LamaDiab's picture
Training checkpoint - Epoch 2, Step 47030
fba5a2c verified
{
"metrics_history": [
{
"epoch": 0.0212630236019562,
"global_step": 500,
"eval_loss": 11.834263801574707,
"eval_cosine_accuracy": 0.9308079481124878
},
{
"epoch": 0.0425260472039124,
"global_step": 1000,
"eval_loss": 11.764849662780762,
"eval_cosine_accuracy": 0.9313969612121582
},
{
"epoch": 0.0637890708058686,
"global_step": 1500,
"eval_loss": 11.667285919189453,
"eval_cosine_accuracy": 0.9325751066207886
},
{
"epoch": 0.0850520944078248,
"global_step": 2000,
"eval_loss": 11.543947219848633,
"eval_cosine_accuracy": 0.934478223323822
},
{
"epoch": 0.106315118009781,
"global_step": 2500,
"eval_loss": 11.422866821289062,
"eval_cosine_accuracy": 0.9360641837120056
},
{
"epoch": 0.1275781416117372,
"global_step": 3000,
"eval_loss": 11.268472671508789,
"eval_cosine_accuracy": 0.9384657144546509
},
{
"epoch": 0.1488411652136934,
"global_step": 3500,
"eval_loss": 11.027884483337402,
"eval_cosine_accuracy": 0.941592276096344
},
{
"epoch": 0.1701041888156496,
"global_step": 4000,
"eval_loss": 10.77338981628418,
"eval_cosine_accuracy": 0.9445375800132751
},
{
"epoch": 0.1913672124176058,
"global_step": 4500,
"eval_loss": 10.502735137939453,
"eval_cosine_accuracy": 0.9471657276153564
},
{
"epoch": 0.212630236019562,
"global_step": 5000,
"eval_loss": 10.223851203918457,
"eval_cosine_accuracy": 0.9499297738075256
},
{
"epoch": 0.2338932596215182,
"global_step": 5500,
"eval_loss": 9.879401206970215,
"eval_cosine_accuracy": 0.9533734917640686
},
{
"epoch": 0.2551562832234744,
"global_step": 6000,
"eval_loss": 9.583606719970703,
"eval_cosine_accuracy": 0.9558656811714172
},
{
"epoch": 0.2764193068254306,
"global_step": 6500,
"eval_loss": 9.295426368713379,
"eval_cosine_accuracy": 0.9583125710487366
},
{
"epoch": 0.2976823304273868,
"global_step": 7000,
"eval_loss": 9.070219993591309,
"eval_cosine_accuracy": 0.9617562890052795
},
{
"epoch": 0.318945354029343,
"global_step": 7500,
"eval_loss": 8.921951293945312,
"eval_cosine_accuracy": 0.9646109938621521
},
{
"epoch": 0.3402083776312992,
"global_step": 8000,
"eval_loss": 8.841903686523438,
"eval_cosine_accuracy": 0.9665141105651855
},
{
"epoch": 0.3614714012332554,
"global_step": 8500,
"eval_loss": 8.776097297668457,
"eval_cosine_accuracy": 0.9681000709533691
},
{
"epoch": 0.3827344248352116,
"global_step": 9000,
"eval_loss": 8.712888717651367,
"eval_cosine_accuracy": 0.9681000709533691
},
{
"epoch": 0.4039974484371678,
"global_step": 9500,
"eval_loss": 8.671957015991211,
"eval_cosine_accuracy": 0.968235969543457
},
{
"epoch": 0.425260472039124,
"global_step": 10000,
"eval_loss": 8.636693000793457,
"eval_cosine_accuracy": 0.9679641127586365
},
{
"epoch": 0.4465234956410802,
"global_step": 10500,
"eval_loss": 8.61970329284668,
"eval_cosine_accuracy": 0.9684625267982483
},
{
"epoch": 0.4677865192430364,
"global_step": 11000,
"eval_loss": 8.59864616394043,
"eval_cosine_accuracy": 0.968598484992981
},
{
"epoch": 0.4890495428449926,
"global_step": 11500,
"eval_loss": 8.581836700439453,
"eval_cosine_accuracy": 0.9678281545639038
},
{
"epoch": 0.5103125664469488,
"global_step": 12000,
"eval_loss": 8.53200912475586,
"eval_cosine_accuracy": 0.968598484992981
},
{
"epoch": 0.531575590048905,
"global_step": 12500,
"eval_loss": 8.522621154785156,
"eval_cosine_accuracy": 0.9685078859329224
},
{
"epoch": 0.5528386136508612,
"global_step": 13000,
"eval_loss": 8.52730941772461,
"eval_cosine_accuracy": 0.9688250422477722
},
{
"epoch": 0.5741016372528174,
"global_step": 13500,
"eval_loss": 8.488916397094727,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 0.5953646608547736,
"global_step": 14000,
"eval_loss": 8.479202270507812,
"eval_cosine_accuracy": 0.9692781567573547
},
{
"epoch": 0.6166276844567298,
"global_step": 14500,
"eval_loss": 8.463949203491211,
"eval_cosine_accuracy": 0.9690062999725342
},
{
"epoch": 0.637890708058686,
"global_step": 15000,
"eval_loss": 8.437935829162598,
"eval_cosine_accuracy": 0.9686437845230103
},
{
"epoch": 0.6591537316606422,
"global_step": 15500,
"eval_loss": 8.473112106323242,
"eval_cosine_accuracy": 0.9689610004425049
},
{
"epoch": 0.6804167552625984,
"global_step": 16000,
"eval_loss": 8.445318222045898,
"eval_cosine_accuracy": 0.9688703417778015
},
{
"epoch": 0.7016797788645546,
"global_step": 16500,
"eval_loss": 8.421878814697266,
"eval_cosine_accuracy": 0.9694594144821167
},
{
"epoch": 0.7229428024665108,
"global_step": 17000,
"eval_loss": 8.462857246398926,
"eval_cosine_accuracy": 0.9686437845230103
},
{
"epoch": 0.744205826068467,
"global_step": 17500,
"eval_loss": 8.401082038879395,
"eval_cosine_accuracy": 0.9691875576972961
},
{
"epoch": 0.7654688496704232,
"global_step": 18000,
"eval_loss": 8.454690933227539,
"eval_cosine_accuracy": 0.9689610004425049
},
{
"epoch": 0.7867318732723794,
"global_step": 18500,
"eval_loss": 8.442588806152344,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 0.8079948968743356,
"global_step": 19000,
"eval_loss": 8.419596672058105,
"eval_cosine_accuracy": 0.9687344431877136
},
{
"epoch": 0.8292579204762918,
"global_step": 19500,
"eval_loss": 8.426375389099121,
"eval_cosine_accuracy": 0.969504714012146
},
{
"epoch": 0.850520944078248,
"global_step": 20000,
"eval_loss": 8.403668403625488,
"eval_cosine_accuracy": 0.969504714012146
},
{
"epoch": 0.8717839676802042,
"global_step": 20500,
"eval_loss": 8.39807415008545,
"eval_cosine_accuracy": 0.9694141149520874
},
{
"epoch": 0.8930469912821604,
"global_step": 21000,
"eval_loss": 8.437390327453613,
"eval_cosine_accuracy": 0.9687344431877136
},
{
"epoch": 0.9143100148841166,
"global_step": 21500,
"eval_loss": 8.418041229248047,
"eval_cosine_accuracy": 0.9688250422477722
},
{
"epoch": 0.9355730384860728,
"global_step": 22000,
"eval_loss": 8.439444541931152,
"eval_cosine_accuracy": 0.968598484992981
},
{
"epoch": 0.956836062088029,
"global_step": 22500,
"eval_loss": 8.415027618408203,
"eval_cosine_accuracy": 0.9693688154220581
},
{
"epoch": 0.9780990856899852,
"global_step": 23000,
"eval_loss": 8.452112197875977,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 0.9993621092919414,
"global_step": 23500,
"eval_loss": 8.457128524780273,
"eval_cosine_accuracy": 0.968598484992981
},
{
"epoch": 1.0206251328938976,
"global_step": 24000,
"eval_loss": 8.447549819946289,
"eval_cosine_accuracy": 0.9685531854629517
},
{
"epoch": 1.0418881564958538,
"global_step": 24500,
"eval_loss": 8.469432830810547,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 1.06315118009781,
"global_step": 25000,
"eval_loss": 8.477595329284668,
"eval_cosine_accuracy": 0.9688250422477722
},
{
"epoch": 1.0844142036997662,
"global_step": 25500,
"eval_loss": 8.455941200256348,
"eval_cosine_accuracy": 0.9689157009124756
},
{
"epoch": 1.1056772273017224,
"global_step": 26000,
"eval_loss": 8.481649398803711,
"eval_cosine_accuracy": 0.9693688154220581
},
{
"epoch": 1.1269402509036786,
"global_step": 26500,
"eval_loss": 8.489095687866211,
"eval_cosine_accuracy": 0.9689157009124756
},
{
"epoch": 1.1482032745056348,
"global_step": 27000,
"eval_loss": 8.516972541809082,
"eval_cosine_accuracy": 0.9683719277381897
},
{
"epoch": 1.169466298107591,
"global_step": 27500,
"eval_loss": 8.527128219604492,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 1.1907293217095472,
"global_step": 28000,
"eval_loss": 8.560052871704102,
"eval_cosine_accuracy": 0.9690062999725342
},
{
"epoch": 1.2119923453115033,
"global_step": 28500,
"eval_loss": 8.618322372436523,
"eval_cosine_accuracy": 0.9681906700134277
},
{
"epoch": 1.2332553689134595,
"global_step": 29000,
"eval_loss": 8.546183586120605,
"eval_cosine_accuracy": 0.969504714012146
},
{
"epoch": 1.2545183925154157,
"global_step": 29500,
"eval_loss": 8.578022956848145,
"eval_cosine_accuracy": 0.969323456287384
},
{
"epoch": 1.275781416117372,
"global_step": 30000,
"eval_loss": 8.658872604370117,
"eval_cosine_accuracy": 0.9687797427177429
},
{
"epoch": 1.2970444397193281,
"global_step": 30500,
"eval_loss": 8.601694107055664,
"eval_cosine_accuracy": 0.9686437845230103
},
{
"epoch": 1.3183074633212843,
"global_step": 31000,
"eval_loss": 8.666234970092773,
"eval_cosine_accuracy": 0.968417227268219
},
{
"epoch": 1.3395704869232405,
"global_step": 31500,
"eval_loss": 8.674742698669434,
"eval_cosine_accuracy": 0.9685531854629517
},
{
"epoch": 1.3608335105251967,
"global_step": 32000,
"eval_loss": 8.65296459197998,
"eval_cosine_accuracy": 0.9680547118186951
},
{
"epoch": 1.382096534127153,
"global_step": 32500,
"eval_loss": 8.634788513183594,
"eval_cosine_accuracy": 0.9688250422477722
},
{
"epoch": 1.4033595577291091,
"global_step": 33000,
"eval_loss": 8.732030868530273,
"eval_cosine_accuracy": 0.967510998249054
},
{
"epoch": 1.4246225813310653,
"global_step": 33500,
"eval_loss": 8.727688789367676,
"eval_cosine_accuracy": 0.9690968990325928
},
{
"epoch": 1.4458856049330215,
"global_step": 34000,
"eval_loss": 8.750975608825684,
"eval_cosine_accuracy": 0.9679641127586365
},
{
"epoch": 1.4671486285349777,
"global_step": 34500,
"eval_loss": 8.7284574508667,
"eval_cosine_accuracy": 0.967510998249054
},
{
"epoch": 1.488411652136934,
"global_step": 35000,
"eval_loss": 8.765801429748535,
"eval_cosine_accuracy": 0.968235969543457
},
{
"epoch": 1.5096746757388901,
"global_step": 35500,
"eval_loss": 8.72378921508789,
"eval_cosine_accuracy": 0.9684625267982483
},
{
"epoch": 1.5309376993408463,
"global_step": 36000,
"eval_loss": 8.823667526245117,
"eval_cosine_accuracy": 0.9674656987190247
},
{
"epoch": 1.5522007229428025,
"global_step": 36500,
"eval_loss": 8.741899490356445,
"eval_cosine_accuracy": 0.9679641127586365
},
{
"epoch": 1.5734637465447587,
"global_step": 37000,
"eval_loss": 8.775369644165039,
"eval_cosine_accuracy": 0.9678281545639038
},
{
"epoch": 1.594726770146715,
"global_step": 37500,
"eval_loss": 8.834284782409668,
"eval_cosine_accuracy": 0.9670125246047974
},
{
"epoch": 1.6159897937486711,
"global_step": 38000,
"eval_loss": 8.824420928955078,
"eval_cosine_accuracy": 0.9676922559738159
},
{
"epoch": 1.6372528173506273,
"global_step": 38500,
"eval_loss": 8.849225044250488,
"eval_cosine_accuracy": 0.9672391414642334
},
{
"epoch": 1.6585158409525835,
"global_step": 39000,
"eval_loss": 8.900370597839355,
"eval_cosine_accuracy": 0.9667859673500061
},
{
"epoch": 1.6797788645545397,
"global_step": 39500,
"eval_loss": 8.904617309570312,
"eval_cosine_accuracy": 0.9670578837394714
},
{
"epoch": 1.701041888156496,
"global_step": 40000,
"eval_loss": 9.0310697555542,
"eval_cosine_accuracy": 0.9654719233512878
},
{
"epoch": 1.7223049117584521,
"global_step": 40500,
"eval_loss": 8.956608772277832,
"eval_cosine_accuracy": 0.9665141105651855
},
{
"epoch": 1.7435679353604083,
"global_step": 41000,
"eval_loss": 8.937081336975098,
"eval_cosine_accuracy": 0.96714848279953
},
{
"epoch": 1.7648309589623645,
"global_step": 41500,
"eval_loss": 8.94690227508545,
"eval_cosine_accuracy": 0.9666500687599182
},
{
"epoch": 1.7860939825643207,
"global_step": 42000,
"eval_loss": 8.9337797164917,
"eval_cosine_accuracy": 0.9672844409942627
},
{
"epoch": 1.807357006166277,
"global_step": 42500,
"eval_loss": 8.93774700164795,
"eval_cosine_accuracy": 0.9669219255447388
},
{
"epoch": 1.8286200297682331,
"global_step": 43000,
"eval_loss": 9.037887573242188,
"eval_cosine_accuracy": 0.965154767036438
},
{
"epoch": 1.8498830533701893,
"global_step": 43500,
"eval_loss": 9.061223030090332,
"eval_cosine_accuracy": 0.9658344388008118
},
{
"epoch": 1.8711460769721455,
"global_step": 44000,
"eval_loss": 9.144049644470215,
"eval_cosine_accuracy": 0.963840663433075
},
{
"epoch": 1.8924091005741017,
"global_step": 44500,
"eval_loss": 9.090474128723145,
"eval_cosine_accuracy": 0.9659703373908997
},
{
"epoch": 1.913672124176058,
"global_step": 45000,
"eval_loss": 9.179637908935547,
"eval_cosine_accuracy": 0.9629797339439392
},
{
"epoch": 1.9349351477780141,
"global_step": 45500,
"eval_loss": 9.226616859436035,
"eval_cosine_accuracy": 0.9639313220977783
},
{
"epoch": 1.9561981713799703,
"global_step": 46000,
"eval_loss": 9.134511947631836,
"eval_cosine_accuracy": 0.9655625820159912
},
{
"epoch": 1.9774611949819265,
"global_step": 46500,
"eval_loss": 9.34079647064209,
"eval_cosine_accuracy": 0.9636141061782837
},
{
"epoch": 1.9987242185838827,
"global_step": 47000,
"eval_loss": 9.222514152526855,
"eval_cosine_accuracy": 0.9648375511169434
}
],
"current_epoch": 2,
"global_step": 47030
}