appvoid commited on
Commit
8a4da96
·
verified ·
1 Parent(s): eb865b2

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790434090210070261-a05fc3fb/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 50000, "seed_holdout": {"answer_byte_loss": 0.20786524512077448, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.399469757080078, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 55000, "seed_holdout": {"answer_byte_loss": 1.7920900200094496, "teacher_forced_byte_accuracy": 0.5714285714285714, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.402945963541667, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
4
  {"step": 60000, "seed_holdout": {"answer_byte_loss": 0.32872645310484444, "teacher_forced_byte_accuracy": 0.8538461538461538, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.0521875593397354, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
2
  {"step": 50000, "seed_holdout": {"answer_byte_loss": 0.20786524512077448, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.399469757080078, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 55000, "seed_holdout": {"answer_byte_loss": 1.7920900200094496, "teacher_forced_byte_accuracy": 0.5714285714285714, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.402945963541667, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
4
  {"step": 60000, "seed_holdout": {"answer_byte_loss": 0.32872645310484444, "teacher_forced_byte_accuracy": 0.8538461538461538, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.0521875593397354, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
5
+ {"step": 65000, "seed_holdout": {"answer_byte_loss": 0.06583652069981573, "teacher_forced_byte_accuracy": 0.9745762711864406, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1907982296413846, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 50000, "seed_holdout": {"answer_byte_loss": 0.20786524512077448, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.399469757080078, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_deque", "surface": "instruction_json", "exact": false, "generated_bytes": 17, "target_bytes": 23}, {"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": true, "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": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_loop_counter", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_multi_register", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_program_trace", "surface": "instruction_json", "exact": false, "generated_bytes": 50, "target_bytes": 42}, {"group": "seed_holdout", "family": "gen_stack_expr", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_bracket_balance", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 16}]}
3
  {"step": 55000, "seed_holdout": {"answer_byte_loss": 1.7920900200094496, "teacher_forced_byte_accuracy": 0.5714285714285714, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.402945963541667, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_bracket_depth", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_remainder", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modular", "surface": "symbolic", "exact": false, "generated_bytes": 1, "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": "seed_holdout", "family": "gen_fraction_equiv", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_affine", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_unit_conversion", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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}]}
4
  {"step": 60000, "seed_holdout": {"answer_byte_loss": 0.32872645310484444, "teacher_forced_byte_accuracy": 0.8538461538461538, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.0521875593397354, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": false, "generated_bytes": 192, "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": false, "generated_bytes": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_toroidal", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_falling", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_obstacle_motion", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_path_keys", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_dynamic_plan", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_competing_hypotheses", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "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": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
2
  {"step": 50000, "seed_holdout": {"answer_byte_loss": 0.20786524512077448, "teacher_forced_byte_accuracy": 0.9333333333333333, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.399469757080078, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_deque", "surface": "instruction_json", "exact": false, "generated_bytes": 17, "target_bytes": 23}, {"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": true, "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": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_loop_counter", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_multi_register", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_program_trace", "surface": "instruction_json", "exact": false, "generated_bytes": 50, "target_bytes": 42}, {"group": "seed_holdout", "family": "gen_stack_expr", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_bracket_balance", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 16}]}
3
  {"step": 55000, "seed_holdout": {"answer_byte_loss": 1.7920900200094496, "teacher_forced_byte_accuracy": 0.5714285714285714, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.402945963541667, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_bracket_depth", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_remainder", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modular", "surface": "symbolic", "exact": false, "generated_bytes": 1, "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": "seed_holdout", "family": "gen_fraction_equiv", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_affine", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_unit_conversion", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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}]}
4
  {"step": 60000, "seed_holdout": {"answer_byte_loss": 0.32872645310484444, "teacher_forced_byte_accuracy": 0.8538461538461538, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.0521875593397354, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": false, "generated_bytes": 192, "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": false, "generated_bytes": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_toroidal", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_falling", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"group": "seed_holdout", "family": "gen_obstacle_motion", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_path_keys", "surface": "instruction_json", "exact": false, "generated_bytes": 192, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_dynamic_plan", "surface": "instruction_json", "exact": false, "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": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_competing_hypotheses", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "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": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
+ {"step": 65000, "seed_holdout": {"answer_byte_loss": 0.06583652069981573, "teacher_forced_byte_accuracy": 0.9745762711864406, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1907982296413846, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 20, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_binary_search", "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": 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.1790434090.372bd512-57cc-4928-b44a-3b375a0fa071-5spg5.451.0.1790434090210070261-a05fc3fb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa134008d5b67f3d1e300e4cbe470ed00e9c11c6ba378d3a0c37a2aaeb5c4323
3
- size 532797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c5ef831da509b877211dca908922754353839d79785a2e5c5f8616b68e0e12
3
+ size 533580