{ "model_details": { "provider": "e-infra", "model_requested": "glm-5", "model_for_requests": "glm-5", "api_base_url": "https://llm.ai.e-infra.cz/v1", "chat_completions_endpoint": "https://llm.ai.e-infra.cz/v1/chat/completions" }, "run_config": { "input": [ "data/input/OE_number.csv" ], "labels": "", "task_name": "OE number", "task_description": "Determining grammatical number (sg./pl.) in Old English nouns.", "tags": "open source;Old English;morphology;number", "model": "glm-5", "temperature": null, "top_p": null, "top_k": null, "service_tier": "standard", "verbosity": null, "reasoning_effort": null, "thinking_level": null, "effort": null, "strict_control_acceptance": true, "provider": "e-infra", "system_prompt": "You are a historical linguist working on a meticulous classification of grammatical number in Old English nouns. Classify each noun as either singular or plural.\nYou will base your analysis mostly on the noun's morphology and grammatical agreement with other elements in the provided context. Only if these are inconclusive, you can also consider the overall meaning as well as the putative source (e.g. Latin original) and broader context.", "system_prompt_b64": null, "few_shot_examples": 0, "prompt_layout": "standard", "cache_pad_target_tokens": 0, "prompt_cache_key": null, "gemini_cached_content": null, "requesty_auto_cache": null, "vertex_auto_adc_login": null, "vertex_access_token_refresh_seconds": null, "create_gemini_cache": false, "gemini_cache_ttl": 3600, "gemini_cache_ttl_autoupdate": true, "keep_gemini_cache": false, "enable_cot": true, "no_explanation": false, "logprobs": true, "calibration": true, "confusion_heatmap": true, "api_key_var": "E-INFRA_API_KEY", "api_base_var": "E-INFRA_BASE_URL", "max_retries": 3, "retry_delay": 5.0, "request_interval_ms": 0, "request_timeout_seconds": 600.0, "threads": 1, "prompt_log_detail": "full", "flush_rows": 100, "flush_seconds": 2.0, "validator_cmd": null, "validator_args": "", "validator_timeout": 5.0, "validator_prompt_max_candidates": 50, "validator_prompt_max_chars": 8000, "validator_exhausted_policy": "accept_blank_confidence", "validator_debug": false, "log_level": "INFO" }, "source_input_csv": "data/input/OE_number.csv", "source_output_csv": "data/output/OE_number__einfra__glm5__2026-04-02-01-04.csv", "source_labels_csv": "", "cache_padding": { "enabled": false, "target_shared_prefix_tokens": 0, "calibration_shared_prefix_tokens": null, "target_prompt_tokens": 0, "calibration_prompt_tokens": null, "calibration_example_id": null, "applied_padding_tokens_estimate": 0, "examples_with_padding_applied": 0 }, "request_control_summary": { "configured": {}, "attempts_total": 1362, "attempts_with_control_telemetry": 1209, "per_control": { "reasoning_effort": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "thinking_level": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "effort": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "verbosity": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "prompt_cache_key": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "gemini_cached_content": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] }, "requesty_auto_cache": { "configured_value": null, "requested_attempts": 0, "sent_attempts": 0, "accepted_attempts": 0, "rejected_attempts": 0, "missing_from_final_request_attempts": 0, "acceptance_rate": null, "rejected_reasons": {}, "rejected_example_ids": [] } } }, "usage_metadata_summary": { "attempts_total": 1362, "attempts_with_usage_metadata": 1209, "attempts_with_cached_token_signals": 0, "cached_tokens_total_estimate": 0, "cache_read_tokens_total": 0, "cache_write_tokens_total": 0, "cache_token_fields_totals": {}, "attempts_with_gemini_cached_content_token_signals": 0, "gemini_cached_content_token_count_total": 0, "gemini_cached_content_token_fields_totals": {} }, "token_usage_totals": { "attempts_total": 1362, "attempts_with_token_usage": 1209, "attempts_with_output_tokens": 1209, "attempts_with_cached_input_tokens": 0, "attempts_with_thinking_tokens": 0, "input_tokens_total": 860270, "cached_input_tokens_total": 0, "non_cached_input_tokens_total": 860270, "output_tokens_total": 1578924, "thinking_tokens_total": 0, "output_tokens_definition": "total_tokens - prompt_tokens (or completion_tokens + thinking_tokens fallback)" }, "truth_label_count": 1200, "prediction_count": 1200, "evaluated_example_count": 1200, "calibration_metrics": { "available": true, "sample_count": 1194, "bin_count": 10, "ece": 0.009489112227812572, "mce": 0.17200000000000026, "brier_score": 0.03291314907872695 }, "first_prompt_timestamp": "2026-04-01T23:04:56.944335Z", "last_prompt_timestamp": "2026-04-02T07:10:46.519016Z", "overall_time_seconds": 29149.574681, "overall_time_human": "8h 05m 50s", "accuracy": 0.9641666666666666, "cohen_kappa": 0.8995307541034676, "macro_precision": 0.6309362681784316, "macro_recall": 0.6366261501999548, "macro_f1": 0.6337096356555558, "per_label": { "plural": { "precision": 0.9113475177304965, "recall": 0.9379562043795621, "f1": 0.9244604316546763, "support": 274 }, "singular": { "precision": 0.9814612868047983, "recall": 0.9719222462203023, "f1": 0.9766684753119913, "support": 926 }, "unclassified": { "precision": 0.0, "recall": 0.0, "f1": 0.0, "support": 0 } }, "labels": [ "plural", "singular", "unclassified" ], "label_count": 3, "total_examples": 1200, "confusion_matrix": { "plural": { "plural": 257, "singular": 17, "unclassified": 0 }, "singular": { "plural": 25, "singular": 900, "unclassified": 1 }, "unclassified": { "plural": 0, "singular": 0, "unclassified": 0 } }, "label_metrics_available": true }