appvoid commited on
Commit
a78bcbc
·
verified ·
1 Parent(s): 1e126aa

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790703713325746110-adad6d18/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 285000, "seed_holdout": {"answer_byte_loss": 1.1887182465621404, "teacher_forced_byte_accuracy": 0.6857142857142857, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8230045742458767, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 290000, "seed_holdout": {"answer_byte_loss": 1.8558023591490032, "teacher_forced_byte_accuracy": 0.6153846153846154, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.3467967139350043, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 295000, "seed_holdout": {"answer_byte_loss": 0.7110476251458749, "teacher_forced_byte_accuracy": 0.85, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.784661059909397, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
1
  {"step": 285000, "seed_holdout": {"answer_byte_loss": 1.1887182465621404, "teacher_forced_byte_accuracy": 0.6857142857142857, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8230045742458767, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 290000, "seed_holdout": {"answer_byte_loss": 1.8558023591490032, "teacher_forced_byte_accuracy": 0.6153846153846154, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.3467967139350043, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
3
  {"step": 295000, "seed_holdout": {"answer_byte_loss": 0.7110476251458749, "teacher_forced_byte_accuracy": 0.85, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.784661059909397, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
+ {"step": 300000, "seed_holdout": {"answer_byte_loss": 0.05388236856251432, "teacher_forced_byte_accuracy": 0.9780701754385965, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.72424307929145, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 285000, "seed_holdout": {"answer_byte_loss": 1.1887182465621404, "teacher_forced_byte_accuracy": 0.6857142857142857, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8230045742458767, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 15}, {"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": 5, "target_bytes": 5}, {"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": 10, "target_bytes": 16}]}
3
  {"step": 290000, "seed_holdout": {"answer_byte_loss": 1.8558023591490032, "teacher_forced_byte_accuracy": 0.6153846153846154, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.3467967139350043, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": false, "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": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": true, "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": false, "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": 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": "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": 295000, "seed_holdout": {"answer_byte_loss": 0.7110476251458749, "teacher_forced_byte_accuracy": 0.85, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.784661059909397, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 7}, {"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": 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": false, "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": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"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}]}
 
 
2
  {"step": 285000, "seed_holdout": {"answer_byte_loss": 1.1887182465621404, "teacher_forced_byte_accuracy": 0.6857142857142857, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8230045742458767, "teacher_forced_byte_accuracy": 0.24444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 35}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 15}, {"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": 5, "target_bytes": 5}, {"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": 10, "target_bytes": 16}]}
3
  {"step": 290000, "seed_holdout": {"answer_byte_loss": 1.8558023591490032, "teacher_forced_byte_accuracy": 0.6153846153846154, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.3467967139350043, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": false, "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": "seed_holdout", "family": "gen_boolean_composition", "surface": "symbolic", "exact": true, "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": false, "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": 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": "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": 295000, "seed_holdout": {"answer_byte_loss": 0.7110476251458749, "teacher_forced_byte_accuracy": 0.85, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.784661059909397, "teacher_forced_byte_accuracy": 0.26666666666666666, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 7}, {"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": 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": false, "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": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"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}]}
5
+ {"step": 300000, "seed_holdout": {"answer_byte_loss": 0.05388236856251432, "teacher_forced_byte_accuracy": 0.9780701754385965, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.72424307929145, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": false, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": true, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 33}, {"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": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": false, "generated_bytes": 49, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"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": "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": 17, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1790703713.3e6d470a-8cc7-4d7e-a224-51a0f9a2ce55-85btc.38629.0.1790703713325746110-adad6d18 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7850e026554607a7700deb48ba2cd861d856ae8f183b442c5e9c649765f37044
3
- size 421878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984f64f63a6d9c46b03440350f09af265cb985eed79cab2d9c3c24d9a17c8d2d
3
+ size 422661