appvoid commited on
Commit
3233289
·
verified ·
1 Parent(s): 2da24a5

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791143623306220418-eb05a537/eval.jsonl CHANGED
@@ -4,3 +4,4 @@
4
  {"step": 705000, "seed_holdout": {"answer_byte_loss": 0.2385293874646155, "teacher_forced_byte_accuracy": 0.8881578947368421, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.743338860405816, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
5
  {"step": 710000, "seed_holdout": {"answer_byte_loss": 0.16763065223426135, "teacher_forced_byte_accuracy": 0.949685534591195, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6708871205647786, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 715000, "seed_holdout": {"answer_byte_loss": 0.022332964481652846, "teacher_forced_byte_accuracy": 0.9821428571428571, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5596530490451388, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
 
 
4
  {"step": 705000, "seed_holdout": {"answer_byte_loss": 0.2385293874646155, "teacher_forced_byte_accuracy": 0.8881578947368421, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.743338860405816, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
5
  {"step": 710000, "seed_holdout": {"answer_byte_loss": 0.16763065223426135, "teacher_forced_byte_accuracy": 0.949685534591195, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6708871205647786, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
6
  {"step": 715000, "seed_holdout": {"answer_byte_loss": 0.022332964481652846, "teacher_forced_byte_accuracy": 0.9821428571428571, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5596530490451388, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
7
+ {"step": 720000, "seed_holdout": {"answer_byte_loss": 0.7124794456081872, "teacher_forced_byte_accuracy": 0.8142857142857143, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7073803371853298, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -4,3 +4,4 @@
4
  {"step": 705000, "seed_holdout": {"answer_byte_loss": 0.2385293874646155, "teacher_forced_byte_accuracy": 0.8881578947368421, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.743338860405816, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_unknown_goal", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_door_key", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_irreversible_action", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"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": true, "generated_bytes": 20, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 32, "target_bytes": 32}, {"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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
5
  {"step": 710000, "seed_holdout": {"answer_byte_loss": 0.16763065223426135, "teacher_forced_byte_accuracy": 0.949685534591195, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6708871205647786, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": true, "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": true, "generated_bytes": 20, "target_bytes": 20}, {"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": 34, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"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": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 66, "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}]}
6
  {"step": 715000, "seed_holdout": {"answer_byte_loss": 0.022332964481652846, "teacher_forced_byte_accuracy": 0.9821428571428571, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5596530490451388, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"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": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 6}, {"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": 10, "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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
4
  {"step": 705000, "seed_holdout": {"answer_byte_loss": 0.2385293874646155, "teacher_forced_byte_accuracy": 0.8881578947368421, "generation_exact_match": 0.4166666666666667, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.743338860405816, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_unknown_goal", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_door_key", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_tool_affordance", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_irreversible_action", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"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": true, "generated_bytes": 20, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_select_cell", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_sequence_composition", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_program_states", "surface": "instruction_json", "exact": true, "generated_bytes": 32, "target_bytes": 32}, {"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": 13, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
5
  {"step": 710000, "seed_holdout": {"answer_byte_loss": 0.16763065223426135, "teacher_forced_byte_accuracy": 0.949685534591195, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6708871205647786, "teacher_forced_byte_accuracy": 0.4, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_grammar_expansion", "surface": "instruction_json", "exact": true, "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": true, "generated_bytes": 20, "target_bytes": 20}, {"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": 34, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_span_reordering", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"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": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 66, "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}]}
6
  {"step": 715000, "seed_holdout": {"answer_byte_loss": 0.022332964481652846, "teacher_forced_byte_accuracy": 0.9821428571428571, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5596530490451388, "teacher_forced_byte_accuracy": 0.45555555555555555, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"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": 24, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 6}, {"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": 10, "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": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
7
+ {"step": 720000, "seed_holdout": {"answer_byte_loss": 0.7124794456081872, "teacher_forced_byte_accuracy": 0.8142857142857143, "generation_exact_match": 0.4166666666666667, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7073803371853298, "teacher_forced_byte_accuracy": 0.3888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"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": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"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": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"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": true, "generated_bytes": 10, "target_bytes": 10}, {"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": 3, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 4}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1791143623.3eb6ddb3-ffce-42e5-bd48-c0d653189e98-8pb7d.369.0.1791143623306220418-eb05a537 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38e74344c6bc1d94cfedd0ec25e319aea91cec7e2541f5127251ecc37df5c6b8
3
- size 746163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1b2ec6e60b1dab3d1304b7026bde77dadfc7369ca315fefeb265c3c4265622
3
+ size 746946