{ "artifacts": { "calibration.jsonl": { "rows": 4096, "sha256": "ee9edaf80a6854c18053b96521090a51bdb76642abeb98618d7aed36e70b6de9" }, "duplicates.jsonl": { "rows": 1401, "sha256": "2ddc5b1b0eaadffd9b9e7b7556f4a756c6d0b0857a509236ae3e090a9d17ad16" }, "test.jsonl": { "rows": 6995, "sha256": "9ed10842a12132b6bfb5421df1e2f88dbcfbf6f6e960f36b22eb9ea6e3c72315" }, "train.jsonl": { "rows": 42626, "sha256": "426ebfaad34b14d7627ba6e668ae36e08e548c9d057b0edc208bcfa6fe527629" }, "validation.jsonl": { "rows": 5319, "sha256": "9ac88b3138de4ca94c2ef3a87ccf19381fc76265c2bc9d65b4791983d0315096" } }, "codesearchnet": { "languages": [ "go", "java", "javascript", "php", "python", "ruby" ], "local_root": "/Users/kearm/datasets/calibrated-code-embeddings/code-search-net", "repository": "code-search-net/code_search_net", "revision": "bd0cf261e357a3eb5c8fba490d23ec1a1cd59555" }, "configuration": { "calibration_rows": 4096, "calibration_sampling": "deterministic_language_round_robin_v2", "evaluation_precedence_during_dedup": [ "test", "validation", "train" ], "near_duplicate_threshold": 0.82, "ngram_size": 8, "per_repo_language": 3000, "test": 750, "train": 6000, "validation": 750 }, "counts": { "test/c/pinned_repository": 95, "test/cpp/pinned_repository": 750, "test/cuda/pinned_repository": 1, "test/go/codesearchnet": 750, "test/java/codesearchnet": 268, "test/java/pinned_repository": 482, "test/javascript/codesearchnet": 332, "test/javascript/pinned_repository": 418, "test/php/codesearchnet": 750, "test/python/codesearchnet": 631, "test/python/pinned_repository": 119, "test/ruby/codesearchnet": 750, "test/rust/pinned_repository": 750, "test/shell/pinned_repository": 6, "test/swift/pinned_repository": 1, "test/toml/pinned_repository": 129, "test/typescript/pinned_repository": 750, "test/yaml/pinned_repository": 13, "train/c/pinned_repository": 389, "train/cpp/pinned_repository": 268, "train/cuda/pinned_repository": 1, "train/go/codesearchnet": 6000, "train/java/codesearchnet": 6000, "train/javascript/codesearchnet": 4939, "train/javascript/pinned_repository": 1061, "train/php/codesearchnet": 6000, "train/python/codesearchnet": 5984, "train/python/pinned_repository": 16, "train/ruby/codesearchnet": 6000, "train/rust/pinned_repository": 2980, "train/shell/pinned_repository": 2, "train/toml/pinned_repository": 21, "train/typescript/pinned_repository": 2945, "train/yaml/pinned_repository": 20, "validation/go/codesearchnet": 561, "validation/go/pinned_repository": 189, "validation/java/codesearchnet": 750, "validation/javascript/codesearchnet": 580, "validation/javascript/pinned_repository": 170, "validation/php/codesearchnet": 750, "validation/python/codesearchnet": 590, "validation/python/pinned_repository": 160, "validation/ruby/codesearchnet": 750, "validation/toml/pinned_repository": 8, "validation/typescript/pinned_repository": 750, "validation/yaml/pinned_repository": 61 }, "input_pairs": 118039, "local_source": "/Users/kearm/datasets/calibrated-code-embeddings/source-repos", "repo_manifest": "/Users/kearm/AlphaHENG/contrib/calibrated-code-embeddings/sources/repos.json", "schema_version": 1, "selected_pairs": 54940, "unique_pairs": 116638 }