appvoid commited on
Commit
1b3f009
·
verified ·
1 Parent(s): 8041b08

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790519810984249790-cb9c9513/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 120000, "seed_holdout": {"answer_byte_loss": 0.104942468383915, "teacher_forced_byte_accuracy": 0.9706546275395034, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.134493933783637, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
2
  {"step": 125000, "seed_holdout": {"answer_byte_loss": 0.161992057581845, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7579417758517795, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 130000, "seed_holdout": {"answer_byte_loss": 0.2870901193236932, "teacher_forced_byte_accuracy": 0.9375, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1070432027180988, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
 
 
1
  {"step": 120000, "seed_holdout": {"answer_byte_loss": 0.104942468383915, "teacher_forced_byte_accuracy": 0.9706546275395034, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.134493933783637, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
2
  {"step": 125000, "seed_holdout": {"answer_byte_loss": 0.161992057581845, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7579417758517795, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 130000, "seed_holdout": {"answer_byte_loss": 0.2870901193236932, "teacher_forced_byte_accuracy": 0.9375, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1070432027180988, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
4
+ {"step": 135000, "seed_holdout": {"answer_byte_loss": 0.08334878754471396, "teacher_forced_byte_accuracy": 0.9722222222222222, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8550008561876083, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 120000, "seed_holdout": {"answer_byte_loss": 0.104942468383915, "teacher_forced_byte_accuracy": 0.9706546275395034, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.134493933783637, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": false, "generated_bytes": 50, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 53, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"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}]}
2
  {"step": 125000, "seed_holdout": {"answer_byte_loss": 0.161992057581845, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7579417758517795, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": 33, "target_bytes": 33}, {"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": true, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_three_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_sort_rows", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": false, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": true, "generated_bytes": 35, "target_bytes": 35}, {"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}]}
3
  {"step": 130000, "seed_holdout": {"answer_byte_loss": 0.2870901193236932, "teacher_forced_byte_accuracy": 0.9375, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1070432027180988, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 6, "target_bytes": 6}, {"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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_temporal_order", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_rank", "surface": "symbolic", "exact": true, "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": true, "generated_bytes": 2, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 9, "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": 7, "target_bytes": 16}]}
 
 
1
  {"step": 120000, "seed_holdout": {"answer_byte_loss": 0.104942468383915, "teacher_forced_byte_accuracy": 0.9706546275395034, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.134493933783637, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": false, "generated_bytes": 40, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": false, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": false, "generated_bytes": 50, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 53, "target_bytes": 53}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"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}]}
2
  {"step": 125000, "seed_holdout": {"answer_byte_loss": 0.161992057581845, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7579417758517795, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": 33, "target_bytes": 33}, {"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": true, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_three_rule_comp", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_sort_rows", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_negative_space", "surface": "symbolic", "exact": false, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_occlusion_complete", "surface": "symbolic", "exact": true, "generated_bytes": 35, "target_bytes": 35}, {"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}]}
3
  {"step": 130000, "seed_holdout": {"answer_byte_loss": 0.2870901193236932, "teacher_forced_byte_accuracy": 0.9375, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1070432027180988, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 6, "target_bytes": 6}, {"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": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_temporal_order", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relative_rank", "surface": "symbolic", "exact": true, "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": true, "generated_bytes": 2, "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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 9, "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": 7, "target_bytes": 16}]}
4
+ {"step": 135000, "seed_holdout": {"answer_byte_loss": 0.08334878754471396, "teacher_forced_byte_accuracy": 0.9722222222222222, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8550008561876083, "teacher_forced_byte_accuracy": 0.15555555555555556, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_quantifier", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_ordering_csp", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assignment_matching", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_small_sat", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_contradiction", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_kv_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_role_filler", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_assoc_distractors", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_lookup", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_mutable_dictionary", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_queue", "surface": "instruction_json", "exact": true, "generated_bytes": 17, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_deque", "surface": "instruction_json", "exact": true, "generated_bytes": 23, "target_bytes": 23}, {"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.1790519810.cad0b19a-59f2-43f0-8fb4-2a94097843e2-tjh7c.1336.0.1790519810984249790-cb9c9513 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f74507f726c663b30934d322dd22c369a4b88ad3f368623d1981ab71ba738c5d
3
- size 426114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:112086377bfe52dfaef1597b55b45448e68467de4ecbbda5575b3bee4fa5c2c2
3
+ size 426897