appvoid commited on
Commit
13fb983
·
verified ·
1 Parent(s): fcd30fe

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790390190216476996-4d8dc439/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 15000, "seed_holdout": {"answer_byte_loss": 0.9870302745709404, "teacher_forced_byte_accuracy": 0.7795527156549521, "generation_exact_match": 0.0, "generation_truncated": 8, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.8398395114474826, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 20000, "seed_holdout": {"answer_byte_loss": 1.5841458638509114, "teacher_forced_byte_accuracy": 0.6111111111111112, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4844625261094837, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
  {"step": 25000, "seed_holdout": {"answer_byte_loss": 2.2672839779406786, "teacher_forced_byte_accuracy": 0.53125, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.5997625986735025, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
 
 
3
  {"step": 15000, "seed_holdout": {"answer_byte_loss": 0.9870302745709404, "teacher_forced_byte_accuracy": 0.7795527156549521, "generation_exact_match": 0.0, "generation_truncated": 8, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.8398395114474826, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 20000, "seed_holdout": {"answer_byte_loss": 1.5841458638509114, "teacher_forced_byte_accuracy": 0.6111111111111112, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4844625261094837, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
  {"step": 25000, "seed_holdout": {"answer_byte_loss": 2.2672839779406786, "teacher_forced_byte_accuracy": 0.53125, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.5997625986735025, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
6
+ {"step": 30000, "seed_holdout": {"answer_byte_loss": 0.6158938384350435, "teacher_forced_byte_accuracy": 0.8098765432098766, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.391873508029514, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 15000, "seed_holdout": {"answer_byte_loss": 0.9870302745709404, "teacher_forced_byte_accuracy": 0.7795527156549521, "generation_exact_match": 0.0, "generation_truncated": 8, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.8398395114474826, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 55}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 36}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 66}, {"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": 1, "target_bytes": 16}]}
4
  {"step": 20000, "seed_holdout": {"answer_byte_loss": 1.5841458638509114, "teacher_forced_byte_accuracy": 0.6111111111111112, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4844625261094837, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 29}, {"group": "seed_holdout", "family": "gen_relational_analogy", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_first_principles_chain", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"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": 15, "target_bytes": 16}]}
5
  {"step": 25000, "seed_holdout": {"answer_byte_loss": 2.2672839779406786, "teacher_forced_byte_accuracy": 0.53125, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.5997625986735025, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "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": 6, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 16}]}
 
 
3
  {"step": 15000, "seed_holdout": {"answer_byte_loss": 0.9870302745709404, "teacher_forced_byte_accuracy": 0.7795527156549521, "generation_exact_match": 0.0, "generation_truncated": 8, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.8398395114474826, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 55}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 36}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 66}, {"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": 1, "target_bytes": 16}]}
4
  {"step": 20000, "seed_holdout": {"answer_byte_loss": 1.5841458638509114, "teacher_forced_byte_accuracy": 0.6111111111111112, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4844625261094837, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 29}, {"group": "seed_holdout", "family": "gen_relational_analogy", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_first_principles_chain", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"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": 15, "target_bytes": 16}]}
5
  {"step": 25000, "seed_holdout": {"answer_byte_loss": 2.2672839779406786, "teacher_forced_byte_accuracy": 0.53125, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.5997625986735025, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "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": 6, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 16}]}
6
+ {"step": 30000, "seed_holdout": {"answer_byte_loss": 0.6158938384350435, "teacher_forced_byte_accuracy": 0.8098765432098766, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.391873508029514, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": false, "generated_bytes": 57, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 25}, {"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": 192, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1790390190.c8125a87-1345-4bfd-b42f-0e32ed8b7bb7-6w295.451.0.1790390190216476996-4d8dc439 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b69d0e295289ad9fc337ca4a17d033b0234697d1ad3abd6a81c44b017205823e
3
- size 633706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f35f6bb9f8e5192bf8add50646aae3cd96b6a764979323e903e39d25efc42a7
3
+ size 634489