appvoid commited on
Commit
0a238bd
·
verified ·
1 Parent(s): 8a572e2

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790485060735632541-7579de36/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 90000, "seed_holdout": {"answer_byte_loss": 0.10723687214872886, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.419833925035265, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 95000, "seed_holdout": {"answer_byte_loss": 1.577071557121892, "teacher_forced_byte_accuracy": 0.5806451612903226, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2091375562879776, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 100000, "seed_holdout": {"answer_byte_loss": 1.3155167066961302, "teacher_forced_byte_accuracy": 0.6541353383458647, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.731900363498264, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
 
 
1
  {"step": 90000, "seed_holdout": {"answer_byte_loss": 0.10723687214872886, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.419833925035265, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 95000, "seed_holdout": {"answer_byte_loss": 1.577071557121892, "teacher_forced_byte_accuracy": 0.5806451612903226, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2091375562879776, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
3
  {"step": 100000, "seed_holdout": {"answer_byte_loss": 1.3155167066961302, "teacher_forced_byte_accuracy": 0.6541353383458647, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.731900363498264, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
4
+ {"step": 105000, "seed_holdout": {"answer_byte_loss": 1.2865558728365831, "teacher_forced_byte_accuracy": 0.6690140845070423, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8422350989447698, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 90000, "seed_holdout": {"answer_byte_loss": 0.10723687214872886, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.419833925035265, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_bounded_arithmetic", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_text_span_extract", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_counterfactual_state", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_missing_information", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 8, "target_bytes": 16}]}
3
  {"step": 95000, "seed_holdout": {"answer_byte_loss": 1.577071557121892, "teacher_forced_byte_accuracy": 0.5806451612903226, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2091375562879776, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_successor_chain", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 15}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "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": 7, "target_bytes": 16}]}
4
  {"step": 100000, "seed_holdout": {"answer_byte_loss": 1.3155167066961302, "teacher_forced_byte_accuracy": 0.6541353383458647, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.731900363498264, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 15}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_binding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 39, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 32, "target_bytes": 31}, {"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": 90000, "seed_holdout": {"answer_byte_loss": 0.10723687214872886, "teacher_forced_byte_accuracy": 0.9587628865979382, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.419833925035265, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_bounded_arithmetic", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_text_span_extract", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_counterfactual_state", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_missing_information", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "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": 8, "target_bytes": 16}]}
3
  {"step": 95000, "seed_holdout": {"answer_byte_loss": 1.577071557121892, "teacher_forced_byte_accuracy": 0.5806451612903226, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.2091375562879776, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_successor_chain", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 15}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 14, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "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": 7, "target_bytes": 16}]}
4
  {"step": 100000, "seed_holdout": {"answer_byte_loss": 1.3155167066961302, "teacher_forced_byte_accuracy": 0.6541353383458647, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.731900363498264, "teacher_forced_byte_accuracy": 0.2, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 15}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_binding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 39, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 32, "target_bytes": 31}, {"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}]}
5
+ {"step": 105000, "seed_holdout": {"answer_byte_loss": 1.2865558728365831, "teacher_forced_byte_accuracy": 0.6690140845070423, "generation_exact_match": 0.08333333333333333, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.8422350989447698, "teacher_forced_byte_accuracy": 0.3111111111111111, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_mixed_world", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_piecewise_dynamics", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_composed_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 7}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 5, "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.1790485060.0b09bbb2-f535-42d2-bd00-cbae7fb94f51-r2qrq.28895.0.1790485060735632541-7579de36 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dafb5ee794ede0bd3e62224bfd644c0b8c41e3c90fd69e29733e8c3b251fec7e
3
- size 426114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdf47be175bb2c58a44e6e28659b1eb3d3fe3c89eeb208df9b42c4453c26a33
3
+ size 426897