Upload stage3/bird/t5-base/run_1/eval_metrics.json with huggingface_hub
Browse files
stage3/bird/t5-base/run_1/eval_metrics.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "t5-base",
|
| 3 |
+
"dataset": "bird",
|
| 4 |
+
"stage": "stage3",
|
| 5 |
+
"run": 1,
|
| 6 |
+
"checkpoint": "stage3/bird/t5-base/run_1/epoch-12-em0_0495",
|
| 7 |
+
"eval_beams": 4,
|
| 8 |
+
"n_samples": 1534,
|
| 9 |
+
"em_raw": 0.0567,
|
| 10 |
+
"em_norm": 0.058,
|
| 11 |
+
"ex": 0.1362,
|
| 12 |
+
"ex_errors": 1006,
|
| 13 |
+
"ex_missing_db": 0,
|
| 14 |
+
"valid_sql_rate": 0.3442,
|
| 15 |
+
"table_precision": 0.7864,
|
| 16 |
+
"table_recall": 0.7664,
|
| 17 |
+
"table_f1": 0.7528,
|
| 18 |
+
"by_difficulty": {
|
| 19 |
+
"simple": {
|
| 20 |
+
"total": 925,
|
| 21 |
+
"em_norm": 0.0908,
|
| 22 |
+
"ex": 0.187
|
| 23 |
+
},
|
| 24 |
+
"moderate": {
|
| 25 |
+
"total": 464,
|
| 26 |
+
"em_norm": 0.0065,
|
| 27 |
+
"ex": 0.0582
|
| 28 |
+
},
|
| 29 |
+
"challenging": {
|
| 30 |
+
"total": 145,
|
| 31 |
+
"em_norm": 0.0138,
|
| 32 |
+
"ex": 0.0621
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"by_sql_type": {
|
| 36 |
+
"ORDER_BY": {
|
| 37 |
+
"total": 305,
|
| 38 |
+
"em_norm": 0.0623,
|
| 39 |
+
"ex": 0.1541
|
| 40 |
+
},
|
| 41 |
+
"LIMIT": {
|
| 42 |
+
"total": 293,
|
| 43 |
+
"em_norm": 0.0683,
|
| 44 |
+
"ex": 0.1638
|
| 45 |
+
},
|
| 46 |
+
"JOIN": {
|
| 47 |
+
"total": 1140,
|
| 48 |
+
"em_norm": 0.043,
|
| 49 |
+
"ex": 0.1132
|
| 50 |
+
},
|
| 51 |
+
"AGGREGATION": {
|
| 52 |
+
"total": 659,
|
| 53 |
+
"em_norm": 0.044,
|
| 54 |
+
"ex": 0.1442
|
| 55 |
+
},
|
| 56 |
+
"NESTED": {
|
| 57 |
+
"total": 118,
|
| 58 |
+
"em_norm": 0.0254,
|
| 59 |
+
"ex": 0.161
|
| 60 |
+
},
|
| 61 |
+
"GROUP_BY": {
|
| 62 |
+
"total": 120,
|
| 63 |
+
"em_norm": 0.0333,
|
| 64 |
+
"ex": 0.125
|
| 65 |
+
},
|
| 66 |
+
"HAVING": {
|
| 67 |
+
"total": 21,
|
| 68 |
+
"em_norm": 0.0476,
|
| 69 |
+
"ex": 0.0476
|
| 70 |
+
},
|
| 71 |
+
"SIMPLE": {
|
| 72 |
+
"total": 119,
|
| 73 |
+
"em_norm": 0.1261,
|
| 74 |
+
"ex": 0.1849
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"error_types": {
|
| 78 |
+
"WRONG_TABLE": 670,
|
| 79 |
+
"OTHER": 443,
|
| 80 |
+
"MISSING_JOIN": 97,
|
| 81 |
+
"MISSING_GROUP_BY": 23,
|
| 82 |
+
"MISSING_ORDER_BY": 15,
|
| 83 |
+
"MISSING_WHERE": 19,
|
| 84 |
+
"EXTRA_JOIN": 178
|
| 85 |
+
}
|
| 86 |
+
}
|