murabcd's picture
feat: add compiled serving shared training and benchmarks
5adf069 verified
Raw History Blame Contribute Delete
293 kB
[
{
"id": "transfer-v4-0000",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.07,
0.0,
0.93,
0.0
],
"target": 2,
"brier": 0.009799999999999993,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0001",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0002",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0003",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.0,
0.0,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0004",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0005",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0006",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0007",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 1,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0008",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0009",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0010",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0011",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.01,
0.96,
0.0,
0.03
],
"target": 1,
"brier": 0.002600000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0012",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0013",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.55,
"probabilities": [
0.01,
0.01,
0.43,
0.55
],
"target": 2,
"brier": 0.6276000000000002,
"nll": 0.843970070294529
},
{
"id": "transfer-v4-0014",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.0,
0.05,
0.0
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0015",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0016",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0017",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99,
0.0
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0018",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0019",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.73,
"probabilities": [
0.73,
0.18,
0.08,
0.01
],
"target": 0,
"brier": 0.11180000000000001,
"nll": 0.31471074483970024
},
{
"id": "transfer-v4-0020",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0021",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.05,
0.03,
0.9,
0.02
],
"target": 2,
"brier": 0.013799999999999996,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0022",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.9,
0.06,
0.03,
0.01
],
"target": 0,
"brier": 0.014599999999999995,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0023",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0024",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8181818181818181,
"probabilities": [
0.0808080808080808,
0.10101010101010101,
0.0,
0.8181818181818181
],
"target": 3,
"brier": 0.04979083766962557,
"nll": 0.20067069546215124
},
{
"id": "transfer-v4-0025",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.77,
"probabilities": [
0.77,
0.13,
0.08,
0.02
],
"target": 0,
"brier": 0.07659999999999999,
"nll": 0.2613647641344075
},
{
"id": "transfer-v4-0026",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0027",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.02,
0.98,
0.0
],
"target": 2,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0028",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.01,
0.9,
0.08,
0.01
],
"target": 1,
"brier": 0.016599999999999997,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0029",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0030",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0031",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0032",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0033",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.01,
0.99
],
"target": 3,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0034",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.0,
0.0,
0.05,
0.95
],
"target": 3,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0035",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0036",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.77,
"probabilities": [
0.77,
0.18,
0.04,
0.01
],
"target": 0,
"brier": 0.08699999999999998,
"nll": 0.2613647641344075
},
{
"id": "transfer-v4-0037",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.69,
"probabilities": [
0.03,
0.02,
0.26,
0.69
],
"target": 3,
"brier": 0.16500000000000004,
"nll": 0.37106368139083207
},
{
"id": "transfer-v4-0038",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0039",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06,
0.0,
0.0
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0040",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.82,
"probabilities": [
0.02,
0.15,
0.01,
0.82
],
"target": 3,
"brier": 0.05540000000000002,
"nll": 0.19845093872383832
},
{
"id": "transfer-v4-0041",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.77,
"probabilities": [
0.09,
0.03,
0.11,
0.77
],
"target": 3,
"brier": 0.07399999999999998,
"nll": 0.2613647641344075
},
{
"id": "transfer-v4-0042",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.57,
"probabilities": [
0.39,
0.57,
0.03,
0.01
],
"target": 0,
"brier": 0.698,
"nll": 0.941608539858445
},
{
"id": "transfer-v4-0043",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0044",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0045",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.04,
0.03,
0.89,
0.04
],
"target": 2,
"brier": 0.0162,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0046",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0047",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.99,
0.01
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0048",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0049",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.0,
0.99
],
"target": 3,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0050",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0051",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.03,
0.0,
0.52,
0.45
],
"target": 3,
"brier": 0.5738000000000001,
"nll": 0.7985076962177716
},
{
"id": "transfer-v4-0052",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0053",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0054",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.45,
"probabilities": [
0.12,
0.45,
0.35,
0.08
],
"target": 2,
"brier": 0.6458,
"nll": 1.0498221244986778
},
{
"id": "transfer-v4-0055",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.13,
0.08,
0.78,
0.01
],
"target": 2,
"brier": 0.07179999999999999,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0056",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0057",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.01,
0.01,
0.96,
0.02
],
"target": 2,
"brier": 0.0022000000000000027,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0058",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.01,
0.05,
0.92,
0.02
],
"target": 2,
"brier": 0.009399999999999993,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0059",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0060",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.91,
0.0,
0.0,
0.09
],
"target": 0,
"brier": 0.016199999999999992,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0061",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.62,
"probabilities": [
0.04,
0.62,
0.04,
0.3
],
"target": 1,
"brier": 0.2376,
"nll": 0.4780358009429998
},
{
"id": "transfer-v4-0062",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0063",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.01,
0.97,
0.01,
0.01
],
"target": 1,
"brier": 0.0012000000000000016,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0064",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0065",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.82,
"probabilities": [
0.09,
0.08,
0.01,
0.82
],
"target": 3,
"brier": 0.04700000000000002,
"nll": 0.19845093872383832
},
{
"id": "transfer-v4-0066",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0067",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.02,
0.02,
0.02,
0.94
],
"target": 3,
"brier": 0.0048000000000000065,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0068",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.59,
"probabilities": [
0.01,
0.59,
0.01,
0.39
],
"target": 1,
"brier": 0.3204,
"nll": 0.527632742082372
},
{
"id": "transfer-v4-0069",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.02,
0.18,
0.05,
0.75
],
"target": 1,
"brier": 1.2378,
"nll": 1.7147984280919266
},
{
"id": "transfer-v4-0070",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.01,
0.08,
0.9,
0.01
],
"target": 2,
"brier": 0.016599999999999997,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0071",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0072",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.65,
"probabilities": [
0.31,
0.04,
0.65,
0.0
],
"target": 0,
"brier": 0.9002,
"nll": 1.171182981502945
},
{
"id": "transfer-v4-0073",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0074",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.0,
0.99,
0.0
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0075",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0076",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0077",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.49,
"probabilities": [
0.04,
0.46,
0.49,
0.01
],
"target": 2,
"brier": 0.4734,
"nll": 0.7133498878774648
},
{
"id": "transfer-v4-0078",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0079",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0080",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.03,
0.2,
0.75,
0.0,
0.01,
0.01
],
"target": 1,
"brier": 1.2036000000000002,
"nll": 1.6094379124341003
},
{
"id": "transfer-v4-0081",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.78,
"probabilities": [
0.22,
0.0,
0.0,
0.78,
0.0,
0.0
],
"target": 0,
"brier": 1.2168,
"nll": 1.5141277326297755
},
{
"id": "transfer-v4-0082",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0083",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.0,
0.03,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0084",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0085",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.83,
"probabilities": [
0.09,
0.08,
0.0,
0.83,
0.0,
0.0
],
"target": 0,
"brier": 1.5234,
"nll": 2.4079456086518722
},
{
"id": "transfer-v4-0086",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.86,
"probabilities": [
0.0,
0.14,
0.86,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 1.4791999999999998,
"nll": 1.9661128563728327
},
{
"id": "transfer-v4-0087",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0088",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.03,
0.83,
0.14,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.04940000000000001,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0089",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.63,
"probabilities": [
0.63,
0.0,
0.02,
0.0,
0.35,
0.0
],
"target": 0,
"brier": 0.2598,
"nll": 0.4620354595965587
},
{
"id": "transfer-v4-0090",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.0,
0.0,
0.01,
0.03,
0.0
],
"target": 0,
"brier": 0.002600000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0091",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0092",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 1.9602,
"nll": 4.605170185988091
},
{
"id": "transfer-v4-0093",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.31,
"probabilities": [
0.31,
0.28,
0.08,
0.0,
0.06,
0.27
],
"target": 4,
"brier": 1.1374,
"nll": 2.8134107167600364
},
{
"id": "transfer-v4-0094",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.22,
0.0,
0.78,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0968,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0095",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8,
"probabilities": [
0.0,
0.2,
0.8,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.07999999999999999,
"nll": 0.2231435513142097
},
{
"id": "transfer-v4-0096",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0097",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.9,
"probabilities": [
0.9,
0.0,
0.04,
0.04,
0.02,
0.0
],
"target": 3,
"brier": 1.7336,
"nll": 3.2188758248682006
},
{
"id": "transfer-v4-0098",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.98,
"probabilities": [
0.98,
0.0,
0.0,
0.0,
0.02,
0.0
],
"target": 4,
"brier": 1.9207999999999998,
"nll": 3.912023005428146
},
{
"id": "transfer-v4-0099",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0100",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.93,
0.0,
0.0,
0.02,
0.05,
0.0
],
"target": 0,
"brier": 0.007799999999999994,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0101",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.0,
0.97,
0.0,
0.0,
0.0,
0.03
],
"target": 1,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0102",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.0,
0.0,
0.05,
0.0,
0.95,
0.0
],
"target": 4,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0103",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.42,
"probabilities": [
0.29,
0.42,
0.25,
0.01,
0.02,
0.01
],
"target": 0,
"brier": 0.7435999999999999,
"nll": 1.2378743560016174
},
{
"id": "transfer-v4-0104",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.81,
"probabilities": [
0.81,
0.02,
0.01,
0.15,
0.0,
0.01
],
"target": 3,
"brier": 1.3792,
"nll": 1.8971199848858813
},
{
"id": "transfer-v4-0105",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.0,
0.17,
0.83,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0106",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0107",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.83,
0.03,
0.14,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.04940000000000001,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0108",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0109",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.57,
"probabilities": [
0.57,
0.0,
0.0,
0.01,
0.39,
0.03
],
"target": 0,
"brier": 0.338,
"nll": 0.5621189181535413
},
{
"id": "transfer-v4-0110",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0111",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 0,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0112",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.72,
"probabilities": [
0.72,
0.28,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.15680000000000002,
"nll": 0.3285040669720361
},
{
"id": "transfer-v4-0113",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0114",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.41,
"probabilities": [
0.26,
0.41,
0.29,
0.0,
0.03,
0.01
],
"target": 2,
"brier": 0.7408,
"nll": 1.2378743560016174
},
{
"id": "transfer-v4-0115",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0116",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.66,
"probabilities": [
0.66,
0.0,
0.05,
0.0,
0.29,
0.0
],
"target": 1,
"brier": 1.5222,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0117",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.66,
"probabilities": [
0.34,
0.66,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.23120000000000002,
"nll": 0.4155154439616658
},
{
"id": "transfer-v4-0118",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.93,
0.03,
0.0,
0.01,
0.02,
0.01
],
"target": 0,
"brier": 0.0063999999999999925,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0119",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0120",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.79,
"probabilities": [
0.79,
0.0,
0.0,
0.0,
0.21,
0.0
],
"target": 0,
"brier": 0.08819999999999997,
"nll": 0.23572233352106983
},
{
"id": "transfer-v4-0121",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.67,
"probabilities": [
0.0,
0.67,
0.33,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.2178,
"nll": 0.40047756659712525
},
{
"id": "transfer-v4-0122",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.96,
"probabilities": [
0.04,
0.0,
0.0,
0.0,
0.96,
0.0
],
"target": 2,
"brier": 1.9232,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0123",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.98,
0.02,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0124",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.49,
"probabilities": [
0.02,
0.49,
0.48,
0.0,
0.01,
0.0
],
"target": 1,
"brier": 0.491,
"nll": 0.7133498878774648
},
{
"id": "transfer-v4-0125",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.85,
"probabilities": [
0.0,
0.85,
0.15,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.045000000000000005,
"nll": 0.16251892949777494
},
{
"id": "transfer-v4-0126",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.53,
"probabilities": [
0.03,
0.53,
0.44,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.5954,
"nll": 0.8209805520698302
},
{
"id": "transfer-v4-0127",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.0,
0.0,
0.03,
0.0,
0.0
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0128",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5555555555555556,
"probabilities": [
0.5555555555555556,
0.0,
0.0,
0.10101010101010101,
0.2828282828282828,
0.0606060606060606
],
"target": 1,
"brier": 1.4025099479644934,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0129",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0130",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.59,
"probabilities": [
0.41,
0.0,
0.0,
0.59,
0.0,
0.0
],
"target": 0,
"brier": 0.6962,
"nll": 0.8915981192837836
},
{
"id": "transfer-v4-0131",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0132",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0133",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0134",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.0,
0.9,
0.1,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.019999999999999997,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0135",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.52,
0.01,
0.01,
0.12,
0.32,
0.02
],
"target": 4,
"brier": 0.7477999999999999,
"nll": 1.1394342831883648
},
{
"id": "transfer-v4-0136",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.86,
"probabilities": [
0.0,
0.86,
0.14,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.039200000000000006,
"nll": 0.15082288973458366
},
{
"id": "transfer-v4-0137",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.98,
"probabilities": [
0.0,
0.98,
0.0,
0.0,
0.0,
0.02
],
"target": 5,
"brier": 1.9207999999999998,
"nll": 3.912023005428146
},
{
"id": "transfer-v4-0138",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.98,
"probabilities": [
0.98,
0.0,
0.0,
0.02,
0.0,
0.0
],
"target": 1,
"brier": 1.9607999999999999,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0139",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.98,
"probabilities": [
0.0,
0.98,
0.0,
0.0,
0.0,
0.02
],
"target": 2,
"brier": 1.9607999999999999,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0140",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.77,
"probabilities": [
0.0,
0.23,
0.77,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 1.1858,
"nll": 1.4696759700589417
},
{
"id": "transfer-v4-0141",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.72,
"probabilities": [
0.01,
0.72,
0.02,
0.0,
0.24,
0.01
],
"target": 4,
"brier": 1.0966,
"nll": 1.4271163556401458
},
{
"id": "transfer-v4-0142",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.95,
"probabilities": [
0.0,
0.95,
0.05,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 1.805,
"nll": 2.995732273553991
},
{
"id": "transfer-v4-0143",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0144",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.0,
0.0,
0.0,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0145",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0146",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0147",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.64,
"probabilities": [
0.14,
0.64,
0.2,
0.0,
0.02,
0.0
],
"target": 2,
"brier": 1.0696,
"nll": 1.6094379124341003
},
{
"id": "transfer-v4-0148",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.75,
0.03,
0.11,
0.1,
0.01,
0.0
],
"target": 2,
"brier": 1.3656,
"nll": 2.2072749131897207
},
{
"id": "transfer-v4-0149",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8,
"probabilities": [
0.8,
0.0,
0.11,
0.01,
0.08,
0.0
],
"target": 3,
"brier": 1.6386,
"nll": 4.605170185988091
},
{
"id": "transfer-v4-0150",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.0,
0.01,
0.0,
0.99
],
"target": 5,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0151",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.0,
0.0,
0.0,
0.99,
0.0
],
"target": 4,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0152",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0153",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0154",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4,
"probabilities": [
0.4,
0.39,
0.04,
0.02,
0.03,
0.12
],
"target": 1,
"brier": 0.5494,
"nll": 0.941608539858445
},
{
"id": "transfer-v4-0155",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0156",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0157",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.91,
0.0,
0.09,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.016199999999999992,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0158",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.99,
"probabilities": [
0.99,
0.0,
0.0,
0.01,
0.0,
0.0
],
"target": 3,
"brier": 1.9602,
"nll": 4.605170185988091
},
{
"id": "transfer-v4-0159",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.0,
0.01,
0.0,
0.99
],
"target": 5,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0160",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 1,
"brier": 0.0288,
"nll": 0.12783337150988489
},
{
"id": "transfer-v4-0161",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5700000000000001,
"probabilities": [
0.5700000000000001,
0.43
],
"target": 1,
"brier": 0.6498000000000002,
"nll": 0.843970070294529
},
{
"id": "transfer-v4-0162",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0163",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6799999999999999,
"probabilities": [
0.6799999999999999,
0.32
],
"target": 0,
"brier": 0.20480000000000004,
"nll": 0.3856624808119848
},
{
"id": "transfer-v4-0164",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.72,
"probabilities": [
0.28,
0.72
],
"target": 1,
"brier": 0.15680000000000002,
"nll": 0.3285040669720361
},
{
"id": "transfer-v4-0165",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0166",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.74,
"probabilities": [
0.26,
0.74
],
"target": 1,
"brier": 0.13520000000000001,
"nll": 0.3011050927839216
},
{
"id": "transfer-v4-0167",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 1,
"brier": 0.01999999999999999,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0168",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 1,
"brier": 0.0288,
"nll": 0.12783337150988489
},
{
"id": "transfer-v4-0169",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.21999999999999997,
0.78
],
"target": 1,
"brier": 0.09679999999999998,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0170",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.58,
"probabilities": [
0.42000000000000004,
0.58
],
"target": 1,
"brier": 0.35280000000000006,
"nll": 0.5447271754416722
},
{
"id": "transfer-v4-0171",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0172",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.69,
"probabilities": [
0.31000000000000005,
0.69
],
"target": 1,
"brier": 0.19220000000000007,
"nll": 0.37106368139083207
},
{
"id": "transfer-v4-0173",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.72,
"probabilities": [
0.72,
0.28
],
"target": 0,
"brier": 0.15680000000000002,
"nll": 0.3285040669720361
},
{
"id": "transfer-v4-0174",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.17000000000000004,
0.83
],
"target": 1,
"brier": 0.057800000000000025,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0175",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.63,
"probabilities": [
0.63,
0.37
],
"target": 0,
"brier": 0.2738,
"nll": 0.4620354595965587
},
{
"id": "transfer-v4-0176",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 0,
"brier": 1.5488,
"nll": 2.120263536200091
},
{
"id": "transfer-v4-0177",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.61,
"probabilities": [
0.39,
0.61
],
"target": 1,
"brier": 0.3042,
"nll": 0.4942963218147801
},
{
"id": "transfer-v4-0178",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.55,
"probabilities": [
0.55,
0.45
],
"target": 0,
"brier": 0.40499999999999997,
"nll": 0.5978370007556204
},
{
"id": "transfer-v4-0179",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.91,
0.09
],
"target": 0,
"brier": 0.016199999999999992,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0180",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0181",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7,
"probabilities": [
0.7,
0.3
],
"target": 0,
"brier": 0.18000000000000002,
"nll": 0.35667494393873245
},
{
"id": "transfer-v4-0182",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6799999999999999,
"probabilities": [
0.6799999999999999,
0.32
],
"target": 0,
"brier": 0.20480000000000004,
"nll": 0.3856624808119848
},
{
"id": "transfer-v4-0183",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.56,
"probabilities": [
0.43999999999999995,
0.56
],
"target": 0,
"brier": 0.6272000000000001,
"nll": 0.8209805520698303
},
{
"id": "transfer-v4-0184",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.25,
0.75
],
"target": 0,
"brier": 1.125,
"nll": 1.3862943611198906
},
{
"id": "transfer-v4-0185",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.65,
"probabilities": [
0.35,
0.65
],
"target": 0,
"brier": 0.8450000000000001,
"nll": 1.0498221244986778
},
{
"id": "transfer-v4-0186",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.69,
"probabilities": [
0.69,
0.31
],
"target": 0,
"brier": 0.19220000000000004,
"nll": 0.37106368139083207
},
{
"id": "transfer-v4-0187",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.54,
"probabilities": [
0.45999999999999996,
0.54
],
"target": 0,
"brier": 0.5832,
"nll": 0.7765287894989964
},
{
"id": "transfer-v4-0188",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.59,
"probabilities": [
0.41000000000000003,
0.59
],
"target": 0,
"brier": 0.6961999999999999,
"nll": 0.8915981192837835
},
{
"id": "transfer-v4-0189",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.53,
"probabilities": [
0.47,
0.53
],
"target": 0,
"brier": 0.5618000000000001,
"nll": 0.7550225842780328
},
{
"id": "transfer-v4-0190",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.050000000000000044,
0.95
],
"target": 1,
"brier": 0.005000000000000009,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0191",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0192",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 1,
"brier": 1.6928,
"nll": 2.5257286443082556
},
{
"id": "transfer-v4-0193",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6699999999999999,
"probabilities": [
0.6699999999999999,
0.33
],
"target": 0,
"brier": 0.21780000000000005,
"nll": 0.4004775665971254
},
{
"id": "transfer-v4-0194",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.81,
"probabilities": [
0.18999999999999995,
0.81
],
"target": 1,
"brier": 0.07219999999999996,
"nll": 0.21072103131565253
},
{
"id": "transfer-v4-0195",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0196",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0197",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.79,
"probabilities": [
0.79,
0.21
],
"target": 0,
"brier": 0.08819999999999997,
"nll": 0.23572233352106983
},
{
"id": "transfer-v4-0198",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 0,
"brier": 0.012799999999999994,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0199",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0200",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8200000000000001,
"probabilities": [
0.8200000000000001,
0.18
],
"target": 0,
"brier": 0.06479999999999997,
"nll": 0.19845093872383818
},
{
"id": "transfer-v4-0201",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0202",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0203",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.89,
0.11
],
"target": 0,
"brier": 0.0242,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0204",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0205",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0206",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 0,
"brier": 0.012799999999999994,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0207",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 0,
"brier": 0.012799999999999994,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0208",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.87,
"probabilities": [
0.87,
0.13
],
"target": 0,
"brier": 0.033800000000000004,
"nll": 0.13926206733350766
},
{
"id": "transfer-v4-0209",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.63,
"probabilities": [
0.63,
0.37
],
"target": 0,
"brier": 0.2738,
"nll": 0.4620354595965587
},
{
"id": "transfer-v4-0210",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 0,
"brier": 0.012799999999999994,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0211",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.83,
0.17
],
"target": 0,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0212",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.52,
"probabilities": [
0.52,
0.48
],
"target": 0,
"brier": 0.4608,
"nll": 0.6539264674066639
},
{
"id": "transfer-v4-0213",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.06999999999999995,
0.93
],
"target": 1,
"brier": 0.009799999999999986,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0214",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0215",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 1,
"brier": 0.0288,
"nll": 0.12783337150988489
},
{
"id": "transfer-v4-0216",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.58,
"probabilities": [
0.42000000000000004,
0.58
],
"target": 0,
"brier": 0.6728,
"nll": 0.867500567704723
},
{
"id": "transfer-v4-0217",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.9,
"probabilities": [
0.9,
0.1
],
"target": 1,
"brier": 1.62,
"nll": 2.3025850929940455
},
{
"id": "transfer-v4-0218",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0219",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9299999999999999,
"probabilities": [
0.9299999999999999,
0.07
],
"target": 0,
"brier": 0.00980000000000001,
"nll": 0.0725706928348355
},
{
"id": "transfer-v4-0220",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.75,
0.25
],
"target": 1,
"brier": 1.125,
"nll": 1.3862943611198906
},
{
"id": "transfer-v4-0221",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.69,
"probabilities": [
0.69,
0.31
],
"target": 1,
"brier": 0.9521999999999998,
"nll": 1.171182981502945
},
{
"id": "transfer-v4-0222",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5900000000000001,
"probabilities": [
0.5900000000000001,
0.41
],
"target": 0,
"brier": 0.33619999999999994,
"nll": 0.5276327420823718
},
{
"id": "transfer-v4-0223",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.79,
"probabilities": [
0.79,
0.21
],
"target": 1,
"brier": 1.2482000000000002,
"nll": 1.5606477482646683
},
{
"id": "transfer-v4-0224",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0225",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5800000000000001,
"probabilities": [
0.5800000000000001,
0.42
],
"target": 0,
"brier": 0.3527999999999999,
"nll": 0.5447271754416719
},
{
"id": "transfer-v4-0226",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.87,
"probabilities": [
0.13,
0.87
],
"target": 1,
"brier": 0.033800000000000004,
"nll": 0.13926206733350766
},
{
"id": "transfer-v4-0227",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.89,
0.11
],
"target": 0,
"brier": 0.0242,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0228",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.67,
"probabilities": [
0.32999999999999996,
0.67
],
"target": 0,
"brier": 0.8978000000000002,
"nll": 1.1086626245216114
},
{
"id": "transfer-v4-0229",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.83,
0.17
],
"target": 0,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0230",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0231",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.10999999999999999,
0.89
],
"target": 1,
"brier": 0.024199999999999996,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0232",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0233",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.53,
"probabilities": [
0.53,
0.47
],
"target": 0,
"brier": 0.44179999999999997,
"nll": 0.6348782724359695
},
{
"id": "transfer-v4-0234",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9299999999999999,
"probabilities": [
0.9299999999999999,
0.07
],
"target": 0,
"brier": 0.00980000000000001,
"nll": 0.0725706928348355
},
{
"id": "transfer-v4-0235",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.58,
"probabilities": [
0.42000000000000004,
0.58
],
"target": 1,
"brier": 0.35280000000000006,
"nll": 0.5447271754416722
},
{
"id": "transfer-v4-0236",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.79,
"probabilities": [
0.20999999999999996,
0.79
],
"target": 1,
"brier": 0.08819999999999997,
"nll": 0.23572233352106983
},
{
"id": "transfer-v4-0237",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.75,
"probabilities": [
0.75,
0.25
],
"target": 0,
"brier": 0.125,
"nll": 0.2876820724517809
},
{
"id": "transfer-v4-0238",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0239",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.75,
"probabilities": [
0.75,
0.25
],
"target": 0,
"brier": 0.125,
"nll": 0.2876820724517809
},
{
"id": "transfer-v4-0240",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0241",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0242",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0243",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0244",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0245",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0246",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.08999999999999997,
0.91
],
"target": 1,
"brier": 0.01619999999999999,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0247",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.71,
"probabilities": [
0.29000000000000004,
0.71
],
"target": 0,
"brier": 1.0082,
"nll": 1.2378743560016172
},
{
"id": "transfer-v4-0248",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0249",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0250",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0251",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.06000000000000005,
0.94
],
"target": 1,
"brier": 0.007200000000000013,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0252",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.75,
"probabilities": [
0.25,
0.75
],
"target": 1,
"brier": 0.125,
"nll": 0.2876820724517809
},
{
"id": "transfer-v4-0253",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.81,
"probabilities": [
0.18999999999999995,
0.81
],
"target": 1,
"brier": 0.07219999999999996,
"nll": 0.21072103131565253
},
{
"id": "transfer-v4-0254",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.68,
"probabilities": [
0.31999999999999995,
0.68
],
"target": 1,
"brier": 0.20479999999999993,
"nll": 0.3856624808119846
},
{
"id": "transfer-v4-0255",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0256",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0257",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0258",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0259",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.06000000000000005,
0.94
],
"target": 1,
"brier": 0.007200000000000013,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0260",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0261",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.74,
"probabilities": [
0.74,
0.26
],
"target": 0,
"brier": 0.13520000000000001,
"nll": 0.3011050927839216
},
{
"id": "transfer-v4-0262",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0263",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.21999999999999997,
0.78
],
"target": 1,
"brier": 0.09679999999999998,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0264",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0265",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0266",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.76,
"probabilities": [
0.24,
0.76
],
"target": 1,
"brier": 0.1152,
"nll": 0.2744368457017603
},
{
"id": "transfer-v4-0267",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0268",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.67,
"probabilities": [
0.32999999999999996,
0.67
],
"target": 0,
"brier": 0.8978000000000002,
"nll": 1.1086626245216114
},
{
"id": "transfer-v4-0269",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0270",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.85,
"probabilities": [
0.85,
0.15
],
"target": 0,
"brier": 0.045000000000000005,
"nll": 0.16251892949777494
},
{
"id": "transfer-v4-0271",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0272",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.16000000000000003,
0.84
],
"target": 1,
"brier": 0.05120000000000002,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0273",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.10999999999999999,
0.89
],
"target": 1,
"brier": 0.024199999999999996,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0274",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0275",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0276",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.5800000000000001,
"probabilities": [
0.5800000000000001,
0.42
],
"target": 1,
"brier": 0.6728000000000002,
"nll": 0.8675005677047231
},
{
"id": "transfer-v4-0277",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0278",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0279",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0280",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0281",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0282",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0283",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.79,
"probabilities": [
0.20999999999999996,
0.79
],
"target": 1,
"brier": 0.08819999999999997,
"nll": 0.23572233352106983
},
{
"id": "transfer-v4-0284",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0285",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0286",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0287",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.08999999999999997,
0.91
],
"target": 1,
"brier": 0.01619999999999999,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0288",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0289",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.48,
0.52
],
"target": 0,
"brier": 0.5408000000000001,
"nll": 0.7339691750802004
},
{
"id": "transfer-v4-0290",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0291",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0292",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0293",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0294",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0295",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0296",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0297",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.91,
0.09
],
"target": 0,
"brier": 0.016199999999999992,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0298",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0299",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6,
"probabilities": [
0.4,
0.6
],
"target": 1,
"brier": 0.32000000000000006,
"nll": 0.5108256237659907
},
{
"id": "transfer-v4-0300",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.75,
"probabilities": [
0.25,
0.75
],
"target": 1,
"brier": 0.125,
"nll": 0.2876820724517809
},
{
"id": "transfer-v4-0301",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0302",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0303",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0304",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.63,
"probabilities": [
0.63,
0.37
],
"target": 1,
"brier": 0.7938000000000001,
"nll": 0.9942522733438669
},
{
"id": "transfer-v4-0305",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0306",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.65,
"probabilities": [
0.65,
0.35
],
"target": 0,
"brier": 0.24499999999999997,
"nll": 0.4307829160924542
},
{
"id": "transfer-v4-0307",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0308",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.89,
0.11
],
"target": 0,
"brier": 0.0242,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0309",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0310",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.67,
"probabilities": [
0.32999999999999996,
0.67
],
"target": 0,
"brier": 0.8978000000000002,
"nll": 1.1086626245216114
},
{
"id": "transfer-v4-0311",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0312",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0313",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.56,
"probabilities": [
0.43999999999999995,
0.56
],
"target": 0,
"brier": 0.6272000000000001,
"nll": 0.8209805520698303
},
{
"id": "transfer-v4-0314",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0315",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.21999999999999997,
0.78
],
"target": 1,
"brier": 0.09679999999999998,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0316",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.16000000000000003,
0.84
],
"target": 1,
"brier": 0.05120000000000002,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0317",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0318",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.89,
"probabilities": [
0.89,
0.11
],
"target": 0,
"brier": 0.0242,
"nll": 0.11653381625595151
},
{
"id": "transfer-v4-0319",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.84,
0.16
],
"target": 0,
"brier": 0.05120000000000001,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0320",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6,
"probabilities": [
0.6,
0.4
],
"target": 0,
"brier": 0.32000000000000006,
"nll": 0.5108256237659907
},
{
"id": "transfer-v4-0321",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5,
"probabilities": [
0.5,
0.5
],
"target": 0,
"brier": 0.5,
"nll": 0.6931471805599453
},
{
"id": "transfer-v4-0322",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0323",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0324",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0325",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.82,
"probabilities": [
0.18000000000000005,
0.82
],
"target": 0,
"brier": 1.3447999999999998,
"nll": 1.7147984280919264
},
{
"id": "transfer-v4-0326",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 0,
"brier": 1.62,
"nll": 2.302585092994046
},
{
"id": "transfer-v4-0327",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0328",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.06999999999999995,
0.93
],
"target": 1,
"brier": 0.009799999999999986,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0329",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.86,
"probabilities": [
0.14,
0.86
],
"target": 1,
"brier": 0.039200000000000006,
"nll": 0.15082288973458366
},
{
"id": "transfer-v4-0330",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0331",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.16000000000000003,
0.84
],
"target": 1,
"brier": 0.05120000000000002,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0332",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0333",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.08999999999999997,
0.91
],
"target": 1,
"brier": 0.01619999999999999,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0334",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.6799999999999999,
"probabilities": [
0.6799999999999999,
0.32
],
"target": 1,
"brier": 0.9247999999999998,
"nll": 1.1394342831883648
},
{
"id": "transfer-v4-0335",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.06999999999999995,
0.93
],
"target": 1,
"brier": 0.009799999999999986,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0336",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0337",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.52,
0.48
],
"target": 1,
"brier": 0.5408000000000001,
"nll": 0.7339691750802004
},
{
"id": "transfer-v4-0338",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0339",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0340",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.52,
"probabilities": [
0.48,
0.52
],
"target": 1,
"brier": 0.4608,
"nll": 0.6539264674066639
},
{
"id": "transfer-v4-0341",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 1,
"brier": 0.0288,
"nll": 0.12783337150988489
},
{
"id": "transfer-v4-0342",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.54,
"probabilities": [
0.54,
0.46
],
"target": 1,
"brier": 0.5832,
"nll": 0.7765287894989963
},
{
"id": "transfer-v4-0343",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0344",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.66,
"probabilities": [
0.33999999999999997,
0.66
],
"target": 1,
"brier": 0.23119999999999996,
"nll": 0.4155154439616658
},
{
"id": "transfer-v4-0345",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0346",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0347",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0348",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.06999999999999995,
0.93
],
"target": 1,
"brier": 0.009799999999999986,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0349",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0350",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0351",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.83,
0.17
],
"target": 0,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0352",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 1,
"brier": 0.01999999999999999,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0353",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 1,
"brier": 0.01999999999999999,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0354",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.81,
"probabilities": [
0.18999999999999995,
0.81
],
"target": 1,
"brier": 0.07219999999999996,
"nll": 0.21072103131565253
},
{
"id": "transfer-v4-0355",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.86,
"probabilities": [
0.86,
0.14
],
"target": 0,
"brier": 0.039200000000000006,
"nll": 0.15082288973458366
},
{
"id": "transfer-v4-0356",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0357",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 1,
"brier": 0.003200000000000006,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0358",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0359",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0360",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 0,
"brier": 1.62,
"nll": 2.302585092994046
},
{
"id": "transfer-v4-0361",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.050000000000000044,
0.95
],
"target": 1,
"brier": 0.005000000000000009,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0362",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.84,
"probabilities": [
0.16000000000000003,
0.84
],
"target": 0,
"brier": 1.4111999999999998,
"nll": 1.83258146374831
},
{
"id": "transfer-v4-0363",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 1,
"brier": 0.01999999999999999,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0364",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0365",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.92,
0.08
],
"target": 0,
"brier": 0.012799999999999994,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0366",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0367",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0368",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0369",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.77,
"probabilities": [
0.22999999999999998,
0.77
],
"target": 0,
"brier": 1.1858,
"nll": 1.4696759700589417
},
{
"id": "transfer-v4-0370",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0371",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5,
"probabilities": [
0.5,
0.5
],
"target": 0,
"brier": 0.5,
"nll": 0.6931471805599453
},
{
"id": "transfer-v4-0372",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0373",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 1,
"brier": 1.8432,
"nll": 3.2188758248682006
},
{
"id": "transfer-v4-0374",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.91,
"probabilities": [
0.08999999999999997,
0.91
],
"target": 0,
"brier": 1.6562000000000001,
"nll": 2.4079456086518722
},
{
"id": "transfer-v4-0375",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0376",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.55,
"probabilities": [
0.44999999999999996,
0.55
],
"target": 0,
"brier": 0.6050000000000001,
"nll": 0.7985076962177717
},
{
"id": "transfer-v4-0377",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0378",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.9,
"probabilities": [
0.09999999999999998,
0.9
],
"target": 0,
"brier": 1.62,
"nll": 2.302585092994046
},
{
"id": "transfer-v4-0379",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0380",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0381",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.85,
"probabilities": [
0.15000000000000002,
0.85
],
"target": 0,
"brier": 1.4449999999999998,
"nll": 1.897119984885881
},
{
"id": "transfer-v4-0382",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.62,
"probabilities": [
0.38,
0.62
],
"target": 0,
"brier": 0.7688,
"nll": 0.9675840262617056
},
{
"id": "transfer-v4-0383",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.92,
"probabilities": [
0.07999999999999996,
0.92
],
"target": 1,
"brier": 0.012799999999999987,
"nll": 0.08338160893905101
},
{
"id": "transfer-v4-0384",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.050000000000000044,
0.95
],
"target": 1,
"brier": 0.005000000000000009,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0385",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0386",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.96,
"probabilities": [
0.040000000000000036,
0.96
],
"target": 0,
"brier": 1.8432,
"nll": 3.2188758248681997
},
{
"id": "transfer-v4-0387",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0388",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.030000000000000027,
0.97
],
"target": 1,
"brier": 0.0018000000000000032,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0389",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.76,
"probabilities": [
0.24,
0.76
],
"target": 1,
"brier": 0.1152,
"nll": 0.2744368457017603
},
{
"id": "transfer-v4-0390",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.03
],
"target": 0,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0391",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.74,
"probabilities": [
0.74,
0.26
],
"target": 0,
"brier": 0.13520000000000001,
"nll": 0.3011050927839216
},
{
"id": "transfer-v4-0392",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.88,
"probabilities": [
0.12,
0.88
],
"target": 0,
"brier": 1.5488,
"nll": 2.120263536200091
},
{
"id": "transfer-v4-0393",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.94,
0.06
],
"target": 0,
"brier": 0.007200000000000007,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0394",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0395",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9299999999999999,
"probabilities": [
0.9299999999999999,
0.07
],
"target": 0,
"brier": 0.00980000000000001,
"nll": 0.0725706928348355
},
{
"id": "transfer-v4-0396",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.86,
"probabilities": [
0.86,
0.14
],
"target": 1,
"brier": 1.4791999999999998,
"nll": 1.9661128563728327
},
{
"id": "transfer-v4-0397",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0398",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0399",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.94,
"probabilities": [
0.06000000000000005,
0.94
],
"target": 1,
"brier": 0.007200000000000013,
"nll": 0.06187540371808753
},
{
"id": "transfer-v4-0400",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0401",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.0,
0.0,
0.99
],
"target": 3,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0402",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0403",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0404",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0405",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0406",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0407",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0408",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0409",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0410",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0411",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0412",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0413",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0414",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0415",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0416",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.75,
"probabilities": [
0.23,
0.01,
0.01,
0.75
],
"target": 3,
"brier": 0.11560000000000001,
"nll": 0.2876820724517809
},
{
"id": "transfer-v4-0417",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0418",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0419",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0420",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0421",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0422",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": false,
"confidence": 0.88,
"probabilities": [
0.12,
0.0,
0.88,
0.0
],
"target": 0,
"brier": 1.5488,
"nll": 2.120263536200091
},
{
"id": "transfer-v4-0423",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0424",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0425",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.02,
0.98,
0.0,
0.0
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0426",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0427",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0428",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0429",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0430",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0431",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.01,
0.0,
0.03
],
"target": 0,
"brier": 0.002600000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0432",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0433",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0434",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0435",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0436",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.5,
"probabilities": [
0.5,
0.34,
0.1,
0.06
],
"target": 0,
"brier": 0.37920000000000004,
"nll": 0.6931471805599453
},
{
"id": "transfer-v4-0437",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0438",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0439",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0440",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0441",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0442",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0443",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0444",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0445",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0446",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0447",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0448",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0449",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0450",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0451",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0452",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0453",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0454",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0455",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0456",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0457",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0458",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0459",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0460",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0461",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0462",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0463",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0464",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0465",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0466",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0467",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.82,
"probabilities": [
0.01,
0.01,
0.82,
0.16
],
"target": 2,
"brier": 0.05820000000000002,
"nll": 0.19845093872383832
},
{
"id": "transfer-v4-0468",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0469",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0470",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0471",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0472",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0473",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0474",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0475",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0476",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0477",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0478",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0479",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0480",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.85,
"probabilities": [
0.85,
0.14,
0.01,
0.0,
0.0
],
"target": 0,
"brier": 0.04220000000000001,
"nll": 0.16251892949777494
},
{
"id": "transfer-v4-0481",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.9393939393939393,
"probabilities": [
0.9393939393939393,
0.0101010101010101,
0.050505050505050504,
0.0
],
"target": 2,
"brier": 1.7841036628915414,
"nll": 2.9856819377004897
},
{
"id": "transfer-v4-0482",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.03,
0.97,
0.0,
0.0
],
"target": 1,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0483",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0484",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.03,
0.97,
0.0,
0.0
],
"target": 1,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0485",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0486",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0487",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.01,
0.99
],
"target": 3,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0488",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0489",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.0,
0.01,
0.0,
0.04
],
"target": 0,
"brier": 0.004200000000000004,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0490",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.68,
"probabilities": [
0.020000000000000004,
0.010000000000000002,
0.68,
0.29000000000000004
],
"target": 2,
"brier": 0.18699999999999997,
"nll": 0.3856624808119846
},
{
"id": "transfer-v4-0491",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.0,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0492",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0493",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.91,
"probabilities": [
0.0,
0.09,
0.0,
0.91
],
"target": 3,
"brier": 0.016199999999999992,
"nll": 0.09431067947124129
},
{
"id": "transfer-v4-0494",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0495",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 2,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0496",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 2,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0497",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 1,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0498",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.98,
0.02,
0.0,
0.0
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0499",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0500",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0501",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.0,
0.01,
0.0
],
"target": 4,
"brier": 1.9802,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0502",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 1,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0503",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0504",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0505",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.59,
"probabilities": [
0.38,
0.03,
0.59,
0.0
],
"target": 2,
"brier": 0.3134,
"nll": 0.527632742082372
},
{
"id": "transfer-v4-0506",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0507",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0,
0.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0508",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.02,
0.01,
0.01
],
"target": 0,
"brier": 0.0022000000000000027,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0509",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0510",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01,
0.0,
0.0
],
"target": 4,
"brier": 1.9802,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0511",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.98,
"probabilities": [
0.98,
0.0,
0.0,
0.02
],
"target": 3,
"brier": 1.9207999999999998,
"nll": 3.912023005428146
},
{
"id": "transfer-v4-0512",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 3,
"brier": 2.0,
"nll": 27.631021115928547
},
{
"id": "transfer-v4-0513",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.01,
0.03,
0.01,
0.95,
0.0
],
"target": 3,
"brier": 0.0036000000000000042,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0514",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.88,
"probabilities": [
0.88,
0.01,
0.02,
0.09
],
"target": 0,
"brier": 0.023,
"nll": 0.12783337150988489
},
{
"id": "transfer-v4-0515",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.02,
0.97,
0.01,
0.0
],
"target": 1,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0516",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6,
"probabilities": [
0.6,
0.05,
0.01,
0.01,
0.01,
0.31,
0.01
],
"target": 1,
"brier": 1.359,
"nll": 2.995732273553991
},
{
"id": "transfer-v4-0517",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.65,
"probabilities": [
0.65,
0.32,
0.01,
0.01,
0.0,
0.01
],
"target": 0,
"brier": 0.22519999999999998,
"nll": 0.4307829160924542
},
{
"id": "transfer-v4-0518",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.74,
"probabilities": [
0.04,
0.18,
0.0,
0.0,
0.74,
0.04
],
"target": 1,
"brier": 1.2232,
"nll": 1.7147984280919266
},
{
"id": "transfer-v4-0519",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.77,
"probabilities": [
0.02,
0.0,
0.0,
0.0,
0.21,
0.0,
0.77
],
"target": 0,
"brier": 1.5974,
"nll": 3.912023005428146
},
{
"id": "transfer-v4-0520",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.0,
0.84,
0.0,
0.16,
0.0,
0.0
],
"target": 1,
"brier": 0.05120000000000001,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0521",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.24,
0.01,
0.0,
0.0,
0.75,
0.0
],
"target": 0,
"brier": 1.1402,
"nll": 1.4271163556401458
},
{
"id": "transfer-v4-0522",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.0,
0.17,
0.83,
0.0,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348
},
{
"id": "transfer-v4-0523",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0524",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0525",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.0,
0.0,
0.93,
0.0,
0.0,
0.02,
0.05
],
"target": 2,
"brier": 0.007799999999999994,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0526",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.68,
"probabilities": [
0.0,
0.68,
0.01,
0.0,
0.31,
0.0
],
"target": 1,
"brier": 0.19859999999999997,
"nll": 0.3856624808119846
},
{
"id": "transfer-v4-0527",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.99,
0.0,
0.0,
0.01
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0528",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.84,
"probabilities": [
0.16,
0.84,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.05120000000000001,
"nll": 0.1743533871447778
},
{
"id": "transfer-v4-0529",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.0,
0.0,
0.0,
0.0,
0.99
],
"target": 5,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0530",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0531",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.44,
"probabilities": [
0.33,
0.01,
0.01,
0.19,
0.02,
0.0,
0.44
],
"target": 4,
"brier": 1.2992,
"nll": 3.912023005428146
},
{
"id": "transfer-v4-0532",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.73,
"probabilities": [
0.0,
0.17,
0.73,
0.1,
0.0,
0.0
],
"target": 1,
"brier": 1.2317999999999998,
"nll": 1.7719568419318752
},
{
"id": "transfer-v4-0533",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.75,
"probabilities": [
0.19,
0.0,
0.0,
0.06,
0.0,
0.75
],
"target": 3,
"brier": 1.4822,
"nll": 2.8134107167600364
},
{
"id": "transfer-v4-0534",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.67,
"probabilities": [
0.67,
0.0,
0.26,
0.06,
0.0,
0.01,
0.0
],
"target": 3,
"brier": 1.4002000000000001,
"nll": 2.8134107167600364
},
{
"id": "transfer-v4-0535",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.63,
"probabilities": [
0.63,
0.0,
0.0,
0.37,
0.0,
0.0
],
"target": 0,
"brier": 0.2738,
"nll": 0.4620354595965587
},
{
"id": "transfer-v4-0536",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.85,
"probabilities": [
0.0,
0.0,
0.85,
0.15,
0.0,
0.0
],
"target": 3,
"brier": 1.4449999999999998,
"nll": 1.8971199848858813
},
{
"id": "transfer-v4-0537",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.87,
"probabilities": [
0.13,
0.0,
0.0,
0.0,
0.0,
0.0,
0.87
],
"target": 6,
"brier": 0.033800000000000004,
"nll": 0.13926206733350766
},
{
"id": "transfer-v4-0538",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0539",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 5,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0540",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.56,
"probabilities": [
0.08,
0.0,
0.32,
0.56,
0.0,
0.0,
0.04
],
"target": 2,
"brier": 0.7839999999999999,
"nll": 1.1394342831883648
},
{
"id": "transfer-v4-0541",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.78,
"probabilities": [
0.0,
0.0,
0.19,
0.78,
0.0,
0.03
],
"target": 3,
"brier": 0.08539999999999999,
"nll": 0.2484613592984996
},
{
"id": "transfer-v4-0542",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.77,
"probabilities": [
0.19,
0.0,
0.77,
0.0,
0.0,
0.04
],
"target": 2,
"brier": 0.09059999999999999,
"nll": 0.2613647641344075
},
{
"id": "transfer-v4-0543",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.59,
"probabilities": [
0.11,
0.0,
0.0,
0.02,
0.0,
0.59,
0.28
],
"target": 6,
"brier": 0.8789999999999999,
"nll": 1.2729656758128873
},
{
"id": "transfer-v4-0544",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.86,
"probabilities": [
0.0,
0.13,
0.0,
0.01,
0.86,
0.0
],
"target": 4,
"brier": 0.03660000000000001,
"nll": 0.15082288973458366
},
{
"id": "transfer-v4-0545",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.72,
"probabilities": [
0.28,
0.0,
0.0,
0.0,
0.0,
0.72
],
"target": 5,
"brier": 0.15680000000000002,
"nll": 0.3285040669720361
},
{
"id": "transfer-v4-0546",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.01,
0.45,
0.0,
0.52,
0.0,
0.02,
0.0
],
"target": 1,
"brier": 0.5734,
"nll": 0.7985076962177716
},
{
"id": "transfer-v4-0547",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.0,
0.93,
0.04,
0.0,
0.01,
0.02
],
"target": 1,
"brier": 0.006999999999999993,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0548",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.0,
0.01,
0.0,
0.04,
0.0
],
"target": 0,
"brier": 0.004200000000000004,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0549",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.61,
"probabilities": [
0.0,
0.0,
0.0,
0.61,
0.0,
0.0,
0.39
],
"target": 6,
"brier": 0.7442,
"nll": 0.941608539858445
},
{
"id": "transfer-v4-0550",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0551",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 5,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0552",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0553",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0554",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0555",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.0,
0.0,
0.0,
0.99
],
"target": 4,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0556",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": false,
"confidence": 0.55,
"probabilities": [
0.05,
0.55,
0.12,
0.28
],
"target": 3,
"brier": 0.8378,
"nll": 1.2729656758128873
},
{
"id": "transfer-v4-0557",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.02,
0.0,
0.98
],
"target": 3,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0558",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0559",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.0,
0.99,
0.01
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0560",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0561",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0562",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.53,
"probabilities": [
0.0,
0.0,
0.47,
0.53
],
"target": 3,
"brier": 0.44179999999999997,
"nll": 0.6348782724359695
},
{
"id": "transfer-v4-0563",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0564",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0565",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.51,
"probabilities": [
0.51,
0.0,
0.49,
0.0
],
"target": 0,
"brier": 0.48019999999999996,
"nll": 0.6733445532637656
},
{
"id": "transfer-v4-0566",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0567",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0568",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.77,
"probabilities": [
0.77,
0.01,
0.0,
0.22
],
"target": 0,
"brier": 0.10139999999999999,
"nll": 0.2613647641344075
},
{
"id": "transfer-v4-0569",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0570",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0571",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0572",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0573",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0574",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0575",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0576",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0577",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.01,
0.01,
0.0,
0.98
],
"target": 3,
"brier": 0.0006000000000000007,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0578",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0579",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0580",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.02,
0.98,
0.0
],
"target": 2,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0581",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0582",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0,
0.0,
0.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0583",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": false,
"confidence": 0.73,
"probabilities": [
0.27,
0.0,
0.0,
0.73
],
"target": 0,
"brier": 1.0657999999999999,
"nll": 1.3093333199837622
},
{
"id": "transfer-v4-0584",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0585",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
0.0,
1.0
],
"target": 4,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0586",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.0,
0.98,
0.02,
0.0
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0587",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
0.0,
1.0
],
"target": 3,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0588",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0589",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0590",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0591",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0592",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0593",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0594",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0595",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0596",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0597",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0598",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0599",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0600",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0601",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0602",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0603",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0604",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0605",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0606",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0607",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0608",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0609",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0610",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0611",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0612",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0613",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0614",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0615",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0616",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0617",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0618",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0619",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0620",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0621",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0622",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0623",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0624",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0625",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0626",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.020000000000000018,
0.98
],
"target": 1,
"brier": 0.0008000000000000014,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0627",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0628",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0629",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0630",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.01,
0.02
],
"target": 0,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.05
},
{
"id": "transfer-v4-0631",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.01,
0.97,
0.02
],
"target": 1,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0632",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0633",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0634",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.01,
0.01
],
"target": 0,
"brier": 0.0006000000000000007,
"nll": 0.020202707317519466,
"ordinalAbsoluteError": 0.03
},
{
"id": "transfer-v4-0635",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.0,
0.05,
0.95
],
"target": 2,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058,
"ordinalAbsoluteError": 0.050000000000000044
},
{
"id": "transfer-v4-0636",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.01,
0.01
],
"target": 0,
"brier": 0.0006000000000000007,
"nll": 0.020202707317519466,
"ordinalAbsoluteError": 0.03
},
{
"id": "transfer-v4-0637",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0638",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.01,
0.01
],
"target": 0,
"brier": 0.0006000000000000007,
"nll": 0.020202707317519466,
"ordinalAbsoluteError": 0.03
},
{
"id": "transfer-v4-0639",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.67,
"probabilities": [
0.0,
0.33,
0.67
],
"target": 2,
"brier": 0.2178,
"nll": 0.40047756659712525,
"ordinalAbsoluteError": 0.32999999999999985
},
{
"id": "transfer-v4-0640",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0641",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.02,
0.98,
0.0
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466,
"ordinalAbsoluteError": 0.020000000000000018
},
{
"id": "transfer-v4-0642",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.01
},
{
"id": "transfer-v4-0643",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.03,
0.95,
0.02
],
"target": 1,
"brier": 0.0038000000000000043,
"nll": 0.05129329438755058,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0644",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.02,
0.01
],
"target": 0,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.04
},
{
"id": "transfer-v4-0645",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.68,
"probabilities": [
0.010000000000000002,
0.68,
0.31000000000000005
],
"target": 1,
"brier": 0.1986,
"nll": 0.3856624808119846,
"ordinalAbsoluteError": 0.30000000000000027
},
{
"id": "transfer-v4-0646",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0647",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0648",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0649",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0650",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0651",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.02,
0.97,
0.01
],
"target": 1,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0652",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0653",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.0,
0.17,
0.83
],
"target": 2,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348,
"ordinalAbsoluteError": 0.17000000000000015
},
{
"id": "transfer-v4-0654",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.01
},
{
"id": "transfer-v4-0655",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.51,
"probabilities": [
0.01,
0.48,
0.51
],
"target": 2,
"brier": 0.47059999999999996,
"nll": 0.6733445532637656,
"ordinalAbsoluteError": 0.5
},
{
"id": "transfer-v4-0656",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.01
},
{
"id": "transfer-v4-0657",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.0,
0.1,
0.9
],
"target": 2,
"brier": 0.019999999999999997,
"nll": 0.10536051565782628,
"ordinalAbsoluteError": 0.09999999999999987
},
{
"id": "transfer-v4-0658",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0659",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99,
0.0
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "transfer-v4-0660",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.01
},
{
"id": "transfer-v4-0661",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.73,
"probabilities": [
0.01,
0.73,
0.26
],
"target": 2,
"brier": 1.0806,
"nll": 1.3470736479666092,
"ordinalAbsoluteError": 0.75
},
{
"id": "transfer-v4-0662",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "transfer-v4-0663",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.03,
0.97,
0.0
],
"target": 1,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.030000000000000027
},
{
"id": "transfer-v4-0664",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01,
0.0
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.01
},
{
"id": "transfer-v4-0665",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.83,
"probabilities": [
0.0,
0.17,
0.83
],
"target": 2,
"brier": 0.05780000000000002,
"nll": 0.18632957819149348,
"ordinalAbsoluteError": 0.17000000000000015
},
{
"id": "transfer-v4-0666",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.97,
0.02,
0.01
],
"target": 0,
"brier": 0.0014000000000000017,
"nll": 0.030459207484708574,
"ordinalAbsoluteError": 0.04
},
{
"id": "transfer-v4-0667",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.0,
0.05,
0.95
],
"target": 2,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058,
"ordinalAbsoluteError": 0.050000000000000044
},
{
"id": "transfer-v4-0668",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0669",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.92,
"probabilities": [
0.08,
0.92
],
"target": 0,
"brier": 1.6928,
"nll": 2.5257286443082556
},
{
"id": "transfer-v4-0670",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0671",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0672",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0673",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0674",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0675",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0676",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.52,
"probabilities": [
0.48,
0.52
],
"target": 1,
"brier": 0.4608,
"nll": 0.6539264674066639
},
{
"id": "transfer-v4-0677",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0678",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.58,
"probabilities": [
0.58,
0.42
],
"target": 1,
"brier": 0.6728000000000001,
"nll": 0.8675005677047231
},
{
"id": "transfer-v4-0679",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.58,
"probabilities": [
0.58,
0.42
],
"target": 1,
"brier": 0.6728000000000001,
"nll": 0.8675005677047231
},
{
"id": "transfer-v4-0680",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0681",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0682",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0683",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0684",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.04,
0.96
],
"target": 1,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0685",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0686",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0687",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.02,
0.98
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0688",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0689",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0690",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0691",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0692",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0693",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0694",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0695",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0696",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0697",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0698",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0699",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0700",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0701",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0702",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0703",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0704",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0705",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0706",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0707",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0708",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.02,
0.98
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0709",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0710",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0711",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0712",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0713",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0714",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0715",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0716",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0717",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0718",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0719",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0720",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.54,
"probabilities": [
0.46,
0.54
],
"target": 1,
"brier": 0.42319999999999997,
"nll": 0.616186139423817
},
{
"id": "transfer-v4-0721",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.53,
"probabilities": [
0.53,
0.47
],
"target": 0,
"brier": 0.44179999999999997,
"nll": 0.6348782724359695
},
{
"id": "transfer-v4-0722",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.58,
"probabilities": [
0.42,
0.58
],
"target": 1,
"brier": 0.3528,
"nll": 0.5447271754416722
},
{
"id": "transfer-v4-0723",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.53,
"probabilities": [
0.47,
0.53
],
"target": 1,
"brier": 0.44179999999999997,
"nll": 0.6348782724359695
},
{
"id": "transfer-v4-0724",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0725",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0726",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0727",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0728",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0729",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0730",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0731",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0732",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0733",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0734",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0735",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.02,
0.98
],
"target": 1,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "transfer-v4-0736",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.07,
0.93
],
"target": 1,
"brier": 0.009799999999999993,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0737",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.96,
"probabilities": [
0.96,
0.04
],
"target": 0,
"brier": 0.003200000000000003,
"nll": 0.040821994520255166
},
{
"id": "transfer-v4-0738",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.97,
"probabilities": [
0.03,
0.97
],
"target": 1,
"brier": 0.0018000000000000017,
"nll": 0.030459207484708574
},
{
"id": "transfer-v4-0739",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.93,
"probabilities": [
0.07,
0.93
],
"target": 1,
"brier": 0.009799999999999993,
"nll": 0.07257069283483537
},
{
"id": "transfer-v4-0740",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0741",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.86,
"probabilities": [
0.86,
0.14
],
"target": 0,
"brier": 0.039200000000000006,
"nll": 0.15082288973458366
},
{
"id": "transfer-v4-0742",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0743",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "transfer-v4-0744",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.65,
"probabilities": [
0.35,
0.65
],
"target": 0,
"brier": 0.8450000000000001,
"nll": 1.0498221244986778
},
{
"id": "transfer-v4-0745",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.69,
"probabilities": [
0.31,
0.69
],
"target": 1,
"brier": 0.19220000000000004,
"nll": 0.37106368139083207
},
{
"id": "transfer-v4-0746",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.62,
"probabilities": [
0.38,
0.62
],
"target": 0,
"brier": 0.7688,
"nll": 0.9675840262617056
},
{
"id": "transfer-v4-0747",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.63,
"probabilities": [
0.37,
0.63
],
"target": 0,
"brier": 0.7938000000000001,
"nll": 0.9942522733438669
},
{
"id": "transfer-v4-0748",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0749",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9,
"probabilities": [
0.1,
0.9
],
"target": 1,
"brier": 0.019999999999999997,
"nll": 0.10536051565782628
},
{
"id": "transfer-v4-0750",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0751",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0752",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8,
"probabilities": [
0.8,
0.2
],
"target": 0,
"brier": 0.07999999999999999,
"nll": 0.2231435513142097
},
{
"id": "transfer-v4-0753",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.68,
"probabilities": [
0.68,
0.32
],
"target": 1,
"brier": 0.9248000000000001,
"nll": 1.1394342831883648
},
{
"id": "transfer-v4-0754",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.82,
"probabilities": [
0.82,
0.18
],
"target": 0,
"brier": 0.06480000000000002,
"nll": 0.19845093872383832
},
{
"id": "transfer-v4-0755",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.79,
"probabilities": [
0.79,
0.21
],
"target": 0,
"brier": 0.08819999999999997,
"nll": 0.23572233352106983
},
{
"id": "transfer-v4-0756",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.63,
"probabilities": [
0.63,
0.37
],
"target": 1,
"brier": 0.7938000000000001,
"nll": 0.9942522733438669
},
{
"id": "transfer-v4-0757",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.95,
"probabilities": [
0.95,
0.05
],
"target": 0,
"brier": 0.0050000000000000044,
"nll": 0.05129329438755058
},
{
"id": "transfer-v4-0758",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.52,
"probabilities": [
0.52,
0.48
],
"target": 1,
"brier": 0.5408000000000001,
"nll": 0.7339691750802004
},
{
"id": "transfer-v4-0759",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.58,
"probabilities": [
0.58,
0.42
],
"target": 1,
"brier": 0.6728000000000001,
"nll": 0.8675005677047231
},
{
"id": "transfer-v4-0760",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0761",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.01,
0.99
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0762",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "transfer-v4-0763",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-0-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-0-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-0-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-0-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-0-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-0-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-0-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-0-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-1-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-1-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-1-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-1-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-2-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-2-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-2-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-2-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-2-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-2-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-2-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-2-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-3-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-3-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "ru-public-3-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-3-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-3-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-3-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-3-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-3-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-3-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-4-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
},
{
"id": "ru-public-4-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-4-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-4-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-4-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-4-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-4-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-4-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-4-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.99,
0.01
],
"target": 0,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.98,
"probabilities": [
0.98,
0.02
],
"target": 0,
"brier": 0.0008000000000000008,
"nll": 0.020202707317519466
},
{
"id": "ru-public-5-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
0.0,
1.0
],
"target": 2,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
1.0,
0.0,
0.0
],
"target": 0,
"brier": 0.0,
"nll": -0.0
},
{
"id": "ru-public-5-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 1.0,
"probabilities": [
0.0,
1.0,
0.0
],
"target": 1,
"brier": 0.0,
"nll": -0.0,
"ordinalAbsoluteError": 0.0
},
{
"id": "ru-public-5-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.99,
0.01
],
"target": 1,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.010000000000000009,
0.99
],
"target": 1,
"brier": 0.00020000000000000036,
"nll": 0.01005033585350145
},
{
"id": "ru-public-5-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.99,
"probabilities": [
0.0,
0.01,
0.99
],
"target": 2,
"brier": 0.0002000000000000002,
"nll": 0.01005033585350145,
"ordinalAbsoluteError": 0.010000000000000009
}
]