diff --git a/pkgs/development/python-modules/torcheval/default.nix b/pkgs/development/python-modules/torcheval/default.nix index aac1a987bf32..d3ffd678a761 100644 --- a/pkgs/development/python-modules/torcheval/default.nix +++ b/pkgs/development/python-modules/torcheval/default.nix @@ -136,6 +136,54 @@ buildPythonPackage { # -- tests/metrics/test_toolkit.py -- "tests/metrics/test_toolkit.py::MetricToolkitTest::test_metric_sync" "tests/metrics/test_toolkit.py::MetricCollectionToolkitTest::test_metric_collection_sync" + + # Cannot access local process over IPv6 (nodename nor servname provided) even with __darwinAllowLocalNetworking + # Will hang, or appear to hang, with an 5 minute (default) timeout per test + "tests/metrics/aggregation/test_auc.py" + "tests/metrics/aggregation/test_cat.py" + "tests/metrics/aggregation/test_max.py" + "tests/metrics/aggregation/test_mean.py" + "tests/metrics/aggregation/test_min.py" + "tests/metrics/aggregation/test_sum.py" + "tests/metrics/aggregation/test_throughput.py" + "tests/metrics/classification/test_accuracy.py" + "tests/metrics/classification/test_auprc.py" + "tests/metrics/classification/test_auroc.py" + "tests/metrics/classification/test_binned_auprc.py" + "tests/metrics/classification/test_binned_auroc.py" + "tests/metrics/classification/test_binned_precision_recall_curve.py" + "tests/metrics/classification/test_confusion_matrix.py" + "tests/metrics/classification/test_f1_score.py" + "tests/metrics/classification/test_normalized_entropy.py" + "tests/metrics/classification/test_precision_recall_curve.py" + "tests/metrics/classification/test_precision.py" + "tests/metrics/classification/test_recall_at_fixed_precision.py" + "tests/metrics/classification/test_recall.py" + "tests/metrics/functional/classification/test_auroc.py" + "tests/metrics/ranking/test_click_through_rate.py::TestClickThroughRate::test_ctr_with_valid_input" + "tests/metrics/ranking/test_hit_rate.py::TestHitRate::test_hitrate_with_valid_input" + "tests/metrics/ranking/test_reciprocal_rank.py::TestReciprocalRank::test_mrr_with_valid_input" + "tests/metrics/ranking/test_retrieval_precision.py::TestRetrievalPrecision::test_retrieval_precision_multiple_updates_1_query" + "tests/metrics/ranking/test_retrieval_precision.py::TestRetrievalPrecision::test_retrieval_precision_multiple_updates_n_queries_without_nan" + "tests/metrics/ranking/test_weighted_calibration.py::TestWeightedCalibration::test_weighted_calibration_with_valid_input" + "tests/metrics/regression/test_mean_squared_error.py" + "tests/metrics/regression/test_r2_score.py" + "tests/metrics/test_synclib.py::SynclibTest::test_gather_uneven_multidim" + "tests/metrics/test_synclib.py::SynclibTest::test_gather_uneven" + "tests/metrics/test_synclib.py::SynclibTest::test_numeric_sync_state" + "tests/metrics/test_synclib.py::SynclibTest::test_sync_list_length" + "tests/metrics/text/test_bleu.py::TestBleu::test_bleu_multiple_examples_per_update" + "tests/metrics/text/test_bleu.py::TestBleu::test_bleu_multiple_updates" + "tests/metrics/text/test_perplexity.py::TestPerplexity::test_perplexity_with_ignore_index" + "tests/metrics/text/test_perplexity.py::TestPerplexity::test_perplexity" + "tests/metrics/text/test_word_error_rate.py::TestWordErrorRate::test_word_error_rate_with_valid_input" + "tests/metrics/text/test_word_information_lost.py::TestWordInformationLost::test_word_information_lost" + "tests/metrics/text/test_word_information_preserved.py::TestWordInformationPreserved::test_word_information_preserved_with_valid_input" + "tests/metrics/window/test_auroc.py" + "tests/metrics/window/test_click_through_rate.py::TestClickThroughRate::test_ctr_with_valid_input" + "tests/metrics/window/test_mean_squared_error.py" + "tests/metrics/window/test_normalized_entropy.py::TestWindowedBinaryNormalizedEntropy::test_ne_with_valid_input" + "tests/metrics/window/test_weighted_calibration.py::TestWindowedWeightedCalibration::test_weighted_calibration_with_valid_input" ]; meta = {