sedrickkeh's picture
End of training
dcb77cc verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9954430379746837,
"eval_steps": 500,
"global_step": 1479,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020253164556962026,
"grad_norm": 8.556459004852009,
"learning_rate": 3.378378378378379e-07,
"loss": 0.8354,
"step": 10
},
{
"epoch": 0.04050632911392405,
"grad_norm": 3.681642301527027,
"learning_rate": 6.756756756756758e-07,
"loss": 0.7599,
"step": 20
},
{
"epoch": 0.060759493670886074,
"grad_norm": 1.726936094306069,
"learning_rate": 1.0135135135135136e-06,
"loss": 0.6959,
"step": 30
},
{
"epoch": 0.0810126582278481,
"grad_norm": 2.37353153377641,
"learning_rate": 1.3513513513513515e-06,
"loss": 0.6575,
"step": 40
},
{
"epoch": 0.10126582278481013,
"grad_norm": 2.0089356033589145,
"learning_rate": 1.6891891891891894e-06,
"loss": 0.6351,
"step": 50
},
{
"epoch": 0.12151898734177215,
"grad_norm": 1.391624997798933,
"learning_rate": 2.0270270270270273e-06,
"loss": 0.6213,
"step": 60
},
{
"epoch": 0.14177215189873418,
"grad_norm": 1.6331791503446509,
"learning_rate": 2.364864864864865e-06,
"loss": 0.6121,
"step": 70
},
{
"epoch": 0.1620253164556962,
"grad_norm": 2.381527517296881,
"learning_rate": 2.702702702702703e-06,
"loss": 0.6048,
"step": 80
},
{
"epoch": 0.18227848101265823,
"grad_norm": 2.1493391697359403,
"learning_rate": 3.040540540540541e-06,
"loss": 0.6016,
"step": 90
},
{
"epoch": 0.20253164556962025,
"grad_norm": 2.907906626199151,
"learning_rate": 3.3783783783783788e-06,
"loss": 0.6034,
"step": 100
},
{
"epoch": 0.22278481012658227,
"grad_norm": 2.742004973375118,
"learning_rate": 3.7162162162162162e-06,
"loss": 0.5956,
"step": 110
},
{
"epoch": 0.2430379746835443,
"grad_norm": 2.7366062341726476,
"learning_rate": 4.0540540540540545e-06,
"loss": 0.592,
"step": 120
},
{
"epoch": 0.26329113924050634,
"grad_norm": 2.61940583080256,
"learning_rate": 4.391891891891892e-06,
"loss": 0.5894,
"step": 130
},
{
"epoch": 0.28354430379746837,
"grad_norm": 2.2813205470058837,
"learning_rate": 4.72972972972973e-06,
"loss": 0.5782,
"step": 140
},
{
"epoch": 0.3037974683544304,
"grad_norm": 2.5170304525110594,
"learning_rate": 4.992486851990984e-06,
"loss": 0.5882,
"step": 150
},
{
"epoch": 0.3240506329113924,
"grad_norm": 1.9290797099657084,
"learning_rate": 4.954921111945906e-06,
"loss": 0.5859,
"step": 160
},
{
"epoch": 0.34430379746835443,
"grad_norm": 1.4336818702016718,
"learning_rate": 4.917355371900827e-06,
"loss": 0.5874,
"step": 170
},
{
"epoch": 0.36455696202531646,
"grad_norm": 1.8411955872042784,
"learning_rate": 4.879789631855748e-06,
"loss": 0.583,
"step": 180
},
{
"epoch": 0.3848101265822785,
"grad_norm": 1.6410006944167816,
"learning_rate": 4.842223891810669e-06,
"loss": 0.5823,
"step": 190
},
{
"epoch": 0.4050632911392405,
"grad_norm": 1.8701658637773764,
"learning_rate": 4.80465815176559e-06,
"loss": 0.5779,
"step": 200
},
{
"epoch": 0.4253164556962025,
"grad_norm": 1.8645518662157583,
"learning_rate": 4.767092411720512e-06,
"loss": 0.5731,
"step": 210
},
{
"epoch": 0.44556962025316454,
"grad_norm": 1.4882959577748913,
"learning_rate": 4.729526671675433e-06,
"loss": 0.5769,
"step": 220
},
{
"epoch": 0.46582278481012657,
"grad_norm": 1.3995352940191192,
"learning_rate": 4.6919609316303534e-06,
"loss": 0.5754,
"step": 230
},
{
"epoch": 0.4860759493670886,
"grad_norm": 1.6983010693170986,
"learning_rate": 4.654395191585275e-06,
"loss": 0.5708,
"step": 240
},
{
"epoch": 0.5063291139240507,
"grad_norm": 2.061097436379402,
"learning_rate": 4.616829451540196e-06,
"loss": 0.5743,
"step": 250
},
{
"epoch": 0.5265822784810127,
"grad_norm": 2.0033851006854624,
"learning_rate": 4.579263711495117e-06,
"loss": 0.5597,
"step": 260
},
{
"epoch": 0.5468354430379747,
"grad_norm": 1.4371666580128166,
"learning_rate": 4.541697971450038e-06,
"loss": 0.568,
"step": 270
},
{
"epoch": 0.5670886075949367,
"grad_norm": 1.5842138481650203,
"learning_rate": 4.504132231404959e-06,
"loss": 0.5636,
"step": 280
},
{
"epoch": 0.5873417721518988,
"grad_norm": 1.4152120878177024,
"learning_rate": 4.46656649135988e-06,
"loss": 0.5642,
"step": 290
},
{
"epoch": 0.6075949367088608,
"grad_norm": 1.5290735652174632,
"learning_rate": 4.429000751314802e-06,
"loss": 0.5635,
"step": 300
},
{
"epoch": 0.6278481012658228,
"grad_norm": 1.3811776146486536,
"learning_rate": 4.3914350112697225e-06,
"loss": 0.5685,
"step": 310
},
{
"epoch": 0.6481012658227848,
"grad_norm": 1.2489817397894598,
"learning_rate": 4.353869271224643e-06,
"loss": 0.5645,
"step": 320
},
{
"epoch": 0.6683544303797468,
"grad_norm": 1.38609447055016,
"learning_rate": 4.316303531179565e-06,
"loss": 0.5643,
"step": 330
},
{
"epoch": 0.6886075949367089,
"grad_norm": 1.5318268452835269,
"learning_rate": 4.278737791134486e-06,
"loss": 0.5636,
"step": 340
},
{
"epoch": 0.7088607594936709,
"grad_norm": 1.4550855449189222,
"learning_rate": 4.2411720510894065e-06,
"loss": 0.5646,
"step": 350
},
{
"epoch": 0.7291139240506329,
"grad_norm": 1.4357986151802806,
"learning_rate": 4.203606311044328e-06,
"loss": 0.5659,
"step": 360
},
{
"epoch": 0.7493670886075949,
"grad_norm": 1.4758039776130085,
"learning_rate": 4.166040570999249e-06,
"loss": 0.5581,
"step": 370
},
{
"epoch": 0.769620253164557,
"grad_norm": 1.4285167058069708,
"learning_rate": 4.12847483095417e-06,
"loss": 0.5548,
"step": 380
},
{
"epoch": 0.789873417721519,
"grad_norm": 1.7405622458735588,
"learning_rate": 4.0909090909090915e-06,
"loss": 0.5581,
"step": 390
},
{
"epoch": 0.810126582278481,
"grad_norm": 1.7189240150684444,
"learning_rate": 4.053343350864012e-06,
"loss": 0.558,
"step": 400
},
{
"epoch": 0.830379746835443,
"grad_norm": 1.6501569274132042,
"learning_rate": 4.015777610818933e-06,
"loss": 0.5519,
"step": 410
},
{
"epoch": 0.850632911392405,
"grad_norm": 1.6731630114484979,
"learning_rate": 3.978211870773855e-06,
"loss": 0.5587,
"step": 420
},
{
"epoch": 0.8708860759493671,
"grad_norm": 2.1187915177073178,
"learning_rate": 3.9406461307287756e-06,
"loss": 0.5513,
"step": 430
},
{
"epoch": 0.8911392405063291,
"grad_norm": 1.5433420890497953,
"learning_rate": 3.903080390683696e-06,
"loss": 0.5564,
"step": 440
},
{
"epoch": 0.9113924050632911,
"grad_norm": 1.8747825342264348,
"learning_rate": 3.865514650638618e-06,
"loss": 0.5471,
"step": 450
},
{
"epoch": 0.9316455696202531,
"grad_norm": 1.59749808793934,
"learning_rate": 3.827948910593539e-06,
"loss": 0.5517,
"step": 460
},
{
"epoch": 0.9518987341772152,
"grad_norm": 1.703614465575271,
"learning_rate": 3.79038317054846e-06,
"loss": 0.5527,
"step": 470
},
{
"epoch": 0.9721518987341772,
"grad_norm": 1.6904288437756008,
"learning_rate": 3.752817430503381e-06,
"loss": 0.5499,
"step": 480
},
{
"epoch": 0.9924050632911392,
"grad_norm": 1.2436069436662953,
"learning_rate": 3.7152516904583025e-06,
"loss": 0.5465,
"step": 490
},
{
"epoch": 0.9984810126582279,
"eval_loss": 0.0686691552400589,
"eval_runtime": 504.1479,
"eval_samples_per_second": 26.389,
"eval_steps_per_second": 0.413,
"step": 493
},
{
"epoch": 1.0126582278481013,
"grad_norm": 1.8140129271933714,
"learning_rate": 3.6776859504132234e-06,
"loss": 0.5154,
"step": 500
},
{
"epoch": 1.0329113924050632,
"grad_norm": 1.2711128895195876,
"learning_rate": 3.640120210368144e-06,
"loss": 0.4864,
"step": 510
},
{
"epoch": 1.0531645569620254,
"grad_norm": 1.594060189939638,
"learning_rate": 3.602554470323066e-06,
"loss": 0.4845,
"step": 520
},
{
"epoch": 1.0734177215189873,
"grad_norm": 1.5462198272155392,
"learning_rate": 3.5649887302779866e-06,
"loss": 0.4869,
"step": 530
},
{
"epoch": 1.0936708860759494,
"grad_norm": 1.3581074119881988,
"learning_rate": 3.527422990232908e-06,
"loss": 0.4847,
"step": 540
},
{
"epoch": 1.1139240506329113,
"grad_norm": 1.413570881088854,
"learning_rate": 3.489857250187829e-06,
"loss": 0.4866,
"step": 550
},
{
"epoch": 1.1341772151898735,
"grad_norm": 1.2703043443689073,
"learning_rate": 3.45229151014275e-06,
"loss": 0.484,
"step": 560
},
{
"epoch": 1.1544303797468354,
"grad_norm": 1.2116910881911624,
"learning_rate": 3.414725770097671e-06,
"loss": 0.49,
"step": 570
},
{
"epoch": 1.1746835443037975,
"grad_norm": 1.22591839207132,
"learning_rate": 3.3771600300525924e-06,
"loss": 0.4883,
"step": 580
},
{
"epoch": 1.1949367088607594,
"grad_norm": 1.1731315032521277,
"learning_rate": 3.3395942900075136e-06,
"loss": 0.4823,
"step": 590
},
{
"epoch": 1.2151898734177216,
"grad_norm": 1.2756842843152258,
"learning_rate": 3.3020285499624344e-06,
"loss": 0.4894,
"step": 600
},
{
"epoch": 1.2354430379746835,
"grad_norm": 1.3941039610425434,
"learning_rate": 3.264462809917356e-06,
"loss": 0.485,
"step": 610
},
{
"epoch": 1.2556962025316456,
"grad_norm": 1.2927381511779246,
"learning_rate": 3.226897069872277e-06,
"loss": 0.4891,
"step": 620
},
{
"epoch": 1.2759493670886077,
"grad_norm": 1.239246362421845,
"learning_rate": 3.1893313298271977e-06,
"loss": 0.4884,
"step": 630
},
{
"epoch": 1.2962025316455696,
"grad_norm": 1.4428586131832628,
"learning_rate": 3.1517655897821194e-06,
"loss": 0.4875,
"step": 640
},
{
"epoch": 1.3164556962025316,
"grad_norm": 1.1942547572789066,
"learning_rate": 3.11419984973704e-06,
"loss": 0.4911,
"step": 650
},
{
"epoch": 1.3367088607594937,
"grad_norm": 1.2924811153254836,
"learning_rate": 3.076634109691961e-06,
"loss": 0.4794,
"step": 660
},
{
"epoch": 1.3569620253164558,
"grad_norm": 1.345772029679538,
"learning_rate": 3.0390683696468826e-06,
"loss": 0.4929,
"step": 670
},
{
"epoch": 1.3772151898734177,
"grad_norm": 1.1190552420786224,
"learning_rate": 3.0015026296018034e-06,
"loss": 0.4897,
"step": 680
},
{
"epoch": 1.3974683544303796,
"grad_norm": 1.196893927879723,
"learning_rate": 2.9639368895567243e-06,
"loss": 0.4891,
"step": 690
},
{
"epoch": 1.4177215189873418,
"grad_norm": 1.2638908138618863,
"learning_rate": 2.9263711495116455e-06,
"loss": 0.4847,
"step": 700
},
{
"epoch": 1.437974683544304,
"grad_norm": 1.1163514888014268,
"learning_rate": 2.8888054094665667e-06,
"loss": 0.4906,
"step": 710
},
{
"epoch": 1.4582278481012658,
"grad_norm": 1.155377067438078,
"learning_rate": 2.851239669421488e-06,
"loss": 0.4898,
"step": 720
},
{
"epoch": 1.4784810126582277,
"grad_norm": 1.2738771806551292,
"learning_rate": 2.8136739293764088e-06,
"loss": 0.4922,
"step": 730
},
{
"epoch": 1.4987341772151899,
"grad_norm": 1.2452118202307745,
"learning_rate": 2.77610818933133e-06,
"loss": 0.4845,
"step": 740
},
{
"epoch": 1.518987341772152,
"grad_norm": 1.219390205919516,
"learning_rate": 2.7385424492862512e-06,
"loss": 0.4872,
"step": 750
},
{
"epoch": 1.539240506329114,
"grad_norm": 1.3476108111898892,
"learning_rate": 2.700976709241172e-06,
"loss": 0.4874,
"step": 760
},
{
"epoch": 1.5594936708860758,
"grad_norm": 1.1947882615361192,
"learning_rate": 2.6634109691960937e-06,
"loss": 0.4854,
"step": 770
},
{
"epoch": 1.579746835443038,
"grad_norm": 1.2664227895565825,
"learning_rate": 2.6258452291510145e-06,
"loss": 0.4863,
"step": 780
},
{
"epoch": 1.6,
"grad_norm": 1.0918882362910753,
"learning_rate": 2.5882794891059353e-06,
"loss": 0.4884,
"step": 790
},
{
"epoch": 1.620253164556962,
"grad_norm": 1.1799041159893287,
"learning_rate": 2.550713749060857e-06,
"loss": 0.4843,
"step": 800
},
{
"epoch": 1.640506329113924,
"grad_norm": 1.2814036637876116,
"learning_rate": 2.513148009015778e-06,
"loss": 0.4774,
"step": 810
},
{
"epoch": 1.660759493670886,
"grad_norm": 1.215664740050223,
"learning_rate": 2.475582268970699e-06,
"loss": 0.4856,
"step": 820
},
{
"epoch": 1.6810126582278482,
"grad_norm": 1.1813078713632477,
"learning_rate": 2.43801652892562e-06,
"loss": 0.4808,
"step": 830
},
{
"epoch": 1.70126582278481,
"grad_norm": 1.1757543183194046,
"learning_rate": 2.400450788880541e-06,
"loss": 0.4813,
"step": 840
},
{
"epoch": 1.721518987341772,
"grad_norm": 1.1411860521089428,
"learning_rate": 2.3628850488354623e-06,
"loss": 0.4834,
"step": 850
},
{
"epoch": 1.7417721518987341,
"grad_norm": 1.0342492999295814,
"learning_rate": 2.325319308790383e-06,
"loss": 0.4832,
"step": 860
},
{
"epoch": 1.7620253164556963,
"grad_norm": 1.1434911938672212,
"learning_rate": 2.2877535687453044e-06,
"loss": 0.4866,
"step": 870
},
{
"epoch": 1.7822784810126582,
"grad_norm": 1.246279092334059,
"learning_rate": 2.2501878287002256e-06,
"loss": 0.4871,
"step": 880
},
{
"epoch": 1.80253164556962,
"grad_norm": 1.1509212405407068,
"learning_rate": 2.212622088655147e-06,
"loss": 0.4845,
"step": 890
},
{
"epoch": 1.8227848101265822,
"grad_norm": 1.2639874530877144,
"learning_rate": 2.175056348610068e-06,
"loss": 0.483,
"step": 900
},
{
"epoch": 1.8430379746835444,
"grad_norm": 1.2029946729772611,
"learning_rate": 2.137490608564989e-06,
"loss": 0.4852,
"step": 910
},
{
"epoch": 1.8632911392405065,
"grad_norm": 1.1169305596935761,
"learning_rate": 2.09992486851991e-06,
"loss": 0.4831,
"step": 920
},
{
"epoch": 1.8835443037974684,
"grad_norm": 1.09196132946494,
"learning_rate": 2.0623591284748313e-06,
"loss": 0.4794,
"step": 930
},
{
"epoch": 1.9037974683544303,
"grad_norm": 1.089272978011173,
"learning_rate": 2.024793388429752e-06,
"loss": 0.483,
"step": 940
},
{
"epoch": 1.9240506329113924,
"grad_norm": 1.0410920443753975,
"learning_rate": 1.9872276483846734e-06,
"loss": 0.4846,
"step": 950
},
{
"epoch": 1.9443037974683546,
"grad_norm": 1.1956033603187548,
"learning_rate": 1.9496619083395946e-06,
"loss": 0.4879,
"step": 960
},
{
"epoch": 1.9645569620253165,
"grad_norm": 1.0920561603907453,
"learning_rate": 1.9120961682945154e-06,
"loss": 0.4866,
"step": 970
},
{
"epoch": 1.9848101265822784,
"grad_norm": 1.0451509677263875,
"learning_rate": 1.8745304282494367e-06,
"loss": 0.4856,
"step": 980
},
{
"epoch": 1.998987341772152,
"eval_loss": 0.06770560145378113,
"eval_runtime": 506.4671,
"eval_samples_per_second": 26.268,
"eval_steps_per_second": 0.411,
"step": 987
},
{
"epoch": 2.0050632911392405,
"grad_norm": 1.8162363718859433,
"learning_rate": 1.8369646882043577e-06,
"loss": 0.4629,
"step": 990
},
{
"epoch": 2.0253164556962027,
"grad_norm": 1.5873140436853967,
"learning_rate": 1.799398948159279e-06,
"loss": 0.4148,
"step": 1000
},
{
"epoch": 2.0455696202531644,
"grad_norm": 1.3250480015078225,
"learning_rate": 1.7618332081142001e-06,
"loss": 0.4141,
"step": 1010
},
{
"epoch": 2.0658227848101265,
"grad_norm": 1.2559122162053822,
"learning_rate": 1.724267468069121e-06,
"loss": 0.4097,
"step": 1020
},
{
"epoch": 2.0860759493670886,
"grad_norm": 1.11730327433827,
"learning_rate": 1.6867017280240422e-06,
"loss": 0.4098,
"step": 1030
},
{
"epoch": 2.1063291139240508,
"grad_norm": 1.1488792674788184,
"learning_rate": 1.6491359879789634e-06,
"loss": 0.4063,
"step": 1040
},
{
"epoch": 2.1265822784810124,
"grad_norm": 1.2194570653560266,
"learning_rate": 1.6115702479338842e-06,
"loss": 0.4148,
"step": 1050
},
{
"epoch": 2.1468354430379746,
"grad_norm": 1.2246780862208726,
"learning_rate": 1.5740045078888055e-06,
"loss": 0.4095,
"step": 1060
},
{
"epoch": 2.1670886075949367,
"grad_norm": 1.1221422744938137,
"learning_rate": 1.5364387678437267e-06,
"loss": 0.4124,
"step": 1070
},
{
"epoch": 2.187341772151899,
"grad_norm": 1.1845225517845253,
"learning_rate": 1.4988730277986477e-06,
"loss": 0.4106,
"step": 1080
},
{
"epoch": 2.207594936708861,
"grad_norm": 1.151643245126613,
"learning_rate": 1.461307287753569e-06,
"loss": 0.4079,
"step": 1090
},
{
"epoch": 2.2278481012658227,
"grad_norm": 1.1727300795743778,
"learning_rate": 1.4237415477084902e-06,
"loss": 0.4166,
"step": 1100
},
{
"epoch": 2.248101265822785,
"grad_norm": 1.140792166225886,
"learning_rate": 1.386175807663411e-06,
"loss": 0.4123,
"step": 1110
},
{
"epoch": 2.268354430379747,
"grad_norm": 1.1592975056739614,
"learning_rate": 1.3486100676183322e-06,
"loss": 0.413,
"step": 1120
},
{
"epoch": 2.2886075949367086,
"grad_norm": 1.144847715133614,
"learning_rate": 1.3110443275732533e-06,
"loss": 0.4142,
"step": 1130
},
{
"epoch": 2.3088607594936708,
"grad_norm": 1.094302060235976,
"learning_rate": 1.2734785875281743e-06,
"loss": 0.409,
"step": 1140
},
{
"epoch": 2.329113924050633,
"grad_norm": 1.8324152294122444,
"learning_rate": 1.2359128474830955e-06,
"loss": 0.4157,
"step": 1150
},
{
"epoch": 2.349367088607595,
"grad_norm": 1.1755976482888877,
"learning_rate": 1.1983471074380167e-06,
"loss": 0.4155,
"step": 1160
},
{
"epoch": 2.369620253164557,
"grad_norm": 1.1610490026245264,
"learning_rate": 1.1607813673929378e-06,
"loss": 0.4143,
"step": 1170
},
{
"epoch": 2.389873417721519,
"grad_norm": 1.1593249771779028,
"learning_rate": 1.1232156273478588e-06,
"loss": 0.4143,
"step": 1180
},
{
"epoch": 2.410126582278481,
"grad_norm": 1.2447447706790171,
"learning_rate": 1.08564988730278e-06,
"loss": 0.4134,
"step": 1190
},
{
"epoch": 2.430379746835443,
"grad_norm": 1.117095640965601,
"learning_rate": 1.048084147257701e-06,
"loss": 0.4113,
"step": 1200
},
{
"epoch": 2.4506329113924052,
"grad_norm": 1.1370447334516511,
"learning_rate": 1.010518407212622e-06,
"loss": 0.4107,
"step": 1210
},
{
"epoch": 2.470886075949367,
"grad_norm": 1.181102859042412,
"learning_rate": 9.729526671675433e-07,
"loss": 0.4137,
"step": 1220
},
{
"epoch": 2.491139240506329,
"grad_norm": 1.2140589114207827,
"learning_rate": 9.353869271224644e-07,
"loss": 0.4123,
"step": 1230
},
{
"epoch": 2.511392405063291,
"grad_norm": 1.1778505184014514,
"learning_rate": 8.978211870773855e-07,
"loss": 0.4162,
"step": 1240
},
{
"epoch": 2.5316455696202533,
"grad_norm": 1.1699977693871288,
"learning_rate": 8.602554470323066e-07,
"loss": 0.4094,
"step": 1250
},
{
"epoch": 2.5518987341772155,
"grad_norm": 1.124119808595154,
"learning_rate": 8.226897069872278e-07,
"loss": 0.4041,
"step": 1260
},
{
"epoch": 2.572151898734177,
"grad_norm": 1.131590151917583,
"learning_rate": 7.851239669421488e-07,
"loss": 0.411,
"step": 1270
},
{
"epoch": 2.5924050632911393,
"grad_norm": 1.1610048489913083,
"learning_rate": 7.4755822689707e-07,
"loss": 0.4127,
"step": 1280
},
{
"epoch": 2.6126582278481014,
"grad_norm": 1.175325258081783,
"learning_rate": 7.09992486851991e-07,
"loss": 0.4181,
"step": 1290
},
{
"epoch": 2.632911392405063,
"grad_norm": 1.1266790071767538,
"learning_rate": 6.724267468069122e-07,
"loss": 0.4114,
"step": 1300
},
{
"epoch": 2.6531645569620252,
"grad_norm": 1.1274406714120246,
"learning_rate": 6.348610067618332e-07,
"loss": 0.4104,
"step": 1310
},
{
"epoch": 2.6734177215189874,
"grad_norm": 1.0855642192635904,
"learning_rate": 5.972952667167544e-07,
"loss": 0.4119,
"step": 1320
},
{
"epoch": 2.6936708860759495,
"grad_norm": 1.0950717526822358,
"learning_rate": 5.597295266716755e-07,
"loss": 0.4145,
"step": 1330
},
{
"epoch": 2.7139240506329116,
"grad_norm": 1.1434523085263464,
"learning_rate": 5.221637866265966e-07,
"loss": 0.4124,
"step": 1340
},
{
"epoch": 2.7341772151898733,
"grad_norm": 1.105475212905674,
"learning_rate": 4.845980465815176e-07,
"loss": 0.4104,
"step": 1350
},
{
"epoch": 2.7544303797468355,
"grad_norm": 1.0837702546358798,
"learning_rate": 4.4703230653643883e-07,
"loss": 0.4063,
"step": 1360
},
{
"epoch": 2.7746835443037976,
"grad_norm": 1.1427611200757817,
"learning_rate": 4.094665664913599e-07,
"loss": 0.4114,
"step": 1370
},
{
"epoch": 2.7949367088607593,
"grad_norm": 1.0776017124660127,
"learning_rate": 3.7190082644628103e-07,
"loss": 0.4092,
"step": 1380
},
{
"epoch": 2.8151898734177214,
"grad_norm": 1.335687040637302,
"learning_rate": 3.343350864012021e-07,
"loss": 0.4121,
"step": 1390
},
{
"epoch": 2.8354430379746836,
"grad_norm": 1.067862661628945,
"learning_rate": 2.9676934635612324e-07,
"loss": 0.4045,
"step": 1400
},
{
"epoch": 2.8556962025316457,
"grad_norm": 1.083663558722376,
"learning_rate": 2.5920360631104436e-07,
"loss": 0.4132,
"step": 1410
},
{
"epoch": 2.875949367088608,
"grad_norm": 1.0900237221256193,
"learning_rate": 2.2163786626596544e-07,
"loss": 0.4077,
"step": 1420
},
{
"epoch": 2.8962025316455695,
"grad_norm": 1.1077884473894029,
"learning_rate": 1.8407212622088657e-07,
"loss": 0.4089,
"step": 1430
},
{
"epoch": 2.9164556962025316,
"grad_norm": 1.0569922478203235,
"learning_rate": 1.4650638617580767e-07,
"loss": 0.4108,
"step": 1440
},
{
"epoch": 2.9367088607594938,
"grad_norm": 1.0634188950315056,
"learning_rate": 1.0894064613072878e-07,
"loss": 0.4193,
"step": 1450
},
{
"epoch": 2.9569620253164555,
"grad_norm": 1.0687631065939336,
"learning_rate": 7.13749060856499e-08,
"loss": 0.4063,
"step": 1460
},
{
"epoch": 2.9772151898734176,
"grad_norm": 1.0945464445026132,
"learning_rate": 3.3809166040571e-08,
"loss": 0.4105,
"step": 1470
},
{
"epoch": 2.9954430379746837,
"eval_loss": 0.0698537528514862,
"eval_runtime": 508.665,
"eval_samples_per_second": 26.155,
"eval_steps_per_second": 0.409,
"step": 1479
},
{
"epoch": 2.9954430379746837,
"step": 1479,
"total_flos": 2477170706350080.0,
"train_loss": 0.494840882935179,
"train_runtime": 84658.1688,
"train_samples_per_second": 8.957,
"train_steps_per_second": 0.017
}
],
"logging_steps": 10,
"max_steps": 1479,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2477170706350080.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}