appvoid commited on
Commit
b66c70e
·
verified ·
1 Parent(s): 9b6c71e

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790868774355361490-de221e1d/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
6
  {"step": 470000, "seed_holdout": {"answer_byte_loss": 1.3975493587072818, "teacher_forced_byte_accuracy": 0.6451612903225806, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3832264794243705, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
7
  {"step": 475000, "seed_holdout": {"answer_byte_loss": 0.20843056368822646, "teacher_forced_byte_accuracy": 0.9444444444444444, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.624815919664171, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
5
  {"step": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
6
  {"step": 470000, "seed_holdout": {"answer_byte_loss": 1.3975493587072818, "teacher_forced_byte_accuracy": 0.6451612903225806, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3832264794243705, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
7
  {"step": 475000, "seed_holdout": {"answer_byte_loss": 0.20843056368822646, "teacher_forced_byte_accuracy": 0.9444444444444444, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.624815919664171, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
8
+ {"step": 480000, "seed_holdout": {"answer_byte_loss": 0.0860693943638777, "teacher_forced_byte_accuracy": 0.9690721649484536, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3620742373996313, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 51, "target_bytes": 51}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_relational_analogy", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_first_principles_chain", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 23, "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}]}
6
  {"step": 470000, "seed_holdout": {"answer_byte_loss": 1.3975493587072818, "teacher_forced_byte_accuracy": 0.6451612903225806, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3832264794243705, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": true, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "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": 3}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": true, "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": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "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": 192, "target_bytes": 16}]}
7
  {"step": 475000, "seed_holdout": {"answer_byte_loss": 0.20843056368822646, "teacher_forced_byte_accuracy": 0.9444444444444444, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.624815919664171, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": false, "generated_bytes": 1, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "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": 3, "target_bytes": 4}, {"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": 47, "target_bytes": 47}, {"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": 29, "target_bytes": 29}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "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": 465000, "seed_holdout": {"answer_byte_loss": 0.8438334028485796, "teacher_forced_byte_accuracy": 0.7605633802816901, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.302869182162815, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 51, "target_bytes": 51}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_relational_analogy", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_first_principles_chain", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 23, "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}]}
6
  {"step": 470000, "seed_holdout": {"answer_byte_loss": 1.3975493587072818, "teacher_forced_byte_accuracy": 0.6451612903225806, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3832264794243705, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": true, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "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": 3}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": true, "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": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "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": 192, "target_bytes": 16}]}
7
  {"step": 475000, "seed_holdout": {"answer_byte_loss": 0.20843056368822646, "teacher_forced_byte_accuracy": 0.9444444444444444, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.624815919664171, "teacher_forced_byte_accuracy": 0.2111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": false, "generated_bytes": 1, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "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": 3, "target_bytes": 4}, {"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": 47, "target_bytes": 47}, {"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": 29, "target_bytes": 29}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "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": 480000, "seed_holdout": {"answer_byte_loss": 0.0860693943638777, "teacher_forced_byte_accuracy": 0.9690721649484536, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3620742373996313, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 44, "target_bytes": 40}, {"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": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": true, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": false, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"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": 41, "target_bytes": 41}, {"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": false, "generated_bytes": 9, "target_bytes": 10}, {"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": 20, "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.1790868774.f92f6aaf-743a-4c24-a54a-850bd75954cb-8js8b.612.0.1790868774355361490-de221e1d CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b7aada626abeb682eda59ad40b92954acac0bc0ab0c9efa014954d59c08bc1c
3
- size 848610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c446fd4985aeeb09ea9e5d662ea42c5d6e217ca6b49ecc83029d9003e5862a9
3
+ size 849393