liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
243 lines
5.6 KiB
JSON
243 lines
5.6 KiB
JSON
{
|
|
"rows": [
|
|
{
|
|
"final_loss": 0.18679947033524513,
|
|
"seed": 20260808,
|
|
"source_accuracy": 0.921875,
|
|
"target_accuracy": {
|
|
"target_bright": 0.798828125,
|
|
"target_realistic": 0.8095703125
|
|
},
|
|
"variant": "source_clean"
|
|
},
|
|
{
|
|
"final_loss": 0.24417539592832327,
|
|
"seed": 20260808,
|
|
"source_accuracy": 0.908203125,
|
|
"target_accuracy": {
|
|
"target_bright": 0.533203125,
|
|
"target_realistic": 0.4169921875
|
|
},
|
|
"variant": "source_background"
|
|
},
|
|
{
|
|
"final_loss": 0.22985628596507013,
|
|
"seed": 20260808,
|
|
"source_accuracy": 0.90234375,
|
|
"target_accuracy": {
|
|
"target_bright": 0.857421875,
|
|
"target_realistic": 0.7880859375
|
|
},
|
|
"variant": "source_appearance"
|
|
},
|
|
{
|
|
"final_loss": 0.4308899687603116,
|
|
"seed": 20260808,
|
|
"source_accuracy": 0.857421875,
|
|
"target_accuracy": {
|
|
"target_bright": 0.771484375,
|
|
"target_realistic": 0.7578125
|
|
},
|
|
"variant": "source_full"
|
|
},
|
|
{
|
|
"final_loss": 0.11670511157717556,
|
|
"seed": 20260809,
|
|
"source_accuracy": 0.939453125,
|
|
"target_accuracy": {
|
|
"target_bright": 0.2880859375,
|
|
"target_realistic": 0.248046875
|
|
},
|
|
"variant": "source_clean"
|
|
},
|
|
{
|
|
"final_loss": 0.20411560125648975,
|
|
"seed": 20260809,
|
|
"source_accuracy": 0.921875,
|
|
"target_accuracy": {
|
|
"target_bright": 0.478515625,
|
|
"target_realistic": 0.353515625
|
|
},
|
|
"variant": "source_background"
|
|
},
|
|
{
|
|
"final_loss": 0.23631400940939784,
|
|
"seed": 20260809,
|
|
"source_accuracy": 0.876953125,
|
|
"target_accuracy": {
|
|
"target_bright": 0.8046875,
|
|
"target_realistic": 0.7568359375
|
|
},
|
|
"variant": "source_appearance"
|
|
},
|
|
{
|
|
"final_loss": 0.4168223310261965,
|
|
"seed": 20260809,
|
|
"source_accuracy": 0.9072265625,
|
|
"target_accuracy": {
|
|
"target_bright": 0.8212890625,
|
|
"target_realistic": 0.796875
|
|
},
|
|
"variant": "source_full"
|
|
},
|
|
{
|
|
"final_loss": 0.13805983471684158,
|
|
"seed": 20260810,
|
|
"source_accuracy": 0.9296875,
|
|
"target_accuracy": {
|
|
"target_bright": 0.609375,
|
|
"target_realistic": 0.5869140625
|
|
},
|
|
"variant": "source_clean"
|
|
},
|
|
{
|
|
"final_loss": 0.29387020831927657,
|
|
"seed": 20260810,
|
|
"source_accuracy": 0.8955078125,
|
|
"target_accuracy": {
|
|
"target_bright": 0.576171875,
|
|
"target_realistic": 0.3359375
|
|
},
|
|
"variant": "source_background"
|
|
},
|
|
{
|
|
"final_loss": 0.21353492327034473,
|
|
"seed": 20260810,
|
|
"source_accuracy": 0.8974609375,
|
|
"target_accuracy": {
|
|
"target_bright": 0.8310546875,
|
|
"target_realistic": 0.6865234375
|
|
},
|
|
"variant": "source_appearance"
|
|
},
|
|
{
|
|
"final_loss": 0.35220852866768837,
|
|
"seed": 20260810,
|
|
"source_accuracy": 0.8603515625,
|
|
"target_accuracy": {
|
|
"target_bright": 0.8134765625,
|
|
"target_realistic": 0.728515625
|
|
},
|
|
"variant": "source_full"
|
|
}
|
|
],
|
|
"summary": {
|
|
"source_appearance": {
|
|
"source": {
|
|
"mean": 0.8922526041666666,
|
|
"std": 0.011000485187966017,
|
|
"values": [
|
|
0.90234375,
|
|
0.876953125,
|
|
0.8974609375
|
|
]
|
|
},
|
|
"target_bright": {
|
|
"mean": 0.8310546875,
|
|
"std": 0.021528718442430275,
|
|
"values": [
|
|
0.857421875,
|
|
0.8046875,
|
|
0.8310546875
|
|
]
|
|
},
|
|
"target_realistic": {
|
|
"mean": 0.7438151041666666,
|
|
"std": 0.04247267299557315,
|
|
"values": [
|
|
0.7880859375,
|
|
0.7568359375,
|
|
0.6865234375
|
|
]
|
|
}
|
|
},
|
|
"source_background": {
|
|
"source": {
|
|
"mean": 0.9085286458333334,
|
|
"std": 0.010766819927435695,
|
|
"values": [
|
|
0.908203125,
|
|
0.921875,
|
|
0.8955078125
|
|
]
|
|
},
|
|
"target_bright": {
|
|
"mean": 0.529296875,
|
|
"std": 0.03996356576360106,
|
|
"values": [
|
|
0.533203125,
|
|
0.478515625,
|
|
0.576171875
|
|
]
|
|
},
|
|
"target_realistic": {
|
|
"mean": 0.3688151041666667,
|
|
"std": 0.03481399276640658,
|
|
"values": [
|
|
0.4169921875,
|
|
0.353515625,
|
|
0.3359375
|
|
]
|
|
}
|
|
},
|
|
"source_clean": {
|
|
"source": {
|
|
"mean": 0.9303385416666666,
|
|
"std": 0.007190990245564624,
|
|
"values": [
|
|
0.921875,
|
|
0.939453125,
|
|
0.9296875
|
|
]
|
|
},
|
|
"target_bright": {
|
|
"mean": 0.5654296875,
|
|
"std": 0.21081237849663584,
|
|
"values": [
|
|
0.798828125,
|
|
0.2880859375,
|
|
0.609375
|
|
]
|
|
},
|
|
"target_realistic": {
|
|
"mean": 0.5481770833333334,
|
|
"std": 0.23087162072123282,
|
|
"values": [
|
|
0.8095703125,
|
|
0.248046875,
|
|
0.5869140625
|
|
]
|
|
}
|
|
},
|
|
"source_full": {
|
|
"source": {
|
|
"mean": 0.875,
|
|
"std": 0.022818987198335788,
|
|
"values": [
|
|
0.857421875,
|
|
0.9072265625,
|
|
0.8603515625
|
|
]
|
|
},
|
|
"target_bright": {
|
|
"mean": 0.8020833333333334,
|
|
"std": 0.02187054301073024,
|
|
"values": [
|
|
0.771484375,
|
|
0.8212890625,
|
|
0.8134765625
|
|
]
|
|
},
|
|
"target_realistic": {
|
|
"mean": 0.7610677083333334,
|
|
"std": 0.02800236089532105,
|
|
"values": [
|
|
0.7578125,
|
|
0.796875,
|
|
0.728515625
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|