appvoid commited on
Commit
1dcb09c
·
verified ·
1 Parent(s): cb3ec3a

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790651964532391049-1e9227c4/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 245000, "seed_holdout": {"answer_byte_loss": 0.10090537052693482, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5146537356906467, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 250000, "seed_holdout": {"answer_byte_loss": 0.14095429658443684, "teacher_forced_byte_accuracy": 0.9380530973451328, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.726464377509223, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 255000, "seed_holdout": {"answer_byte_loss": 0.34777149767119514, "teacher_forced_byte_accuracy": 0.8723404255319149, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.520393286810981, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
 
 
2
  {"step": 245000, "seed_holdout": {"answer_byte_loss": 0.10090537052693482, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5146537356906467, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 250000, "seed_holdout": {"answer_byte_loss": 0.14095429658443684, "teacher_forced_byte_accuracy": 0.9380530973451328, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.726464377509223, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 255000, "seed_holdout": {"answer_byte_loss": 0.34777149767119514, "teacher_forced_byte_accuracy": 0.8723404255319149, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.520393286810981, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}}
5
+ {"step": 260000, "seed_holdout": {"answer_byte_loss": 0.16937774823129395, "teacher_forced_byte_accuracy": 0.9352941176470588, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.927911631266276, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -2,3 +2,4 @@
2
  {"step": 245000, "seed_holdout": {"answer_byte_loss": 0.10090537052693482, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5146537356906467, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_qual_bayes", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_causal_intervention", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_causal_abduction", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_rule_change", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_anomaly_cause", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 58, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_binary_search", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_string_match", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_bfs_order", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"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": 1, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 16}]}
3
  {"step": 250000, "seed_holdout": {"answer_byte_loss": 0.14095429658443684, "teacher_forced_byte_accuracy": 0.9380530973451328, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.726464377509223, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_topo_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_union_find", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_interval_overlap", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_novel_primitive", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modifier_comp", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 16, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_cross_domain", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_context_operator", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_representation_remap", "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": 9, "target_bytes": 16}]}
4
  {"step": 255000, "seed_holdout": {"answer_byte_loss": 0.34777149767119514, "teacher_forced_byte_accuracy": 0.8723404255319149, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.520393286810981, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_compositional_holdout", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_recursive_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_instruction_comp", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_rule_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_hidden_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 4, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "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": "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": 245000, "seed_holdout": {"answer_byte_loss": 0.10090537052693482, "teacher_forced_byte_accuracy": 0.9473684210526315, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5146537356906467, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_qual_bayes", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_causal_intervention", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_causal_abduction", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_rule_change", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_anomaly_cause", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_selection_sort", "surface": "instruction_json", "exact": false, "generated_bytes": 58, "target_bytes": 72}, {"group": "seed_holdout", "family": "gen_insertion_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 32, "target_bytes": 32}, {"group": "seed_holdout", "family": "gen_minmax_scan", "surface": "instruction_json", "exact": true, "generated_bytes": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_linear_search", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_binary_search", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_string_match", "surface": "instruction_json", "exact": false, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_bfs_order", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"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": 1, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 16}]}
3
  {"step": 250000, "seed_holdout": {"answer_byte_loss": 0.14095429658443684, "teacher_forced_byte_accuracy": 0.9380530973451328, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.726464377509223, "teacher_forced_byte_accuracy": 0.23333333333333334, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_dfs_order", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_topo_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_union_find", "surface": "instruction_json", "exact": false, "generated_bytes": 5, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_shortest_path", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_interval_overlap", "surface": "instruction_json", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_novel_primitive", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_modifier_comp", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_mini_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 16, "target_bytes": 16}, {"group": "seed_holdout", "family": "gen_cross_domain", "surface": "instruction_json", "exact": false, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_context_operator", "surface": "instruction_json", "exact": false, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_meta_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_representation_remap", "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": 9, "target_bytes": 16}]}
4
  {"step": 255000, "seed_holdout": {"answer_byte_loss": 0.34777149767119514, "teacher_forced_byte_accuracy": 0.8723404255319149, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.520393286810981, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 3, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_compositional_holdout", "surface": "instruction_json", "exact": false, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_recursive_dsl", "surface": "instruction_json", "exact": true, "generated_bytes": 14, "target_bytes": 14}, {"group": "seed_holdout", "family": "gen_instruction_comp", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_rule_remap", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_hidden_rule", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"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": 4, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_sparse_nav", "surface": "instruction_json", "exact": false, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_partial_map", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "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": "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": 260000, "seed_holdout": {"answer_byte_loss": 0.16937774823129395, "teacher_forced_byte_accuracy": 0.9352941176470588, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.927911631266276, "teacher_forced_byte_accuracy": 0.2222222222222222, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"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": 20}, {"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": false, "generated_bytes": 22, "target_bytes": 22}, {"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": false, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_run_length_codec", "surface": "instruction_json", "exact": false, "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": 26, "target_bytes": 26}, {"group": "seed_holdout", "family": "gen_edit_script", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_conditional_rewrite", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"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}]}
runs/void-byte-v1/events.out.tfevents.1790651964.96f3217e-af24-484e-a73b-abea9eb37bd2-c4mbg.442.0.1790651964532391049-1e9227c4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe143b3512842c8a0dcdf0810b0b5df0fdb2b6c13e5c4bdeac4bb96929dd0918
3
- size 488319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c464c8900c6936785b2494364fab588c8af6ac3bee2aec99c095f2b5026aec
3
+ size 489102