appvoid commited on
Commit
2f9e4f2
·
verified ·
1 Parent(s): 3860d43

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790563279934888633-82973089/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
5
  {"step": 180000, "seed_holdout": {"answer_byte_loss": 0.40631541374104674, "teacher_forced_byte_accuracy": 0.8785046728971962, "generation_exact_match": 0.8333333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.104140133327908, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
5
  {"step": 180000, "seed_holdout": {"answer_byte_loss": 0.40631541374104674, "teacher_forced_byte_accuracy": 0.8785046728971962, "generation_exact_match": 0.8333333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.104140133327908, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
+ {"step": 185000, "seed_holdout": {"answer_byte_loss": 0.9845203371983398, "teacher_forced_byte_accuracy": 0.7431192660550459, "generation_exact_match": 0.16666666666666666, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9127580006917317, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_explore_infer_exploit", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_rule_switch", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_goal_switch", "surface": "instruction_json", "exact": false, "generated_bytes": 17, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_scope_shadowing", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relational_join", "surface": "instruction_json", "exact": false, "generated_bytes": 58, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_nested_substitution", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"group": "seed_holdout", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_instruction_override", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_output_schema", "surface": "instruction_json", "exact": true, "generated_bytes": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": 180000, "seed_holdout": {"answer_byte_loss": 0.40631541374104674, "teacher_forced_byte_accuracy": 0.8785046728971962, "generation_exact_match": 0.8333333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.104140133327908, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": true, "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": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 13}, {"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": 9, "target_bytes": 16}]}
 
 
3
  {"step": 170000, "seed_holdout": {"answer_byte_loss": 0.19442400832256107, "teacher_forced_byte_accuracy": 0.9078947368421053, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.048811976114909, "teacher_forced_byte_accuracy": 0.17777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_explore_infer_exploit", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_rule_switch", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_goal_switch", "surface": "instruction_json", "exact": false, "generated_bytes": 17, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_stable_partition", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_scope_shadowing", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_relational_join", "surface": "instruction_json", "exact": false, "generated_bytes": 58, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 22, "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": 175000, "seed_holdout": {"answer_byte_loss": 0.19696718628280205, "teacher_forced_byte_accuracy": 0.9180327868852459, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.7545394049750436, "teacher_forced_byte_accuracy": 0.25555555555555554, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_nested_substitution", "surface": "instruction_json", "exact": true, "generated_bytes": 18, "target_bytes": 18}, {"group": "seed_holdout", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_instruction_override", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_output_schema", "surface": "instruction_json", "exact": true, "generated_bytes": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"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": 180000, "seed_holdout": {"answer_byte_loss": 0.40631541374104674, "teacher_forced_byte_accuracy": 0.8785046728971962, "generation_exact_match": 0.8333333333333334, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.104140133327908, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": true, "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": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 13}, {"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": 9, "target_bytes": 16}]}
6
+ {"step": 185000, "seed_holdout": {"answer_byte_loss": 0.9845203371983398, "teacher_forced_byte_accuracy": 0.7431192660550459, "generation_exact_match": 0.16666666666666666, "generation_truncated": 2, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.9127580006917317, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 65}, {"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": 192, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 6}, {"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}]}
runs/void-byte-v1/events.out.tfevents.1790563279.bdfa290c-aca9-4e96-a5d2-8425921a3278-d85hq.1304.0.1790563279934888633-82973089 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f96ff5f7c022af899099f41cfb21bc7c693d1f8ae268684e91e9b694ef7151
3
- size 639480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b03dd3ced4b5c4bc38df8e73fe826c2b2152445ecea43f5be6bfcab4da6db39
3
+ size 640263