appvoid commited on
Commit
c8930d8
·
verified ·
1 Parent(s): d49a99e

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790989041640695387-36510d53/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 560000, "seed_holdout": {"answer_byte_loss": 0.8940724665590096, "teacher_forced_byte_accuracy": 0.6875, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.6826861487494575, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 565000, "seed_holdout": {"answer_byte_loss": 0.05673352440657175, "teacher_forced_byte_accuracy": 0.9891304347826086, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3207723405626086, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 570000, "seed_holdout": {"answer_byte_loss": 0.06971308760248221, "teacher_forced_byte_accuracy": 0.987012987012987, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5129309548272025, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
 
 
1
  {"step": 560000, "seed_holdout": {"answer_byte_loss": 0.8940724665590096, "teacher_forced_byte_accuracy": 0.6875, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.6826861487494575, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 565000, "seed_holdout": {"answer_byte_loss": 0.05673352440657175, "teacher_forced_byte_accuracy": 0.9891304347826086, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3207723405626086, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 570000, "seed_holdout": {"answer_byte_loss": 0.06971308760248221, "teacher_forced_byte_accuracy": 0.987012987012987, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5129309548272025, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
4
+ {"step": 575000, "seed_holdout": {"answer_byte_loss": 0.06719702047352888, "teacher_forced_byte_accuracy": 0.9795918367346939, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.1740833282470704, "teacher_forced_byte_accuracy": 0.37777777777777777, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 560000, "seed_holdout": {"answer_byte_loss": 0.8940724665590096, "teacher_forced_byte_accuracy": 0.6875, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.6826861487494575, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 2}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 565000, "seed_holdout": {"answer_byte_loss": 0.05673352440657175, "teacher_forced_byte_accuracy": 0.9891304347826086, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3207723405626086, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 20, "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}]}
3
  {"step": 570000, "seed_holdout": {"answer_byte_loss": 0.06971308760248221, "teacher_forced_byte_accuracy": 0.987012987012987, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5129309548272025, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": true, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"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": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 30}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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}]}
 
 
1
  {"step": 560000, "seed_holdout": {"answer_byte_loss": 0.8940724665590096, "teacher_forced_byte_accuracy": 0.6875, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.6826861487494575, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 2}, {"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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 565000, "seed_holdout": {"answer_byte_loss": 0.05673352440657175, "teacher_forced_byte_accuracy": 0.9891304347826086, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3207723405626086, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 20, "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}]}
3
  {"step": 570000, "seed_holdout": {"answer_byte_loss": 0.06971308760248221, "teacher_forced_byte_accuracy": 0.987012987012987, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5129309548272025, "teacher_forced_byte_accuracy": 0.28888888888888886, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": true, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"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": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 30, "target_bytes": 30}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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}]}
4
+ {"step": 575000, "seed_holdout": {"answer_byte_loss": 0.06719702047352888, "teacher_forced_byte_accuracy": 0.9795918367346939, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.1740833282470704, "teacher_forced_byte_accuracy": 0.37777777777777777, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 46, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_three_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_sort_rows", "surface": "symbolic", "exact": true, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": true, "generated_bytes": 41, "target_bytes": 41}, {"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": true, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_single_fact", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_two_hop", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_hop", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_inverse", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_transitivity", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"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": 38, "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.1790989041.fb9d4967-10f3-4fa9-9622-1d5a28f8589b-vh8db.427.0.1790989041640695387-36510d53 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dffd76166db3e648894bfc921d0ef0e605b422540ebe1386f93655c2e3b6200c
3
- size 381636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f4dd9a5a1987ed1079bd7ed19eac9380f909817fd742f26bcd50a7f207ab9b
3
+ size 382419