Upload stage3/bird/codet5-base/run_1/eval_metrics.json with huggingface_hub
Browse files
stage3/bird/codet5-base/run_1/eval_metrics.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "codet5-base",
|
| 3 |
+
"dataset": "bird",
|
| 4 |
+
"stage": "stage3",
|
| 5 |
+
"run": 1,
|
| 6 |
+
"checkpoint": "stage3/bird/codet5-base/run_1/epoch-11-em0_1037",
|
| 7 |
+
"eval_beams": 4,
|
| 8 |
+
"n_samples": 1534,
|
| 9 |
+
"em_raw": 0.0958,
|
| 10 |
+
"em_norm": 0.0991,
|
| 11 |
+
"ex": 0.2269,
|
| 12 |
+
"ex_errors": 683,
|
| 13 |
+
"ex_missing_db": 0,
|
| 14 |
+
"valid_sql_rate": 0.5548,
|
| 15 |
+
"table_precision": 0.8985,
|
| 16 |
+
"table_recall": 0.8526,
|
| 17 |
+
"table_f1": 0.8577,
|
| 18 |
+
"by_difficulty": {
|
| 19 |
+
"simple": {
|
| 20 |
+
"total": 925,
|
| 21 |
+
"em_norm": 0.1524,
|
| 22 |
+
"ex": 0.2865
|
| 23 |
+
},
|
| 24 |
+
"moderate": {
|
| 25 |
+
"total": 464,
|
| 26 |
+
"em_norm": 0.0237,
|
| 27 |
+
"ex": 0.1509
|
| 28 |
+
},
|
| 29 |
+
"challenging": {
|
| 30 |
+
"total": 145,
|
| 31 |
+
"em_norm": 0.0,
|
| 32 |
+
"ex": 0.0897
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"by_sql_type": {
|
| 36 |
+
"ORDER_BY": {
|
| 37 |
+
"total": 305,
|
| 38 |
+
"em_norm": 0.0787,
|
| 39 |
+
"ex": 0.1934
|
| 40 |
+
},
|
| 41 |
+
"LIMIT": {
|
| 42 |
+
"total": 293,
|
| 43 |
+
"em_norm": 0.0819,
|
| 44 |
+
"ex": 0.198
|
| 45 |
+
},
|
| 46 |
+
"JOIN": {
|
| 47 |
+
"total": 1140,
|
| 48 |
+
"em_norm": 0.0675,
|
| 49 |
+
"ex": 0.2053
|
| 50 |
+
},
|
| 51 |
+
"AGGREGATION": {
|
| 52 |
+
"total": 659,
|
| 53 |
+
"em_norm": 0.0728,
|
| 54 |
+
"ex": 0.2367
|
| 55 |
+
},
|
| 56 |
+
"NESTED": {
|
| 57 |
+
"total": 118,
|
| 58 |
+
"em_norm": 0.0254,
|
| 59 |
+
"ex": 0.1441
|
| 60 |
+
},
|
| 61 |
+
"GROUP_BY": {
|
| 62 |
+
"total": 120,
|
| 63 |
+
"em_norm": 0.0167,
|
| 64 |
+
"ex": 0.1333
|
| 65 |
+
},
|
| 66 |
+
"HAVING": {
|
| 67 |
+
"total": 21,
|
| 68 |
+
"em_norm": 0.0,
|
| 69 |
+
"ex": 0.1429
|
| 70 |
+
},
|
| 71 |
+
"SIMPLE": {
|
| 72 |
+
"total": 119,
|
| 73 |
+
"em_norm": 0.2773,
|
| 74 |
+
"ex": 0.2773
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"error_types": {
|
| 78 |
+
"WRONG_TABLE": 651,
|
| 79 |
+
"OTHER": 152,
|
| 80 |
+
"MISSING_ORDER_BY": 20,
|
| 81 |
+
"WRONG_COLUMNS": 358,
|
| 82 |
+
"MISSING_JOIN": 86,
|
| 83 |
+
"MISSING_GROUP_BY": 27,
|
| 84 |
+
"EXTRA_JOIN": 60,
|
| 85 |
+
"MISSING_WHERE": 28
|
| 86 |
+
}
|
| 87 |
+
}
|