appvoid commited on
Commit
3eb575e
·
verified ·
1 Parent(s): 440828f

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790606918076636751-3952f1c5/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 205000, "seed_holdout": {"answer_byte_loss": 1.0292715753771757, "teacher_forced_byte_accuracy": 0.6578947368421053, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.12231928507487, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 210000, "seed_holdout": {"answer_byte_loss": 0.05323252784725368, "teacher_forced_byte_accuracy": 0.9782135076252724, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.876017549302843, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
4
  {"step": 215000, "seed_holdout": {"answer_byte_loss": 0.193016217333429, "teacher_forced_byte_accuracy": 0.9458823529411765, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2571710798475477, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
2
  {"step": 205000, "seed_holdout": {"answer_byte_loss": 1.0292715753771757, "teacher_forced_byte_accuracy": 0.6578947368421053, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.12231928507487, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 210000, "seed_holdout": {"answer_byte_loss": 0.05323252784725368, "teacher_forced_byte_accuracy": 0.9782135076252724, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.876017549302843, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
4
  {"step": 215000, "seed_holdout": {"answer_byte_loss": 0.193016217333429, "teacher_forced_byte_accuracy": 0.9458823529411765, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2571710798475477, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
5
+ {"step": 220000, "seed_holdout": {"answer_byte_loss": 0.4564366127031722, "teacher_forced_byte_accuracy": 0.8857142857142857, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9706293741861978, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 205000, "seed_holdout": {"answer_byte_loss": 1.0292715753771757, "teacher_forced_byte_accuracy": 0.6578947368421053, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.12231928507487, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": false, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"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}]}
3
  {"step": 210000, "seed_holdout": {"answer_byte_loss": 0.05323252784725368, "teacher_forced_byte_accuracy": 0.9782135076252724, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.876017549302843, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 58, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 53, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_extract_largest", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"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": 215000, "seed_holdout": {"answer_byte_loss": 0.193016217333429, "teacher_forced_byte_accuracy": 0.9458823529411765, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2571710798475477, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_complete_symmetry", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": true, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 68, "target_bytes": 68}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 33}, {"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": 54, "target_bytes": 54}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_single_fact", "surface": "symbolic", "exact": true, "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": 20, "target_bytes": 16}]}
 
 
2
  {"step": 205000, "seed_holdout": {"answer_byte_loss": 1.0292715753771757, "teacher_forced_byte_accuracy": 0.6578947368421053, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.12231928507487, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": false, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"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}]}
3
  {"step": 210000, "seed_holdout": {"answer_byte_loss": 0.05323252784725368, "teacher_forced_byte_accuracy": 0.9782135076252724, "generation_exact_match": 0.5833333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.876017549302843, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 58, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 53, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_extract_largest", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"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": 215000, "seed_holdout": {"answer_byte_loss": 0.193016217333429, "teacher_forced_byte_accuracy": 0.9458823529411765, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2571710798475477, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_complete_symmetry", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": true, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 68, "target_bytes": 68}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 33}, {"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": 54, "target_bytes": 54}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_single_fact", "surface": "symbolic", "exact": true, "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": 20, "target_bytes": 16}]}
5
+ {"step": 220000, "seed_holdout": {"answer_byte_loss": 0.4564366127031722, "teacher_forced_byte_accuracy": 0.8857142857142857, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9706293741861978, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_transitivity", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_symmetric", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"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": false, "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": false, "generated_bytes": 1, "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": 6, "target_bytes": 6}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 13, "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}]}
runs/void-byte-v1/events.out.tfevents.1790606918.0a7f8bdc-23d3-4ecb-bd0c-4a4bf460026e-rl2cx.1192.0.1790606918076636751-3952f1c5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3fefc09f5baffb07cf032229d498c8681c34568a299a002c34fae265fe4ddfb
3
- size 532797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e4540b84aa3fabf0e7aafbbdbb7daff6cb45459469d726594e5352432ada30
3
+ size 533580