appvoid commited on
Commit
92dbe79
·
verified ·
1 Parent(s): 901b8ec

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791399463488568880-054ba646/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 900000, "seed_holdout": {"answer_byte_loss": 0.24635956257138655, "teacher_forced_byte_accuracy": 0.9514563106796117, "generation_exact_match": 0.6666666666666666, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8900953080919054, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 905000, "seed_holdout": {"answer_byte_loss": 1.0345791613852435, "teacher_forced_byte_accuracy": 0.6590909090909091, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6006631003485785, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
  {"step": 910000, "seed_holdout": {"answer_byte_loss": 0.47912809097371395, "teacher_forced_byte_accuracy": 0.8056872037914692, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4498549037509494, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
 
 
3
  {"step": 900000, "seed_holdout": {"answer_byte_loss": 0.24635956257138655, "teacher_forced_byte_accuracy": 0.9514563106796117, "generation_exact_match": 0.6666666666666666, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8900953080919054, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
  {"step": 905000, "seed_holdout": {"answer_byte_loss": 1.0345791613852435, "teacher_forced_byte_accuracy": 0.6590909090909091, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6006631003485785, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
5
  {"step": 910000, "seed_holdout": {"answer_byte_loss": 0.47912809097371395, "teacher_forced_byte_accuracy": 0.8056872037914692, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4498549037509494, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
6
+ {"step": 915000, "seed_holdout": {"answer_byte_loss": 0.39518059462760435, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4526077694363064, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -3,3 +3,4 @@
3
  {"step": 900000, "seed_holdout": {"answer_byte_loss": 0.24635956257138655, "teacher_forced_byte_accuracy": 0.9514563106796117, "generation_exact_match": 0.6666666666666666, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8900953080919054, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 20, "target_bytes": 20}, {"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": 2}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"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": true, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 36, "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": 905000, "seed_holdout": {"answer_byte_loss": 1.0345791613852435, "teacher_forced_byte_accuracy": 0.6590909090909091, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6006631003485785, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 13, "target_bytes": 10}, {"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": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": true, "generated_bytes": 21, "target_bytes": 21}, {"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": 27, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
  {"step": 910000, "seed_holdout": {"answer_byte_loss": 0.47912809097371395, "teacher_forced_byte_accuracy": 0.8056872037914692, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4498549037509494, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": true, "generated_bytes": 27, "target_bytes": 27}, {"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": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"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": 8, "target_bytes": 6}, {"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": 9, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 23, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 39, "target_bytes": 37}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
 
 
3
  {"step": 900000, "seed_holdout": {"answer_byte_loss": 0.24635956257138655, "teacher_forced_byte_accuracy": 0.9514563106796117, "generation_exact_match": 0.6666666666666666, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.8900953080919054, "teacher_forced_byte_accuracy": 0.34444444444444444, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": true, "generated_bytes": 20, "target_bytes": 20}, {"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": 2}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 2}, {"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": true, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 36, "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": 905000, "seed_holdout": {"answer_byte_loss": 1.0345791613852435, "teacher_forced_byte_accuracy": 0.6590909090909091, "generation_exact_match": 0.25, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.6006631003485785, "teacher_forced_byte_accuracy": 0.43333333333333335, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"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": 13, "target_bytes": 10}, {"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": 6, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 22, "target_bytes": 19}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": true, "generated_bytes": 21, "target_bytes": 21}, {"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": 27, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
5
  {"step": 910000, "seed_holdout": {"answer_byte_loss": 0.47912809097371395, "teacher_forced_byte_accuracy": 0.8056872037914692, "generation_exact_match": 0.16666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4498549037509494, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": true, "generated_bytes": 27, "target_bytes": 27}, {"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": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 25}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"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": 8, "target_bytes": 6}, {"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": 9, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_variable_code_recurrence", "surface": "symbolic", "exact": false, "generated_bytes": 23, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 39, "target_bytes": 37}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 36, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
6
+ {"step": 915000, "seed_holdout": {"answer_byte_loss": 0.39518059462760435, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.5, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.4526077694363064, "teacher_forced_byte_accuracy": 0.5333333333333333, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 11, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": false, "generated_bytes": 19, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": true, "generated_bytes": 17, "target_bytes": 17}, {"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": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_object_permanence", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_heuristic_vs_model", "surface": "symbolic", "exact": true, "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": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 28, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 15, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1791399463.60f38c85-66c9-4fe6-8e58-7b3a56dc2cee-wtkw8.346.0.1791399463488568880-054ba646 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e03cd9fa4e39dc43dc7824e44c0c3b17658647b17dac0a09fc1661a33cf5d6
3
- size 639480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292ed5ed5e5ced811754f8740c10b0dfcdd92ebeb21dd9b10a06d9e43ad8954a
3
+ size 640263