Karar-git's picture
Add FINAL-2 pipeline, overnight search scripts and results (11 Nov 2026)
2c2dd6c verified
Raw History Blame Contribute Delete
3.82 kB
{
"grid": [
60,
150,
300,
600
],
"rows": [
{
"steps": 60,
"n": 5,
"rep": 0,
"f1": 0.4752690893967487
},
{
"steps": 60,
"n": 5,
"rep": 1,
"f1": 0.47896254829584733
},
{
"steps": 60,
"n": 5,
"rep": 2,
"f1": 0.5194485521018687
},
{
"steps": 60,
"n": 50,
"rep": 0,
"f1": 0.5490712016882752
},
{
"steps": 60,
"n": 50,
"rep": 1,
"f1": 0.5527083307285695
},
{
"steps": 60,
"n": 50,
"rep": 2,
"f1": 0.5471363494676702
},
{
"steps": 60,
"n": 200,
"rep": 0,
"f1": 0.569542112151458
},
{
"steps": 60,
"n": 200,
"rep": 1,
"f1": 0.5796882061538661
},
{
"steps": 60,
"n": 200,
"rep": 2,
"f1": 0.5713353577497671
},
{
"steps": 150,
"n": 5,
"rep": 0,
"f1": 0.4852931580202636
},
{
"steps": 150,
"n": 5,
"rep": 1,
"f1": 0.48677743627345416
},
{
"steps": 150,
"n": 5,
"rep": 2,
"f1": 0.5172077383688378
},
{
"steps": 150,
"n": 50,
"rep": 0,
"f1": 0.5500076016916534
},
{
"steps": 150,
"n": 50,
"rep": 1,
"f1": 0.5535162303676714
},
{
"steps": 150,
"n": 50,
"rep": 2,
"f1": 0.5492764425118571
},
{
"steps": 150,
"n": 200,
"rep": 0,
"f1": 0.5817608944835705
},
{
"steps": 150,
"n": 200,
"rep": 1,
"f1": 0.5931042791351125
},
{
"steps": 150,
"n": 200,
"rep": 2,
"f1": 0.5911666068678278
},
{
"steps": 300,
"n": 5,
"rep": 0,
"f1": 0.4897960121180538
},
{
"steps": 300,
"n": 5,
"rep": 1,
"f1": 0.48523236779901824
},
{
"steps": 300,
"n": 5,
"rep": 2,
"f1": 0.5119732403602113
},
{
"steps": 300,
"n": 50,
"rep": 0,
"f1": 0.5511885140219575
},
{
"steps": 300,
"n": 50,
"rep": 1,
"f1": 0.5555369949864464
},
{
"steps": 300,
"n": 50,
"rep": 2,
"f1": 0.5495949162897769
},
{
"steps": 300,
"n": 200,
"rep": 0,
"f1": 0.5823060301505336
},
{
"steps": 300,
"n": 200,
"rep": 1,
"f1": 0.5952846799978556
},
{
"steps": 300,
"n": 200,
"rep": 2,
"f1": 0.5921326359044334
},
{
"steps": 600,
"n": 5,
"rep": 0,
"f1": 0.49339758915215653
},
{
"steps": 600,
"n": 5,
"rep": 1,
"f1": 0.486544192320482
},
{
"steps": 600,
"n": 5,
"rep": 2,
"f1": 0.5095993040970357
},
{
"steps": 600,
"n": 50,
"rep": 0,
"f1": 0.5494823439061667
},
{
"steps": 600,
"n": 50,
"rep": 1,
"f1": 0.55489372104404
},
{
"steps": 600,
"n": 50,
"rep": 2,
"f1": 0.550785704695016
},
{
"steps": 600,
"n": 200,
"rep": 0,
"f1": 0.5804620115742651
},
{
"steps": 600,
"n": 200,
"rep": 1,
"f1": 0.5912347874606855
},
{
"steps": 600,
"n": 200,
"rep": 2,
"f1": 0.5928397211154817
}
],
"mean_by_steps": {
"60": 0.5381290830815634,
"150": 0.5453455986355832,
"300": 0.545893932403143,
"600": 0.5454710417072588
},
"by_n": {
"60": {
"5": 0.49122672993148825,
"50": 0.5496386272948383,
"200": 0.5735218920183637
},
"150": {
"5": 0.49642611088751853,
"50": 0.5509334248570606,
"200": 0.5886772601621703
},
"300": {
"5": 0.4956672067590944,
"50": 0.5521068084327269,
"200": 0.5899077820176076
},
"600": {
"5": 0.4965136951898914,
"50": 0.5517205898817409,
"200": 0.5881788400501441
}
},
"chosen": 300,
"rule": "highest mean macro F1 over n in (5, 50, 200) x 3 draws on the Madrid pseudo-target"
}