Ines-1 / training /data_audit.json
Endikavi's picture
Ines-1 RC1 (private staging; release commit b7f5644)
61b6fb9 verified
Raw History Blame Contribute Delete
9.67 kB
{
"files": {
"s1:typed_train_en": {
"cases": 1084,
"questions": 5420,
"types": {
"choice": 1633,
"noul": 1619,
"score": 2168
},
"groups": 4,
"langs": {
"en": 1084
},
"path": "typed_train_en.jsonl",
"sha256": "3197db6961f706d774147c1ba9eb6d8722d1de0b4f9a0d7be7cef0b5349e51d3"
},
"s1:typed_train_es": {
"cases": 1067,
"questions": 5335,
"types": {
"choice": 1599,
"noul": 1602,
"score": 2134
},
"groups": 4,
"langs": {
"es": 1067
},
"path": "typed_train_es.jsonl",
"sha256": "ebac9d7d37143d78e3f2b4f3b8b1a7f3e30d7d621d01739f803ad0dfe7ca7d04"
},
"s1:jev_train": {
"cases": 9478,
"questions": 9478,
"types": {
"choice": 9478
},
"groups": 3,
"langs": {
"en": 9478
},
"path": "jev_train.jsonl",
"sha256": "eb1d4adc0a6512adfe9f7e8de2d8e52c8d2366d75ea6bbfb952df285e4bc6812"
},
"val:typed_val_en": {
"cases": 116,
"questions": 580,
"types": {
"choice": 167,
"noul": 181,
"score": 232
},
"groups": 4,
"langs": {
"en": 116
},
"path": "typed_val_en.jsonl",
"sha256": "9f682d98e305a151dd69062506f0070a9ecb48e93620c41613fb5b0a276418ba"
},
"val:typed_val_es": {
"cases": 115,
"questions": 575,
"types": {
"choice": 165,
"noul": 180,
"score": 230
},
"groups": 4,
"langs": {
"es": 115
},
"path": "typed_val_es.jsonl",
"sha256": "8dc112f8535b2cefbb9a0b0385e3677a36a29a8adedae4419aeabb5f11dd4565"
},
"val:jev_val": {
"cases": 522,
"questions": 522,
"types": {
"choice": 522
},
"groups": 3,
"langs": {
"en": 522
},
"path": "jev_val.jsonl",
"sha256": "1e29ba65acad8fe2050890c27dc12f8f46818d51684e5d678f4c3a1dcbf2bd21"
},
"s2:train_helmo": {
"cases": 9408,
"questions": 9408,
"types": {
"noul": 3131,
"score": 3151,
"choice": 3126
},
"groups": 207,
"langs": {
"en": 9408
},
"path": "train_helmo.jsonl",
"sha256": "5dd10b18b9a2e71dfe748f2d395e7e84dca726332625e7e71552c9358a7e7548"
},
"s2:train_jev": {
"cases": 17898,
"questions": 17898,
"types": {
"choice": 17898
},
"groups": 3,
"langs": {
"en": 17898
},
"path": "train_jev.jsonl",
"sha256": "6250700107ad14cd7a8e56443eb3b977fbc40a75bee4243167c484c801e2e21c"
},
"s2:train_n4ze3m": {
"cases": 5156,
"questions": 18001,
"types": {
"noul": 7083,
"score": 3812,
"choice": 7106
},
"groups": 149,
"langs": {
"en": 5156
},
"path": "train_n4ze3m.jsonl",
"sha256": "61dc830ccb67deaff81e94ede78deab82b5567d83b508a3769852269fffd3774"
},
"s2:train_tasksource": {
"cases": 24959,
"questions": 24959,
"types": {
"score": 1734,
"noul": 3296,
"choice": 19929
},
"groups": 159,
"langs": {
"en": 24959
},
"path": "train_tasksource.jsonl",
"sha256": "14f3b7169e308746074eacf57edb800f5ec138962a3c88cd73d9b89f0b9851cc"
},
"s2:train_typed_en": {
"cases": 1084,
"questions": 5420,
"types": {
"choice": 1633,
"noul": 1619,
"score": 2168
},
"groups": 4,
"langs": {
"en": 1084
},
"path": "train_typed_en.jsonl",
"sha256": "3197db6961f706d774147c1ba9eb6d8722d1de0b4f9a0d7be7cef0b5349e51d3"
},
"s2:train_typed_es": {
"cases": 1067,
"questions": 5335,
"types": {
"choice": 1599,
"noul": 1602,
"score": 2134
},
"groups": 4,
"langs": {
"es": 1067
},
"path": "train_typed_es.jsonl",
"sha256": "ebac9d7d37143d78e3f2b4f3b8b1a7f3e30d7d621d01739f803ad0dfe7ca7d04"
},
"s2:train_typed_es_telepatia": {
"cases": 1083,
"questions": 5415,
"types": {
"choice": 1631,
"noul": 1618,
"score": 2166
},
"groups": 4,
"langs": {
"es": 1083
},
"path": "train_typed_es_telepatia.jsonl",
"sha256": "01b2392ba793d0233b02b727219fa446a942fa73ef2b7ed6c8b28e5f3330ff5e"
},
"val2:val_helmo": {
"cases": 470,
"questions": 470,
"types": {
"choice": 155,
"noul": 162,
"score": 153
},
"groups": 186,
"langs": {
"en": 470
},
"path": "val_helmo.jsonl",
"sha256": "38831c93786961217272c26d264903e5ce5d779777c41da7c1fc390da9f48141"
},
"val2:val_jev": {
"cases": 522,
"questions": 522,
"types": {
"choice": 522
},
"groups": 3,
"langs": {
"en": 522
},
"path": "val_jev.jsonl",
"sha256": "b1c698b2305aeaba225c46ec504b4c7935cde2edd9b05e13834de0d2ad797449"
},
"val2:val_n4ze3m": {
"cases": 426,
"questions": 1500,
"types": {
"choice": 584,
"score": 330,
"noul": 586
},
"groups": 138,
"langs": {
"en": 426
},
"path": "val_n4ze3m.jsonl",
"sha256": "71cf5b53f104e4633cd6db6eb65f369bdd3440bdde6ce14324ce947365494805"
},
"val2:val_tasksource": {
"cases": 1495,
"questions": 1495,
"types": {
"choice": 1261,
"noul": 164,
"score": 70
},
"groups": 159,
"langs": {
"en": 1495
},
"path": "val_tasksource.jsonl",
"sha256": "fd616817f1d967db3b7ef95348b86fff5a1249f8e352ee1fdddf05cf636b99d8"
},
"val2:val_typed_en": {
"cases": 116,
"questions": 580,
"types": {
"choice": 167,
"noul": 181,
"score": 232
},
"groups": 4,
"langs": {
"en": 116
},
"path": "val_typed_en.jsonl",
"sha256": "9f682d98e305a151dd69062506f0070a9ecb48e93620c41613fb5b0a276418ba"
},
"val2:val_typed_es": {
"cases": 115,
"questions": 575,
"types": {
"choice": 165,
"noul": 180,
"score": 230
},
"groups": 4,
"langs": {
"es": 115
},
"path": "val_typed_es.jsonl",
"sha256": "8dc112f8535b2cefbb9a0b0385e3677a36a29a8adedae4419aeabb5f11dd4565"
},
"test:typed_en": {
"cases": 400,
"questions": 2000,
"types": {
"choice": 600,
"noul": 600,
"score": 800
},
"groups": 4,
"langs": {
"en": 400
},
"path": "typed_test_en.jsonl",
"sha256": "a0a60436151b7fd13d53bfbfd848e3a8cd398e31d477a202a49fa6f02394ebab"
},
"test:typed_es": {
"cases": 397,
"questions": 1985,
"types": {
"choice": 594,
"noul": 597,
"score": 794
},
"groups": 4,
"langs": {
"es": 397
},
"path": "typed_test_es.jsonl",
"sha256": "72be4d18b6546e971bb69622d2061ed213772f5c5218e4150d2c58b2eb39e61e"
},
"test:telepatia_es": {
"cases": 400,
"questions": 2000,
"types": {
"choice": 600,
"noul": 600,
"score": 800
},
"groups": 4,
"langs": {
"es": 400
},
"path": "test_telepatia_es.jsonl",
"sha256": "4d9964ec1b83113339b7d09c2e6c03e5cdee3c0c67e6889f6f91f88ee0840435"
},
"test:tasksource": {
"cases": 2206,
"questions": 2206,
"types": {
"choice": 1815,
"noul": 261,
"score": 130
},
"groups": 157,
"langs": {
"en": 2206
},
"path": "test_tasksource.jsonl",
"sha256": "985e0ff6fe335ccb36dcd6c5d9f5de093c094ffaceecea76c708f5557bb24400"
}
},
"overlap_test_vs_train_val": {
"test:tasksource x s2:train_tasksource": {
"pair": 0,
"state": 4,
"fp": 0,
"text": 5
},
"test:tasksource x val2:val_tasksource": {
"pair": 0,
"state": 1,
"fp": 0,
"text": 1
}
},
"tasksource": {
"meta_missing": 0,
"train_sources": 366,
"test_sources": 350,
"test_families": 157,
"test_items": 2206,
"test_items_with": {
"source_in_train": 2206,
"family_in_train": 2206,
"group_in_train": 0,
"question_text_in_train": 2100,
"state_text_in_train": 51
},
"test_sources_not_in_train": [],
"test_variants": {
"direct": 1814,
"packed_derived": 164,
"label_verification": 87,
"instruction_paraphrase": 40,
"criteria_permutation": 80,
"paired_text_format": 21
}
},
"typed_workflows": {
"s1:typed_train_en": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"s1:typed_train_es": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"val:typed_val_en": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"val:typed_val_es": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"s2:train_typed_en": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"s2:train_typed_es": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"s2:train_typed_es_telepatia": [
"telepatia/agent_trace_observability",
"telepatia/customer_service",
"telepatia/invoice_processing",
"telepatia/security_incidents"
],
"val2:val_typed_en": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"val2:val_typed_es": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"test:typed_en": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"test:typed_es": [
"typed/agent_trace_observability",
"typed/customer_service",
"typed/invoice_processing",
"typed/security_incidents"
],
"test:telepatia_es": [
"telepatia/agent_trace_observability",
"telepatia/customer_service",
"telepatia/invoice_processing",
"telepatia/security_incidents"
]
}
}