appvoid commited on
Commit
483b5b5
·
verified ·
1 Parent(s): 8be36d0

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791209746770022608-f3fe5fb7/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 730000, "seed_holdout": {"answer_byte_loss": 0.36044036056245526, "teacher_forced_byte_accuracy": 0.842741935483871, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8071771409776476, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 735000, "seed_holdout": {"answer_byte_loss": 1.019450135960959, "teacher_forced_byte_accuracy": 0.6666666666666666, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.705854500664605, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
4
  {"step": 740000, "seed_holdout": {"answer_byte_loss": 0.3206533582866541, "teacher_forced_byte_accuracy": 0.9, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6817543665568033, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
 
 
2
  {"step": 730000, "seed_holdout": {"answer_byte_loss": 0.36044036056245526, "teacher_forced_byte_accuracy": 0.842741935483871, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8071771409776476, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 735000, "seed_holdout": {"answer_byte_loss": 1.019450135960959, "teacher_forced_byte_accuracy": 0.6666666666666666, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.705854500664605, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
4
  {"step": 740000, "seed_holdout": {"answer_byte_loss": 0.3206533582866541, "teacher_forced_byte_accuracy": 0.9, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6817543665568033, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
+ {"step": 745000, "seed_holdout": {"answer_byte_loss": 0.05287774541954461, "teacher_forced_byte_accuracy": 0.981203007518797, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.669119464026557, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 730000, "seed_holdout": {"answer_byte_loss": 0.36044036056245526, "teacher_forced_byte_accuracy": 0.842741935483871, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8071771409776476, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": true, "generated_bytes": 64, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 37, "target_bytes": 37}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": true, "generated_bytes": 23, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 10}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 31, "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": 15, "target_bytes": 16}]}
3
  {"step": 735000, "seed_holdout": {"answer_byte_loss": 1.019450135960959, "teacher_forced_byte_accuracy": 0.6666666666666666, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.705854500664605, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 13}, {"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": 6}, {"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": 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": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
4
  {"step": 740000, "seed_holdout": {"answer_byte_loss": 0.3206533582866541, "teacher_forced_byte_accuracy": 0.9, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6817543665568033, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 11, "target_bytes": 11}, {"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": 3, "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": true, "generated_bytes": 8, "target_bytes": 8}, {"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": 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": "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": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
2
  {"step": 730000, "seed_holdout": {"answer_byte_loss": 0.36044036056245526, "teacher_forced_byte_accuracy": 0.842741935483871, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8071771409776476, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": true, "generated_bytes": 64, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 37, "target_bytes": 37}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": true, "generated_bytes": 23, "target_bytes": 23}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 10}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 31, "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": 15, "target_bytes": 16}]}
3
  {"step": 735000, "seed_holdout": {"answer_byte_loss": 1.019450135960959, "teacher_forced_byte_accuracy": 0.6666666666666666, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.705854500664605, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 13}, {"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": 6}, {"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": 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": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
4
  {"step": 740000, "seed_holdout": {"answer_byte_loss": 0.3206533582866541, "teacher_forced_byte_accuracy": 0.9, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6817543665568033, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 11, "target_bytes": 11}, {"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": 3, "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": true, "generated_bytes": 8, "target_bytes": 8}, {"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": 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": "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": 14, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
+ {"step": 745000, "seed_holdout": {"answer_byte_loss": 0.05287774541954461, "teacher_forced_byte_accuracy": 0.981203007518797, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.669119464026557, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": true, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": false, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": false, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 21, "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.1791209746.ebd20fd8-0561-42d8-bf2b-56d08e7106ef-6qqk2.329.0.1791209746770022608-f3fe5fb7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a227486157bfa985ddd1ae655cf3afe951278708e90a6378c3ee7a1c2c15188
3
- size 532797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3575b5c7491965e1a8cf9c1cd1d93fb3bb6bcd7331bf0dca92f3ab3775e2886d
3
+ size 533580