Mukul Rayana
Add conversation memory, fix Gradio stack, improve SYSTEM_PROMPT, log human eval turns
15920d0 | { | |
| "mean_precision": 0.8074, | |
| "mean_recall": 0.8469, | |
| "mean_f1": 0.8266, | |
| "target": 0.72, | |
| "pass": true, | |
| "n_evaluated": 50, | |
| "n_skipped": 0, | |
| "per_prompt": [ | |
| { | |
| "prompt_id": "d01", | |
| "f1": 0.8284, | |
| "precision": 0.8111, | |
| "recall": 0.8465 | |
| }, | |
| { | |
| "prompt_id": "d02", | |
| "f1": 0.8305, | |
| "precision": 0.8167, | |
| "recall": 0.8447 | |
| }, | |
| { | |
| "prompt_id": "d03", | |
| "f1": 0.8158, | |
| "precision": 0.8077, | |
| "recall": 0.8241 | |
| }, | |
| { | |
| "prompt_id": "d04", | |
| "f1": 0.8302, | |
| "precision": 0.8085, | |
| "recall": 0.8531 | |
| }, | |
| { | |
| "prompt_id": "d05", | |
| "f1": 0.8302, | |
| "precision": 0.8104, | |
| "recall": 0.851 | |
| }, | |
| { | |
| "prompt_id": "d06", | |
| "f1": 0.8468, | |
| "precision": 0.8238, | |
| "recall": 0.8711 | |
| }, | |
| { | |
| "prompt_id": "d07", | |
| "f1": 0.8198, | |
| "precision": 0.805, | |
| "recall": 0.8351 | |
| }, | |
| { | |
| "prompt_id": "d08", | |
| "f1": 0.8247, | |
| "precision": 0.8091, | |
| "recall": 0.8408 | |
| }, | |
| { | |
| "prompt_id": "d09", | |
| "f1": 0.8389, | |
| "precision": 0.8113, | |
| "recall": 0.8684 | |
| }, | |
| { | |
| "prompt_id": "d10", | |
| "f1": 0.8184, | |
| "precision": 0.8081, | |
| "recall": 0.829 | |
| }, | |
| { | |
| "prompt_id": "a01", | |
| "f1": 0.8105, | |
| "precision": 0.8055, | |
| "recall": 0.8156 | |
| }, | |
| { | |
| "prompt_id": "a02", | |
| "f1": 0.813, | |
| "precision": 0.8102, | |
| "recall": 0.8158 | |
| }, | |
| { | |
| "prompt_id": "a03", | |
| "f1": 0.8343, | |
| "precision": 0.8141, | |
| "recall": 0.8555 | |
| }, | |
| { | |
| "prompt_id": "a04", | |
| "f1": 0.8291, | |
| "precision": 0.8113, | |
| "recall": 0.8476 | |
| }, | |
| { | |
| "prompt_id": "a05", | |
| "f1": 0.8219, | |
| "precision": 0.8127, | |
| "recall": 0.8313 | |
| }, | |
| { | |
| "prompt_id": "a06", | |
| "f1": 0.8298, | |
| "precision": 0.8211, | |
| "recall": 0.8387 | |
| }, | |
| { | |
| "prompt_id": "a07", | |
| "f1": 0.847, | |
| "precision": 0.8211, | |
| "recall": 0.8746 | |
| }, | |
| { | |
| "prompt_id": "a08", | |
| "f1": 0.8055, | |
| "precision": 0.783, | |
| "recall": 0.8293 | |
| }, | |
| { | |
| "prompt_id": "a09", | |
| "f1": 0.8382, | |
| "precision": 0.8194, | |
| "recall": 0.8579 | |
| }, | |
| { | |
| "prompt_id": "a10", | |
| "f1": 0.8382, | |
| "precision": 0.8194, | |
| "recall": 0.8579 | |
| }, | |
| { | |
| "prompt_id": "f01", | |
| "f1": 0.82, | |
| "precision": 0.8009, | |
| "recall": 0.8401 | |
| }, | |
| { | |
| "prompt_id": "f02", | |
| "f1": 0.825, | |
| "precision": 0.8142, | |
| "recall": 0.836 | |
| }, | |
| { | |
| "prompt_id": "f03", | |
| "f1": 0.8332, | |
| "precision": 0.8084, | |
| "recall": 0.8595 | |
| }, | |
| { | |
| "prompt_id": "f04", | |
| "f1": 0.813, | |
| "precision": 0.8102, | |
| "recall": 0.8158 | |
| }, | |
| { | |
| "prompt_id": "f05", | |
| "f1": 0.819, | |
| "precision": 0.7934, | |
| "recall": 0.8462 | |
| }, | |
| { | |
| "prompt_id": "f06", | |
| "f1": 0.8167, | |
| "precision": 0.7949, | |
| "recall": 0.8397 | |
| }, | |
| { | |
| "prompt_id": "f07", | |
| "f1": 0.8316, | |
| "precision": 0.8077, | |
| "recall": 0.8569 | |
| }, | |
| { | |
| "prompt_id": "f08", | |
| "f1": 0.8144, | |
| "precision": 0.7878, | |
| "recall": 0.8428 | |
| }, | |
| { | |
| "prompt_id": "f09", | |
| "f1": 0.8276, | |
| "precision": 0.8194, | |
| "recall": 0.836 | |
| }, | |
| { | |
| "prompt_id": "f10", | |
| "f1": 0.8198, | |
| "precision": 0.8101, | |
| "recall": 0.8297 | |
| }, | |
| { | |
| "prompt_id": "n01", | |
| "f1": 0.8341, | |
| "precision": 0.7951, | |
| "recall": 0.8771 | |
| }, | |
| { | |
| "prompt_id": "n02", | |
| "f1": 0.8038, | |
| "precision": 0.777, | |
| "recall": 0.8325 | |
| }, | |
| { | |
| "prompt_id": "n03", | |
| "f1": 0.8074, | |
| "precision": 0.788, | |
| "recall": 0.8279 | |
| }, | |
| { | |
| "prompt_id": "n04", | |
| "f1": 0.8328, | |
| "precision": 0.795, | |
| "recall": 0.8744 | |
| }, | |
| { | |
| "prompt_id": "n05", | |
| "f1": 0.7861, | |
| "precision": 0.768, | |
| "recall": 0.8051 | |
| }, | |
| { | |
| "prompt_id": "n06", | |
| "f1": 0.8336, | |
| "precision": 0.8076, | |
| "recall": 0.8614 | |
| }, | |
| { | |
| "prompt_id": "n07", | |
| "f1": 0.8071, | |
| "precision": 0.7869, | |
| "recall": 0.8285 | |
| }, | |
| { | |
| "prompt_id": "n08", | |
| "f1": 0.8011, | |
| "precision": 0.7939, | |
| "recall": 0.8085 | |
| }, | |
| { | |
| "prompt_id": "n09", | |
| "f1": 0.8321, | |
| "precision": 0.8052, | |
| "recall": 0.8609 | |
| }, | |
| { | |
| "prompt_id": "n10", | |
| "f1": 0.8337, | |
| "precision": 0.8108, | |
| "recall": 0.8578 | |
| }, | |
| { | |
| "prompt_id": "h01", | |
| "f1": 0.8436, | |
| "precision": 0.8268, | |
| "recall": 0.8612 | |
| }, | |
| { | |
| "prompt_id": "h02", | |
| "f1": 0.8419, | |
| "precision": 0.813, | |
| "recall": 0.8729 | |
| }, | |
| { | |
| "prompt_id": "h03", | |
| "f1": 0.8342, | |
| "precision": 0.8128, | |
| "recall": 0.8567 | |
| }, | |
| { | |
| "prompt_id": "h04", | |
| "f1": 0.8415, | |
| "precision": 0.8158, | |
| "recall": 0.8689 | |
| }, | |
| { | |
| "prompt_id": "h05", | |
| "f1": 0.8396, | |
| "precision": 0.8188, | |
| "recall": 0.8614 | |
| }, | |
| { | |
| "prompt_id": "h06", | |
| "f1": 0.8296, | |
| "precision": 0.8308, | |
| "recall": 0.8284 | |
| }, | |
| { | |
| "prompt_id": "h07", | |
| "f1": 0.8432, | |
| "precision": 0.8197, | |
| "recall": 0.8682 | |
| }, | |
| { | |
| "prompt_id": "h08", | |
| "f1": 0.8367, | |
| "precision": 0.8078, | |
| "recall": 0.8678 | |
| }, | |
| { | |
| "prompt_id": "h09", | |
| "f1": 0.8332, | |
| "precision": 0.8084, | |
| "recall": 0.8595 | |
| }, | |
| { | |
| "prompt_id": "h10", | |
| "f1": 0.8419, | |
| "precision": 0.813, | |
| "recall": 0.8729 | |
| } | |
| ] | |
| } |