appvoid commited on
Commit
f70aa6d
·
verified ·
1 Parent(s): 791c2b9

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790390190216476996-4d8dc439/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
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}}
7
  {"step": 35000, "seed_holdout": {"answer_byte_loss": 0.4161311358653853, "teacher_forced_byte_accuracy": 0.9039408866995073, "generation_exact_match": 0.08333333333333333, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.224186537000868, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "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}}
7
  {"step": 35000, "seed_holdout": {"answer_byte_loss": 0.4161311358653853, "teacher_forced_byte_accuracy": 0.9039408866995073, "generation_exact_match": 0.08333333333333333, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.224186537000868, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
8
+ {"step": 40000, "seed_holdout": {"answer_byte_loss": 0.5500017883851356, "teacher_forced_byte_accuracy": 0.8762886597938144, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4070293850368922, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
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}]}
7
  {"step": 35000, "seed_holdout": {"answer_byte_loss": 0.4161311358653853, "teacher_forced_byte_accuracy": 0.9039408866995073, "generation_exact_match": 0.08333333333333333, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.224186537000868, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_extract_largest", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_complete_symmetry", "surface": "symbolic", "exact": false, "generated_bytes": 23, "target_bytes": 29}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": false, "generated_bytes": 13, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": false, "generated_bytes": 52, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 48, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_three_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_sort_rows", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 29}, {"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}]}
 
 
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}]}
7
  {"step": 35000, "seed_holdout": {"answer_byte_loss": 0.4161311358653853, "teacher_forced_byte_accuracy": 0.9039408866995073, "generation_exact_match": 0.08333333333333333, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.224186537000868, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_extract_largest", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_complete_symmetry", "surface": "symbolic", "exact": false, "generated_bytes": 23, "target_bytes": 29}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": false, "generated_bytes": 13, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": false, "generated_bytes": 52, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 48, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_three_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_sort_rows", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 29}, {"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}]}
8
+ {"step": 40000, "seed_holdout": {"answer_byte_loss": 0.5500017883851356, "teacher_forced_byte_accuracy": 0.8762886597938144, "generation_exact_match": 0.08333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.4070293850368922, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": false, "generated_bytes": 60, "target_bytes": 68}, {"group": "seed_holdout", "family": "gen_single_fact", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_two_hop", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_hop", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_inverse", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_transitivity", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_symmetric", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_temporal_order", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_rank", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relation_comp", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_exactly_one", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_at_least", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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:e21a3897c8da5e98ec0f5fcd9be7fcf45d68003410aa9dff93766a1e05f8529d
3
- size 847072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4db0457abc340dfee14d69a99223e2736a148670a4cad94355de4dc6c8f8303
3
+ size 847855