": 0.32222222222222224, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_fraction_equiv", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"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": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_line_of_sight", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_containment", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_collision", "surface": "instruction_json", "exact": true, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_toroidal", "surface": "instruction_json", "exact": true, "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": 10, "target_bytes": 10}, {"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": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1791083219.1a73f132-ede3-4b51-9e4f-0cafff989449-8p4r7.435.0.1791083219122319327-61ae60ac CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:415103dd0bc580394fd3de86ff784b135ec1c1fefbca12cbbc054172e79bd077
3
- size 852846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98644e3f3a5b85987d675d78e1a8da4bbb73bce9ad8415b92eb3277daceb8cc0
3
+ size 853629