appvoid commited on
Commit
3e28ed5
·
verified ·
1 Parent(s): f229b26

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1791300814123050567-72be911d/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 825000, "seed_holdout": {"answer_byte_loss": 0.439346332475543, "teacher_forced_byte_accuracy": 0.825, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7205108642578124, "teacher_forced_byte_accuracy": 0.4888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
6
  {"step": 830000, "seed_holdout": {"answer_byte_loss": 0.28710586828123213, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5931295182969836, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
7
  {"step": 835000, "seed_holdout": {"answer_byte_loss": 0.005490333977464864, "teacher_forced_byte_accuracy": 0.9968944099378882, "generation_exact_match": 0.9166666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.591941515604655, "teacher_forced_byte_accuracy": 0.4444444444444444, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
 
 
5
  {"step": 825000, "seed_holdout": {"answer_byte_loss": 0.439346332475543, "teacher_forced_byte_accuracy": 0.825, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7205108642578124, "teacher_forced_byte_accuracy": 0.4888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
6
  {"step": 830000, "seed_holdout": {"answer_byte_loss": 0.28710586828123213, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5931295182969836, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
7
  {"step": 835000, "seed_holdout": {"answer_byte_loss": 0.005490333977464864, "teacher_forced_byte_accuracy": 0.9968944099378882, "generation_exact_match": 0.9166666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.591941515604655, "teacher_forced_byte_accuracy": 0.4444444444444444, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
8
+ {"step": 840000, "seed_holdout": {"answer_byte_loss": 0.009959762385597183, "teacher_forced_byte_accuracy": 0.9945504087193461, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.490101284450955, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -5,3 +5,4 @@
5
  {"step": 825000, "seed_holdout": {"answer_byte_loss": 0.439346332475543, "teacher_forced_byte_accuracy": 0.825, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7205108642578124, "teacher_forced_byte_accuracy": 0.4888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 26, "target_bytes": 28}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 17, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 9}, {"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 15, "target_bytes": 16}]}
6
  {"step": 830000, "seed_holdout": {"answer_byte_loss": 0.28710586828123213, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5931295182969836, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 16}]}
7
  {"step": 835000, "seed_holdout": {"answer_byte_loss": 0.005490333977464864, "teacher_forced_byte_accuracy": 0.9968944099378882, "generation_exact_match": 0.9166666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.591941515604655, "teacher_forced_byte_accuracy": 0.4444444444444444, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": true, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": true, "generated_bytes": 30, "target_bytes": 30}, {"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": 11, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
 
 
5
  {"step": 825000, "seed_holdout": {"answer_byte_loss": 0.439346332475543, "teacher_forced_byte_accuracy": 0.825, "generation_exact_match": 0.3333333333333333, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.7205108642578124, "teacher_forced_byte_accuracy": 0.4888888888888889, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_hierarchical_chunk_rewrite", "surface": "symbolic", "exact": false, "generated_bytes": 26, "target_bytes": 28}, {"group": "seed_holdout", "family": "gen_contextual_segmentation", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_rule_competition_counts", "surface": "symbolic", "exact": true, "generated_bytes": 17, "target_bytes": 17}, {"group": "seed_holdout", "family": "gen_simple_prior_counts", "surface": "symbolic", "exact": false, "generated_bytes": 10, "target_bytes": 9}, {"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": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_xor_constraints", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_algebra_invariant", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_conservation_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 15, "target_bytes": 16}]}
6
  {"step": 830000, "seed_holdout": {"answer_byte_loss": 0.28710586828123213, "teacher_forced_byte_accuracy": 0.8787878787878788, "generation_exact_match": 0.6666666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.5931295182969836, "teacher_forced_byte_accuracy": 0.4222222222222222, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_causal_delay", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_simulated_multimodal_motion", "surface": "symbolic", "exact": false, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_intervention", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_abduction_set", "surface": "symbolic", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_corrupted_rule_robustness", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cross_faculty_transfer", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_identity_copy", "surface": "symbolic", "exact": true, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_equality_detection", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_odd_one_out", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_majority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_minority_symbol", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_parity_count", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 18, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 16}]}
7
  {"step": 835000, "seed_holdout": {"answer_byte_loss": 0.005490333977464864, "teacher_forced_byte_accuracy": 0.9968944099378882, "generation_exact_match": 0.9166666666666666, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.591941515604655, "teacher_forced_byte_accuracy": 0.4444444444444444, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_set_membership_basic", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_adjacency_1d", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_run_length_count", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_deduplicate_sequence", "surface": "symbolic", "exact": true, "generated_bytes": 5, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_first_last_relation", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_translate_right", "surface": "symbolic", "exact": true, "generated_bytes": 61, "target_bytes": 61}, {"group": "seed_holdout", "family": "gen_translate_down", "surface": "symbolic", "exact": true, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_reflect_h", "surface": "symbolic", "exact": true, "generated_bytes": 50, "target_bytes": 50}, {"group": "seed_holdout", "family": "gen_reflect_v", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_rotate90", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_rotate180", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_transpose", "surface": "symbolic", "exact": true, "generated_bytes": 30, "target_bytes": 30}, {"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": 11, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 16}]}
8
+ {"step": 840000, "seed_holdout": {"answer_byte_loss": 0.009959762385597183, "teacher_forced_byte_accuracy": 0.9945504087193461, "generation_exact_match": 0.8333333333333334, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 1.490101284450955, "teacher_forced_byte_accuracy": 0.4111111111111111, "generation_exact_match": 0.0, "generation_truncated": 0, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_crop_bbox", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_bbox_outline", "surface": "symbolic", "exact": true, "generated_bytes": 40, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_recolor_largest", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"group": "seed_holdout", "family": "gen_recolor_smallest", "surface": "symbolic", "exact": true, "generated_bytes": 33, "target_bytes": 33}, {"group": "seed_holdout", "family": "gen_extract_largest", "surface": "symbolic", "exact": true, "generated_bytes": 11, "target_bytes": 11}, {"group": "seed_holdout", "family": "gen_complete_symmetry", "surface": "symbolic", "exact": false, "generated_bytes": 35, "target_bytes": 37}, {"group": "seed_holdout", "family": "gen_tile_motif", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_count_to_bar", "surface": "symbolic", "exact": true, "generated_bytes": 13, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_remove_noise", "surface": "symbolic", "exact": true, "generated_bytes": 30, "target_bytes": 30}, {"group": "seed_holdout", "family": "gen_fill_holes", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "seed_holdout", "family": "gen_conditional_transform", "surface": "symbolic", "exact": false, "generated_bytes": 41, "target_bytes": 40}, {"group": "seed_holdout", "family": "gen_two_rule_comp", "surface": "symbolic", "exact": true, "generated_bytes": 29, "target_bytes": 29}, {"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": 13, "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.1791300814.0c9d201b-2dbc-40fb-b739-4ee2350a0f54-7b2tx.840.0.1791300814123050567-72be911d CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c2d1512c1bd013ba7d76f52dbb0f0d0290881c2e8858e6637f1ec053509784c
3
- size 852846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5125e25765136ed2d0ddde5749f147149ea0d41f6b2e1e0cec7e278015c8d331
3
+ size 853629