{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false }, "collected_at": "2026-05-18T13:24:59.836130+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "eval.tests.test_autotune.TestAutotune.test_autotune_invalid_metric", "eval.tests.test_error_handling.TestArgumentValidation.test_quantize_with_unsupported_model_type", "eval.tests.test_training.TestSupervisedTraining.test_supervised_invalid_loss_shows_error", "eval.tests.test_quantize_dump.TestQuantize.test_quantize_creates_ftz_file", "eval.tests.test_training.TestSupervisedTraining.test_supervised_help_flag", "eval.tests.test_training.TestTrainingArguments.test_ova_loss_function", "eval.tests.test_autotune.test_autotune_with_f1_label_metric_optimizes_per_label", "eval.tests.test_autotune.test_autotune_invalid_metric_name_fails_with_clear_error", "eval.tests.test_autotune.test_autotune_invalid_label_in_metric_fails_at_runtime", "eval.tests.test_autotune.test_autotune_with_different_modelsize_units", "eval.tests.test_autotune.test_autotune_missing_validation_file_fails_with_clear_error", "eval.tests.test_autotune.test_autotune_with_label_precision_at_recall_metric", "eval.tests.test_autotune.test_autotune_zero_duration_fails_with_timeout_error", "eval.tests.test_autotune.test_autotune_modelsize_constraint_creates_quantized_ftz_model", "eval.tests.test_autotune.test_autotune_invalid_modelsize_format_fails_at_parse_time", "eval.tests.test_autotune.test_autotune_with_predictions_parameter_affects_evaluation", "eval.tests.test_autotune.test_autotune_precision_at_recall_metric_optimizes_correctly", "eval.tests.test_autotune.test_autotune_empty_validation_file_produces_nan_scores", "eval.tests.test_autotune.test_autotune_recall_at_precision_metric_works", "eval.tests.test_autotune.test_autotune_basic_f1_metric_runs_trials_and_creates_model", "eval.tests.test_errors_edge_cases.test_empty_training_file_throws_empty_vocabulary_error", "eval.tests.test_autotune.test_autotune_best_score_improves_or_stays_constant", "eval.tests.test_autotune.test_autotune_with_wordngrams_flag_warns_not_optimized", "eval.tests.test_autotune.test_autotune_creates_final_model_with_best_hyperparameters", "eval.tests.test_autotune.test_autotune_progress_percentage_increases_monotonically", "eval.tests.test_autotune.test_autotune_trial_count_increases_during_optimization", "eval.tests.test_autotune.test_autotune_manually_set_hyperparameters_not_optimized", "eval.tests.test_autotune.test_autotune_very_small_modelsize_constraint_fails_or_times_out", "eval.tests.test_autotune.test_autotune_with_epoch_flag_warns_not_optimized", "eval.tests.test_errors_edge_cases.test_read_only_output_directory_error", "eval.tests.test_autotune.test_autotune_with_multiple_metrics_produces_different_models", "eval.tests.test_errors_edge_cases.test_test_command_with_mismatched_labels", "eval.tests.test_harvest.test_quantization_workflow", "eval.tests.test_model_io.test_bin_file_is_binary_format", "eval.tests.test_errors_edge_cases.test_invalid_loss_function_name_shows_valid_options", "eval.tests.test_errors_edge_cases.test_dimension_zero_trains_without_crash", "eval.tests.test_predict_eval.test_test_label_per_label_metrics", "eval.tests.test_errors_edge_cases.test_learning_rate_zero_trains_without_crash", "eval.tests.test_predict_eval.test_predict_prob_k_parameter", "eval.tests.test_errors_edge_cases.test_nn_command_with_zero_k_parameter", "eval.tests.test_quantize_dump.test_quantized_model_still_makes_predictions", "eval.tests.test_quantize_dump.test_dump_args_shows_training_configuration", "eval.tests.test_quantize_dump.test_dump_input_shows_input_matrix", "eval.tests.test_quantize_dump.test_dump_quantized_model_input_not_supported", "eval.tests.test_quantize_dump.test_quantize_basic_creates_ftz_file", "eval.tests.test_quantize_dump.test_dump_quantized_model_output_not_supported", "eval.tests.test_quantize_dump.test_quantize_with_qnorm_option", "eval.tests.test_model_io.test_model_metadata_in_dump_output", "eval.tests.test_quantize_dump.test_dump_dict_format_with_special_token", "eval.tests.test_quantize_dump.test_quantize_different_dsub_values", "eval.tests.test_quantize_dump.test_quantize_retrain_option_with_cutoff", "eval.tests.test_quantize_dump.test_quantize_cutoff_option_prunes_vocabulary", "eval.tests.test_quantize_dump.test_quantize_preserves_model_args", "eval.tests.test_quantize_dump.test_dump_dict_shows_vocabulary", "eval.tests.test_quantize_dump.test_dump_output_shows_output_matrix", "eval.tests.test_quantize_dump.test_dump_quantized_model_args_dict_work", "eval.tests.test_quantize_dump.test_quantize_creates_new_file_preserves_original", "eval.tests.test_training.test_skipgram_with_character_ngrams", "eval.tests.test_vectors_queries.test_analogies_basic@analogies_serial", "eval.tests.test_training.test_cbow_with_character_ngrams", "eval.tests.test_quantize_dump.test_quantize_with_qnorm_and_dsub", "eval.tests.test_vectors_queries.test_print_word_vectors_oov_word", "eval.tests.test_quantize_dump.test_dump_output_matrix_row_count_matches_labels", "eval.tests.test_vectors_queries.test_print_ngrams_basic", "eval.tests.test_training.test_supervised_with_learning_rate_variations", "eval.tests.test_vectors_queries.test_print_sentence_vectors_single_word", "eval.tests.test_vectors_queries.test_print_sentence_vectors_basic", "eval.tests.test_quantize_dump.test_quantize_only_works_on_supervised_models", "eval.tests.test_quantize_dump.test_dump_input_matrix_dimensions_match_words", "eval.tests.test_quantize_dump.test_dump_all_options_on_bin_model", "eval.tests.test_quantize_dump.test_quantize_then_test_accuracy_reasonable", "eval.tests.test_vectors_queries.test_print_word_vectors_multiword_input", "eval.tests.test_vectors_queries.test_print_sentence_vectors_empty_line", "eval.tests.test_vectors_queries.test_nn_oov_query", "eval.tests.test_vectors_queries.test_analogies_invalid_k", "eval.tests.test_vectors_queries.test_print_word_vectors_empty_input", "eval.tests.test_vectors_queries.test_nn_default_k", "eval.tests.test_vectors_queries.test_print_ngrams_short_word", "eval.tests.test_vectors_queries.test_nn_basic_query", "eval.tests.test_vectors_queries.test_print_word_vectors_basic" ], "failed_tests_omitted": 6, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": {}, "test_records": 352, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "instance_id": "facebookresearch__fasttext.1142dc4", "metrics": { "almost_resolved": "False", "cached_input_tokens": "4376576", "calls": "88", "created_at": "2026-05-17T11:01:28.860108+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "4.2970", "evaluator_problem": "False", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "input_tokens": "4558870", "instance_id": "facebookresearch__fasttext.1142dc4", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "247", "n_system_errors": "0", "n_tests": "312", "n_warnings": "0", "output_tokens": "39908", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "12857", "resolved": "False", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-facebookresearch-fasttext", "run_version": "", "score": "0.7916666666666666", "session_ended_at": "2026-05-17T11:17:02.147Z", "session_started_at": "2026-05-17T11:01:31.694Z", "test_branch_errors": "{}", "total_tokens": "4598778", "wall_clock_seconds": "930" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./compile.sh", "./executable", "./fasttext_compat.py" ], "contents_omitted": 0, "submission_available_local_only": true }, "paper_compliant": false, "paper_mode": false, "reasoning_effort": "xhigh", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-facebookresearch-fasttext", "run_version": "", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }