MHGanainy's picture
MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-6
8819217 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 8676,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.011526048870447211,
"grad_norm": 0.19771268963813782,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.4498,
"step": 100
},
{
"epoch": 0.023052097740894423,
"grad_norm": 0.16720762848854065,
"learning_rate": 4.000000000000001e-06,
"loss": 2.4238,
"step": 200
},
{
"epoch": 0.034578146611341634,
"grad_norm": 0.2238711267709732,
"learning_rate": 6e-06,
"loss": 2.3975,
"step": 300
},
{
"epoch": 0.046104195481788846,
"grad_norm": 0.3389110565185547,
"learning_rate": 8.000000000000001e-06,
"loss": 2.3696,
"step": 400
},
{
"epoch": 0.05763024435223606,
"grad_norm": 0.38851398229599,
"learning_rate": 1e-05,
"loss": 2.2957,
"step": 500
},
{
"epoch": 0.06915629322268327,
"grad_norm": 0.4800083041191101,
"learning_rate": 1.2e-05,
"loss": 2.2861,
"step": 600
},
{
"epoch": 0.08068234209313048,
"grad_norm": 0.6024179458618164,
"learning_rate": 1.4e-05,
"loss": 2.2327,
"step": 700
},
{
"epoch": 0.09220839096357769,
"grad_norm": 0.6432300806045532,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.192,
"step": 800
},
{
"epoch": 0.1037344398340249,
"grad_norm": 0.8140468001365662,
"learning_rate": 1.8e-05,
"loss": 2.2126,
"step": 900
},
{
"epoch": 0.11526048870447211,
"grad_norm": 0.7425789833068848,
"learning_rate": 2e-05,
"loss": 2.1765,
"step": 1000
},
{
"epoch": 0.1267865375749193,
"grad_norm": 0.8718421459197998,
"learning_rate": 1.999162587972224e-05,
"loss": 2.1527,
"step": 1100
},
{
"epoch": 0.13831258644536654,
"grad_norm": 0.8124021887779236,
"learning_rate": 1.9966517544067045e-05,
"loss": 2.1203,
"step": 1200
},
{
"epoch": 0.14983863531581373,
"grad_norm": 0.7131963968276978,
"learning_rate": 1.9924717045078964e-05,
"loss": 2.0871,
"step": 1300
},
{
"epoch": 0.16136468418626096,
"grad_norm": 0.8409954309463501,
"learning_rate": 1.986629439123924e-05,
"loss": 2.1075,
"step": 1400
},
{
"epoch": 0.17289073305670816,
"grad_norm": 0.8746618628501892,
"learning_rate": 1.9791347430213906e-05,
"loss": 2.0631,
"step": 1500
},
{
"epoch": 0.18441678192715538,
"grad_norm": 0.8083209991455078,
"learning_rate": 1.970000168497618e-05,
"loss": 2.0434,
"step": 1600
},
{
"epoch": 0.19594283079760258,
"grad_norm": 0.7458757162094116,
"learning_rate": 1.9592410143577566e-05,
"loss": 2.0568,
"step": 1700
},
{
"epoch": 0.2074688796680498,
"grad_norm": 0.9946633577346802,
"learning_rate": 1.9468753002919764e-05,
"loss": 2.0231,
"step": 1800
},
{
"epoch": 0.218994928538497,
"grad_norm": 0.8859148025512695,
"learning_rate": 1.932923736695659e-05,
"loss": 2.015,
"step": 1900
},
{
"epoch": 0.23052097740894423,
"grad_norm": 0.7294831871986389,
"learning_rate": 1.917409689983128e-05,
"loss": 2.0288,
"step": 2000
},
{
"epoch": 0.24204702627939143,
"grad_norm": 1.2180194854736328,
"learning_rate": 1.900359143453017e-05,
"loss": 1.9958,
"step": 2100
},
{
"epoch": 0.2535730751498386,
"grad_norm": 0.8870425820350647,
"learning_rate": 1.8818006537708148e-05,
"loss": 2.0638,
"step": 2200
},
{
"epoch": 0.26509912402028585,
"grad_norm": 0.9545063376426697,
"learning_rate": 1.8617653031414752e-05,
"loss": 1.9911,
"step": 2300
},
{
"epoch": 0.2766251728907331,
"grad_norm": 1.0659151077270508,
"learning_rate": 1.8402866472521944e-05,
"loss": 1.9976,
"step": 2400
},
{
"epoch": 0.28815122176118024,
"grad_norm": 1.2996395826339722,
"learning_rate": 1.8174006590725364e-05,
"loss": 2.0412,
"step": 2500
},
{
"epoch": 0.29967727063162747,
"grad_norm": 1.068005919456482,
"learning_rate": 1.7931456686060396e-05,
"loss": 2.0828,
"step": 2600
},
{
"epoch": 0.3112033195020747,
"grad_norm": 0.814568281173706,
"learning_rate": 1.7675622986942045e-05,
"loss": 2.0401,
"step": 2700
},
{
"epoch": 0.3227293683725219,
"grad_norm": 1.509273648262024,
"learning_rate": 1.7406933969803815e-05,
"loss": 1.99,
"step": 2800
},
{
"epoch": 0.3342554172429691,
"grad_norm": 1.2622814178466797,
"learning_rate": 1.7125839641475074e-05,
"loss": 2.01,
"step": 2900
},
{
"epoch": 0.3457814661134163,
"grad_norm": 0.9653475284576416,
"learning_rate": 1.683281078549878e-05,
"loss": 2.0083,
"step": 3000
},
{
"epoch": 0.35730751498386354,
"grad_norm": 1.0271968841552734,
"learning_rate": 1.6528338173651898e-05,
"loss": 1.9546,
"step": 3100
},
{
"epoch": 0.36883356385431076,
"grad_norm": 0.8832419514656067,
"learning_rate": 1.6212931743989004e-05,
"loss": 1.9482,
"step": 3200
},
{
"epoch": 0.38035961272475793,
"grad_norm": 1.2330228090286255,
"learning_rate": 1.5887119746785776e-05,
"loss": 1.9766,
"step": 3300
},
{
"epoch": 0.39188566159520516,
"grad_norm": 0.9083070158958435,
"learning_rate": 1.5551447859812716e-05,
"loss": 1.9726,
"step": 3400
},
{
"epoch": 0.4034117104656524,
"grad_norm": 0.9940272569656372,
"learning_rate": 1.5206478274420895e-05,
"loss": 1.9762,
"step": 3500
},
{
"epoch": 0.4149377593360996,
"grad_norm": 0.9907180070877075,
"learning_rate": 1.4852788753970369e-05,
"loss": 1.9756,
"step": 3600
},
{
"epoch": 0.4264638082065468,
"grad_norm": 0.9995633363723755,
"learning_rate": 1.4490971666178177e-05,
"loss": 2.032,
"step": 3700
},
{
"epoch": 0.437989857076994,
"grad_norm": 1.0873900651931763,
"learning_rate": 1.412163299100667e-05,
"loss": 1.9659,
"step": 3800
},
{
"epoch": 0.44951590594744123,
"grad_norm": 0.8924662470817566,
"learning_rate": 1.3745391305753669e-05,
"loss": 1.989,
"step": 3900
},
{
"epoch": 0.46104195481788846,
"grad_norm": 0.8575798869132996,
"learning_rate": 1.3362876749044334e-05,
"loss": 2.0116,
"step": 4000
},
{
"epoch": 0.4725680036883356,
"grad_norm": 1.1529802083969116,
"learning_rate": 1.2974729965459843e-05,
"loss": 1.9598,
"step": 4100
},
{
"epoch": 0.48409405255878285,
"grad_norm": 1.0156272649765015,
"learning_rate": 1.2581601032570427e-05,
"loss": 1.9568,
"step": 4200
},
{
"epoch": 0.4956201014292301,
"grad_norm": 0.9686967134475708,
"learning_rate": 1.2184148372169826e-05,
"loss": 1.9608,
"step": 4300
},
{
"epoch": 0.5071461502996772,
"grad_norm": 0.9760933518409729,
"learning_rate": 1.1783037647534621e-05,
"loss": 1.9117,
"step": 4400
},
{
"epoch": 0.5186721991701245,
"grad_norm": 1.3244590759277344,
"learning_rate": 1.1378940648555367e-05,
"loss": 1.9626,
"step": 4500
},
{
"epoch": 0.5301982480405717,
"grad_norm": 1.1514652967453003,
"learning_rate": 1.0972534166606734e-05,
"loss": 1.9407,
"step": 4600
},
{
"epoch": 0.5417242969110189,
"grad_norm": 1.070824384689331,
"learning_rate": 1.0564498861041025e-05,
"loss": 1.9533,
"step": 4700
},
{
"epoch": 0.5532503457814661,
"grad_norm": 0.9388185739517212,
"learning_rate": 1.0155518119203511e-05,
"loss": 1.971,
"step": 4800
},
{
"epoch": 0.5647763946519133,
"grad_norm": 0.9750696420669556,
"learning_rate": 9.74627691187888e-06,
"loss": 1.9924,
"step": 4900
},
{
"epoch": 0.5763024435223605,
"grad_norm": 1.0221482515335083,
"learning_rate": 9.337460646085684e-06,
"loss": 1.9991,
"step": 5000
},
{
"epoch": 0.5878284923928078,
"grad_norm": 1.3475196361541748,
"learning_rate": 8.929754017140172e-06,
"loss": 1.9161,
"step": 5100
},
{
"epoch": 0.5993545412632549,
"grad_norm": 1.2582361698150635,
"learning_rate": 8.523839861912114e-06,
"loss": 1.9163,
"step": 5200
},
{
"epoch": 0.6108805901337022,
"grad_norm": 1.0771867036819458,
"learning_rate": 8.120398015193171e-06,
"loss": 1.9663,
"step": 5300
},
{
"epoch": 0.6224066390041494,
"grad_norm": 1.1660715341567993,
"learning_rate": 7.720104171093247e-06,
"loss": 1.956,
"step": 5400
},
{
"epoch": 0.6339326878745966,
"grad_norm": 1.200835943222046,
"learning_rate": 7.3236287513717275e-06,
"loss": 1.9511,
"step": 5500
},
{
"epoch": 0.6454587367450438,
"grad_norm": 0.9402092099189758,
"learning_rate": 6.931635782599e-06,
"loss": 1.9615,
"step": 5600
},
{
"epoch": 0.656984785615491,
"grad_norm": 0.8676489591598511,
"learning_rate": 6.544781784028769e-06,
"loss": 1.9899,
"step": 5700
},
{
"epoch": 0.6685108344859382,
"grad_norm": 0.9059965014457703,
"learning_rate": 6.163714668043834e-06,
"loss": 1.9786,
"step": 5800
},
{
"epoch": 0.6800368833563855,
"grad_norm": 1.3843269348144531,
"learning_rate": 5.789072655016817e-06,
"loss": 1.9591,
"step": 5900
},
{
"epoch": 0.6915629322268326,
"grad_norm": 1.0491424798965454,
"learning_rate": 5.421483204403355e-06,
"loss": 1.9437,
"step": 6000
},
{
"epoch": 0.7030889810972798,
"grad_norm": 0.8120349049568176,
"learning_rate": 5.061561963857914e-06,
"loss": 1.9221,
"step": 6100
},
{
"epoch": 0.7146150299677271,
"grad_norm": 0.9938396215438843,
"learning_rate": 4.709911738132252e-06,
"loss": 1.982,
"step": 6200
},
{
"epoch": 0.7261410788381742,
"grad_norm": 1.0250656604766846,
"learning_rate": 4.367121479483565e-06,
"loss": 1.9804,
"step": 6300
},
{
"epoch": 0.7376671277086215,
"grad_norm": 0.9957606792449951,
"learning_rate": 4.0337653012830365e-06,
"loss": 1.9699,
"step": 6400
},
{
"epoch": 0.7491931765790687,
"grad_norm": 1.3013089895248413,
"learning_rate": 3.710401516476997e-06,
"loss": 1.9395,
"step": 6500
},
{
"epoch": 0.7607192254495159,
"grad_norm": 0.9715898633003235,
"learning_rate": 3.397571702510918e-06,
"loss": 1.9448,
"step": 6600
},
{
"epoch": 0.7722452743199631,
"grad_norm": 0.9100465774536133,
"learning_rate": 3.0957997942825337e-06,
"loss": 1.9169,
"step": 6700
},
{
"epoch": 0.7837713231904103,
"grad_norm": 0.9665968418121338,
"learning_rate": 2.8055912066430314e-06,
"loss": 1.9538,
"step": 6800
},
{
"epoch": 0.7952973720608575,
"grad_norm": 1.5346043109893799,
"learning_rate": 2.52743198791612e-06,
"loss": 1.892,
"step": 6900
},
{
"epoch": 0.8068234209313048,
"grad_norm": 0.8448971509933472,
"learning_rate": 2.2617880058525942e-06,
"loss": 1.9466,
"step": 7000
},
{
"epoch": 0.8183494698017519,
"grad_norm": 1.1289533376693726,
"learning_rate": 2.009104167383833e-06,
"loss": 1.9142,
"step": 7100
},
{
"epoch": 0.8298755186721992,
"grad_norm": 0.9741213917732239,
"learning_rate": 1.769803673480942e-06,
"loss": 1.9677,
"step": 7200
},
{
"epoch": 0.8414015675426464,
"grad_norm": 1.1484721899032593,
"learning_rate": 1.544287310367625e-06,
"loss": 1.9834,
"step": 7300
},
{
"epoch": 0.8529276164130936,
"grad_norm": 1.4257473945617676,
"learning_rate": 1.332932778273739e-06,
"loss": 1.9686,
"step": 7400
},
{
"epoch": 0.8644536652835408,
"grad_norm": 1.19083833694458,
"learning_rate": 1.1360940588538883e-06,
"loss": 1.9588,
"step": 7500
},
{
"epoch": 0.875979714153988,
"grad_norm": 1.4401795864105225,
"learning_rate": 9.541008223304181e-07,
"loss": 1.9146,
"step": 7600
},
{
"epoch": 0.8875057630244352,
"grad_norm": 0.9895892143249512,
"learning_rate": 7.872578753538107e-07,
"loss": 1.9502,
"step": 7700
},
{
"epoch": 0.8990318118948825,
"grad_norm": 1.0904405117034912,
"learning_rate": 6.358446505051574e-07,
"loss": 1.947,
"step": 7800
},
{
"epoch": 0.9105578607653296,
"grad_norm": 1.1551321744918823,
"learning_rate": 5.001147382957639e-07,
"loss": 1.9828,
"step": 7900
},
{
"epoch": 0.9220839096357769,
"grad_norm": 1.3340507745742798,
"learning_rate": 3.802954624476585e-07,
"loss": 1.8885,
"step": 8000
},
{
"epoch": 0.9336099585062241,
"grad_norm": 0.9464887380599976,
"learning_rate": 2.7658749916634864e-07,
"loss": 1.9799,
"step": 8100
},
{
"epoch": 0.9451360073766712,
"grad_norm": 1.0508813858032227,
"learning_rate": 1.8916454104349058e-07,
"loss": 1.9436,
"step": 8200
},
{
"epoch": 0.9566620562471185,
"grad_norm": 1.4017341136932373,
"learning_rate": 1.1817300615235672e-07,
"loss": 1.9354,
"step": 8300
},
{
"epoch": 0.9681881051175657,
"grad_norm": 0.9612733125686646,
"learning_rate": 6.373179282332275e-08,
"loss": 1.9696,
"step": 8400
},
{
"epoch": 0.9797141539880129,
"grad_norm": 1.061047911643982,
"learning_rate": 2.6227471163585705e-08,
"loss": 1.9373,
"step": 8500
},
{
"epoch": 0.9912402028584602,
"grad_norm": 1.4511463642120361,
"learning_rate": 4.965298070647162e-09,
"loss": 1.925,
"step": 8600
},
{
"epoch": 1.0,
"step": 8676,
"total_flos": 1.58472345255936e+17,
"train_loss": 2.0172890398896968,
"train_runtime": 2382.4555,
"train_samples_per_second": 7.283,
"train_steps_per_second": 3.642
}
],
"logging_steps": 100,
"max_steps": 8676,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.58472345255936e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}