wangrongsheng's picture
add v1
43646eb
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.699235344095157,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.999919851200522e-05,
"loss": 9.9461,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.9996428002198536e-05,
"loss": 6.4908,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 4.9992242747551964e-05,
"loss": 3.708,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.99857130295276e-05,
"loss": 0.8908,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.997720546222574e-05,
"loss": 0.2454,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 4.996672071909866e-05,
"loss": 0.1348,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 4.995425963011034e-05,
"loss": 0.0487,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 4.993982318167074e-05,
"loss": 0.0282,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 4.992341251655768e-05,
"loss": 0.0455,
"step": 90
},
{
"epoch": 0.08,
"learning_rate": 4.9905028933826435e-05,
"loss": 0.0472,
"step": 100
},
{
"epoch": 0.09,
"learning_rate": 4.988467388870688e-05,
"loss": 0.0526,
"step": 110
},
{
"epoch": 0.1,
"learning_rate": 4.986234899248826e-05,
"loss": 0.0679,
"step": 120
},
{
"epoch": 0.11,
"learning_rate": 4.983805601239172e-05,
"loss": 0.0314,
"step": 130
},
{
"epoch": 0.12,
"learning_rate": 4.981179687143034e-05,
"loss": 0.0136,
"step": 140
},
{
"epoch": 0.13,
"learning_rate": 4.978357364825695e-05,
"loss": 0.0409,
"step": 150
},
{
"epoch": 0.14,
"learning_rate": 4.975338857699956e-05,
"loss": 0.0284,
"step": 160
},
{
"epoch": 0.14,
"learning_rate": 4.972124404708454e-05,
"loss": 0.0364,
"step": 170
},
{
"epoch": 0.15,
"learning_rate": 4.968714260304743e-05,
"loss": 0.0147,
"step": 180
},
{
"epoch": 0.16,
"learning_rate": 4.965108694433159e-05,
"loss": 0.0174,
"step": 190
},
{
"epoch": 0.17,
"learning_rate": 4.961307992507443e-05,
"loss": 0.0244,
"step": 200
},
{
"epoch": 0.18,
"learning_rate": 4.957312455388152e-05,
"loss": 0.0387,
"step": 210
},
{
"epoch": 0.19,
"learning_rate": 4.953122399358845e-05,
"loss": 0.0264,
"step": 220
},
{
"epoch": 0.2,
"learning_rate": 4.948738156101042e-05,
"loss": 0.0291,
"step": 230
},
{
"epoch": 0.2,
"learning_rate": 4.9441600726679694e-05,
"loss": 0.0214,
"step": 240
},
{
"epoch": 0.21,
"learning_rate": 4.939388511457092e-05,
"loss": 0.0116,
"step": 250
},
{
"epoch": 0.22,
"learning_rate": 4.934423850181419e-05,
"loss": 0.0191,
"step": 260
},
{
"epoch": 0.23,
"learning_rate": 4.9292664818396117e-05,
"loss": 0.0064,
"step": 270
},
{
"epoch": 0.24,
"learning_rate": 4.9239168146848666e-05,
"loss": 0.0184,
"step": 280
},
{
"epoch": 0.25,
"learning_rate": 4.9183752721926036e-05,
"loss": 0.0026,
"step": 290
},
{
"epoch": 0.25,
"learning_rate": 4.912642293026942e-05,
"loss": 0.0223,
"step": 300
},
{
"epoch": 0.26,
"learning_rate": 4.906718331005979e-05,
"loss": 0.0405,
"step": 310
},
{
"epoch": 0.27,
"learning_rate": 4.900603855065861e-05,
"loss": 0.0461,
"step": 320
},
{
"epoch": 0.28,
"learning_rate": 4.894299349223665e-05,
"loss": 0.0199,
"step": 330
},
{
"epoch": 0.29,
"learning_rate": 4.8878053125390875e-05,
"loss": 0.0193,
"step": 340
},
{
"epoch": 0.3,
"learning_rate": 4.881122259074935e-05,
"loss": 0.004,
"step": 350
},
{
"epoch": 0.31,
"learning_rate": 4.874250717856433e-05,
"loss": 0.0018,
"step": 360
},
{
"epoch": 0.31,
"learning_rate": 4.867191232829348e-05,
"loss": 0.0021,
"step": 370
},
{
"epoch": 0.32,
"learning_rate": 4.8599443628169295e-05,
"loss": 0.018,
"step": 380
},
{
"epoch": 0.33,
"learning_rate": 4.8525106814756754e-05,
"loss": 0.0261,
"step": 390
},
{
"epoch": 0.34,
"learning_rate": 4.84489077724992e-05,
"loss": 0.016,
"step": 400
},
{
"epoch": 0.35,
"learning_rate": 4.8370852533252536e-05,
"loss": 0.0402,
"step": 410
},
{
"epoch": 0.36,
"learning_rate": 4.8290947275807755e-05,
"loss": 0.0038,
"step": 420
},
{
"epoch": 0.37,
"learning_rate": 4.8209198325401815e-05,
"loss": 0.008,
"step": 430
},
{
"epoch": 0.37,
"learning_rate": 4.8125612153216976e-05,
"loss": 0.0296,
"step": 440
},
{
"epoch": 0.38,
"learning_rate": 4.804019537586849e-05,
"loss": 0.0012,
"step": 450
},
{
"epoch": 0.39,
"learning_rate": 4.7952954754880886e-05,
"loss": 0.0142,
"step": 460
},
{
"epoch": 0.4,
"learning_rate": 4.7863897196152704e-05,
"loss": 0.0163,
"step": 470
},
{
"epoch": 0.41,
"learning_rate": 4.7773029749409836e-05,
"loss": 0.0021,
"step": 480
},
{
"epoch": 0.42,
"learning_rate": 4.76803596076475e-05,
"loss": 0.0355,
"step": 490
},
{
"epoch": 0.42,
"learning_rate": 4.758589410656078e-05,
"loss": 0.0199,
"step": 500
},
{
"epoch": 0.42,
"eval_loss": 0.010466881096363068,
"eval_runtime": 88.037,
"eval_samples_per_second": 22.525,
"eval_steps_per_second": 2.817,
"step": 500
},
{
"epoch": 0.43,
"learning_rate": 4.748964072396403e-05,
"loss": 0.0341,
"step": 510
},
{
"epoch": 0.44,
"learning_rate": 4.7391607079198876e-05,
"loss": 0.0137,
"step": 520
},
{
"epoch": 0.45,
"learning_rate": 4.7291800932531064e-05,
"loss": 0.0138,
"step": 530
},
{
"epoch": 0.46,
"learning_rate": 4.719023018453623e-05,
"loss": 0.0063,
"step": 540
},
{
"epoch": 0.47,
"learning_rate": 4.708690287547441e-05,
"loss": 0.0376,
"step": 550
},
{
"epoch": 0.48,
"learning_rate": 4.698182718465368e-05,
"loss": 0.006,
"step": 560
},
{
"epoch": 0.48,
"learning_rate": 4.687501142978258e-05,
"loss": 0.0371,
"step": 570
},
{
"epoch": 0.49,
"learning_rate": 4.6766464066311765e-05,
"loss": 0.0322,
"step": 580
},
{
"epoch": 0.5,
"learning_rate": 4.665619368676466e-05,
"loss": 0.0086,
"step": 590
},
{
"epoch": 0.51,
"learning_rate": 4.6544209020057285e-05,
"loss": 0.002,
"step": 600
},
{
"epoch": 0.52,
"learning_rate": 4.643051893080725e-05,
"loss": 0.0147,
"step": 610
},
{
"epoch": 0.53,
"learning_rate": 4.631513241863209e-05,
"loss": 0.0038,
"step": 620
},
{
"epoch": 0.54,
"learning_rate": 4.619805861743683e-05,
"loss": 0.0187,
"step": 630
},
{
"epoch": 0.54,
"learning_rate": 4.607930679469096e-05,
"loss": 0.0063,
"step": 640
},
{
"epoch": 0.55,
"learning_rate": 4.595888635069481e-05,
"loss": 0.0109,
"step": 650
},
{
"epoch": 0.56,
"learning_rate": 4.5836806817835475e-05,
"loss": 0.005,
"step": 660
},
{
"epoch": 0.57,
"learning_rate": 4.57130778598322e-05,
"loss": 0.0167,
"step": 670
},
{
"epoch": 0.58,
"learning_rate": 4.5587709270971425e-05,
"loss": 0.0143,
"step": 680
},
{
"epoch": 0.59,
"learning_rate": 4.546071097533145e-05,
"loss": 0.0015,
"step": 690
},
{
"epoch": 0.59,
"learning_rate": 4.533209302599691e-05,
"loss": 0.0003,
"step": 700
},
{
"epoch": 0.6,
"learning_rate": 4.520186560426292e-05,
"loss": 0.006,
"step": 710
},
{
"epoch": 0.61,
"learning_rate": 4.507003901882915e-05,
"loss": 0.0093,
"step": 720
},
{
"epoch": 0.62,
"learning_rate": 4.493662370498383e-05,
"loss": 0.0046,
"step": 730
},
{
"epoch": 0.63,
"learning_rate": 4.4801630223777665e-05,
"loss": 0.0147,
"step": 740
},
{
"epoch": 0.64,
"learning_rate": 4.466506926118782e-05,
"loss": 0.0102,
"step": 750
},
{
"epoch": 0.65,
"learning_rate": 4.4526951627272074e-05,
"loss": 0.017,
"step": 760
},
{
"epoch": 0.65,
"learning_rate": 4.438728825531305e-05,
"loss": 0.0033,
"step": 770
},
{
"epoch": 0.66,
"learning_rate": 4.4246090200952816e-05,
"loss": 0.0061,
"step": 780
},
{
"epoch": 0.67,
"learning_rate": 4.410336864131762e-05,
"loss": 0.0032,
"step": 790
},
{
"epoch": 0.68,
"learning_rate": 4.395913487413324e-05,
"loss": 0.0043,
"step": 800
},
{
"epoch": 0.69,
"learning_rate": 4.3813400316830576e-05,
"loss": 0.0063,
"step": 810
},
{
"epoch": 0.7,
"learning_rate": 4.36661765056419e-05,
"loss": 0.0273,
"step": 820
},
{
"epoch": 0.71,
"learning_rate": 4.351747509468763e-05,
"loss": 0.0125,
"step": 830
},
{
"epoch": 0.71,
"learning_rate": 4.336730785505382e-05,
"loss": 0.0076,
"step": 840
},
{
"epoch": 0.72,
"learning_rate": 4.3215686673860384e-05,
"loss": 0.0127,
"step": 850
},
{
"epoch": 0.73,
"learning_rate": 4.306262355332006e-05,
"loss": 0.0161,
"step": 860
},
{
"epoch": 0.74,
"learning_rate": 4.290813060978839e-05,
"loss": 0.0169,
"step": 870
},
{
"epoch": 0.75,
"learning_rate": 4.2752220072804564e-05,
"loss": 0.0081,
"step": 880
},
{
"epoch": 0.76,
"learning_rate": 4.259490428412335e-05,
"loss": 0.0131,
"step": 890
},
{
"epoch": 0.76,
"learning_rate": 4.243619569673814e-05,
"loss": 0.0205,
"step": 900
},
{
"epoch": 0.77,
"learning_rate": 4.2276106873895143e-05,
"loss": 0.0026,
"step": 910
},
{
"epoch": 0.78,
"learning_rate": 4.2114650488098936e-05,
"loss": 0.018,
"step": 920
},
{
"epoch": 0.79,
"learning_rate": 4.19518393201093e-05,
"loss": 0.0083,
"step": 930
},
{
"epoch": 0.8,
"learning_rate": 4.178768625792949e-05,
"loss": 0.0291,
"step": 940
},
{
"epoch": 0.81,
"learning_rate": 4.162220429578605e-05,
"loss": 0.0226,
"step": 950
},
{
"epoch": 0.82,
"learning_rate": 4.145540653310018e-05,
"loss": 0.0042,
"step": 960
},
{
"epoch": 0.82,
"learning_rate": 4.128730617345084e-05,
"loss": 0.0078,
"step": 970
},
{
"epoch": 0.83,
"learning_rate": 4.111791652352952e-05,
"loss": 0.0084,
"step": 980
},
{
"epoch": 0.84,
"learning_rate": 4.094725099208688e-05,
"loss": 0.0044,
"step": 990
},
{
"epoch": 0.85,
"learning_rate": 4.077532308887141e-05,
"loss": 0.0011,
"step": 1000
},
{
"epoch": 0.85,
"eval_loss": 0.01175768580287695,
"eval_runtime": 88.0904,
"eval_samples_per_second": 22.511,
"eval_steps_per_second": 2.815,
"step": 1000
},
{
"epoch": 0.86,
"learning_rate": 4.060214642355989e-05,
"loss": 0.0011,
"step": 1010
},
{
"epoch": 0.87,
"learning_rate": 4.042773470468016e-05,
"loss": 0.021,
"step": 1020
},
{
"epoch": 0.88,
"learning_rate": 4.0252101738525916e-05,
"loss": 0.0424,
"step": 1030
},
{
"epoch": 0.88,
"learning_rate": 4.0075261428063806e-05,
"loss": 0.0194,
"step": 1040
},
{
"epoch": 0.89,
"learning_rate": 3.9897227771832924e-05,
"loss": 0.0025,
"step": 1050
},
{
"epoch": 0.9,
"learning_rate": 3.971801486283665e-05,
"loss": 0.0044,
"step": 1060
},
{
"epoch": 0.91,
"learning_rate": 3.953763688742708e-05,
"loss": 0.0051,
"step": 1070
},
{
"epoch": 0.92,
"learning_rate": 3.9356108124182067e-05,
"loss": 0.0071,
"step": 1080
},
{
"epoch": 0.93,
"learning_rate": 3.9173442942774885e-05,
"loss": 0.0145,
"step": 1090
},
{
"epoch": 0.93,
"learning_rate": 3.898965580283681e-05,
"loss": 0.0371,
"step": 1100
},
{
"epoch": 0.94,
"learning_rate": 3.880476125281244e-05,
"loss": 0.0076,
"step": 1110
},
{
"epoch": 0.95,
"learning_rate": 3.861877392880808e-05,
"loss": 0.0035,
"step": 1120
},
{
"epoch": 0.96,
"learning_rate": 3.843170855343317e-05,
"loss": 0.008,
"step": 1130
},
{
"epoch": 0.97,
"learning_rate": 3.8243579934634846e-05,
"loss": 0.0089,
"step": 1140
},
{
"epoch": 0.98,
"learning_rate": 3.805440296452574e-05,
"loss": 0.0034,
"step": 1150
},
{
"epoch": 0.99,
"learning_rate": 3.786419261820514e-05,
"loss": 0.0019,
"step": 1160
},
{
"epoch": 0.99,
"learning_rate": 3.7672963952573614e-05,
"loss": 0.0164,
"step": 1170
},
{
"epoch": 1.0,
"learning_rate": 3.748073210514102e-05,
"loss": 0.0012,
"step": 1180
},
{
"epoch": 1.01,
"learning_rate": 3.728751229282836e-05,
"loss": 0.0072,
"step": 1190
},
{
"epoch": 1.02,
"learning_rate": 3.70933198107631e-05,
"loss": 0.0041,
"step": 1200
},
{
"epoch": 1.03,
"learning_rate": 3.689817003106852e-05,
"loss": 0.0021,
"step": 1210
},
{
"epoch": 1.04,
"learning_rate": 3.670207840164678e-05,
"loss": 0.0024,
"step": 1220
},
{
"epoch": 1.05,
"learning_rate": 3.650506044495615e-05,
"loss": 0.0026,
"step": 1230
},
{
"epoch": 1.05,
"learning_rate": 3.630713175678222e-05,
"loss": 0.005,
"step": 1240
},
{
"epoch": 1.06,
"learning_rate": 3.610830800500335e-05,
"loss": 0.0069,
"step": 1250
},
{
"epoch": 1.07,
"learning_rate": 3.590860492835046e-05,
"loss": 0.0081,
"step": 1260
},
{
"epoch": 1.08,
"learning_rate": 3.5708038335161134e-05,
"loss": 0.0107,
"step": 1270
},
{
"epoch": 1.09,
"learning_rate": 3.550662410212819e-05,
"loss": 0.0074,
"step": 1280
},
{
"epoch": 1.1,
"learning_rate": 3.5304378173043e-05,
"loss": 0.0048,
"step": 1290
},
{
"epoch": 1.1,
"learning_rate": 3.5101316557533294e-05,
"loss": 0.0006,
"step": 1300
},
{
"epoch": 1.11,
"learning_rate": 3.489745532979593e-05,
"loss": 0.0076,
"step": 1310
},
{
"epoch": 1.12,
"learning_rate": 3.469281062732442e-05,
"loss": 0.0002,
"step": 1320
},
{
"epoch": 1.13,
"learning_rate": 3.448739864963154e-05,
"loss": 0.0073,
"step": 1330
},
{
"epoch": 1.14,
"learning_rate": 3.4281235656966915e-05,
"loss": 0.0008,
"step": 1340
},
{
"epoch": 1.15,
"learning_rate": 3.4074337969029965e-05,
"loss": 0.001,
"step": 1350
},
{
"epoch": 1.16,
"learning_rate": 3.386672196367799e-05,
"loss": 0.0047,
"step": 1360
},
{
"epoch": 1.16,
"learning_rate": 3.365840407562974e-05,
"loss": 0.0131,
"step": 1370
},
{
"epoch": 1.17,
"learning_rate": 3.3449400795164416e-05,
"loss": 0.001,
"step": 1380
},
{
"epoch": 1.18,
"learning_rate": 3.323972866681637e-05,
"loss": 0.0058,
"step": 1390
},
{
"epoch": 1.19,
"learning_rate": 3.3029404288065426e-05,
"loss": 0.0047,
"step": 1400
},
{
"epoch": 1.2,
"learning_rate": 3.2818444308023e-05,
"loss": 0.0029,
"step": 1410
},
{
"epoch": 1.21,
"learning_rate": 3.2606865426114234e-05,
"loss": 0.0073,
"step": 1420
},
{
"epoch": 1.21,
"learning_rate": 3.239468439075604e-05,
"loss": 0.0006,
"step": 1430
},
{
"epoch": 1.22,
"learning_rate": 3.2181917998031326e-05,
"loss": 0.0028,
"step": 1440
},
{
"epoch": 1.23,
"learning_rate": 3.196858309035941e-05,
"loss": 0.0003,
"step": 1450
},
{
"epoch": 1.24,
"learning_rate": 3.175469655516284e-05,
"loss": 0.0007,
"step": 1460
},
{
"epoch": 1.25,
"learning_rate": 3.154027532353052e-05,
"loss": 0.0037,
"step": 1470
},
{
"epoch": 1.26,
"learning_rate": 3.132533636887753e-05,
"loss": 0.0065,
"step": 1480
},
{
"epoch": 1.27,
"learning_rate": 3.1109896705601485e-05,
"loss": 0.0092,
"step": 1490
},
{
"epoch": 1.27,
"learning_rate": 3.0893973387735687e-05,
"loss": 0.0001,
"step": 1500
},
{
"epoch": 1.27,
"eval_loss": 0.010954583063721657,
"eval_runtime": 88.0029,
"eval_samples_per_second": 22.533,
"eval_steps_per_second": 2.818,
"step": 1500
},
{
"epoch": 1.28,
"learning_rate": 3.067758350759917e-05,
"loss": 0.0002,
"step": 1510
},
{
"epoch": 1.29,
"learning_rate": 3.046074419444366e-05,
"loss": 0.0004,
"step": 1520
},
{
"epoch": 1.3,
"learning_rate": 3.0243472613097656e-05,
"loss": 0.001,
"step": 1530
},
{
"epoch": 1.31,
"learning_rate": 3.002578596260765e-05,
"loss": 0.0001,
"step": 1540
},
{
"epoch": 1.32,
"learning_rate": 2.980770147487668e-05,
"loss": 0.0086,
"step": 1550
},
{
"epoch": 1.33,
"learning_rate": 2.958923641330028e-05,
"loss": 0.0021,
"step": 1560
},
{
"epoch": 1.33,
"learning_rate": 2.9370408071399898e-05,
"loss": 0.0001,
"step": 1570
},
{
"epoch": 1.34,
"learning_rate": 2.9151233771453956e-05,
"loss": 0.0076,
"step": 1580
},
{
"epoch": 1.35,
"learning_rate": 2.8931730863126666e-05,
"loss": 0.0001,
"step": 1590
},
{
"epoch": 1.36,
"learning_rate": 2.871191672209459e-05,
"loss": 0.0001,
"step": 1600
},
{
"epoch": 1.37,
"learning_rate": 2.8491808748671255e-05,
"loss": 0.0001,
"step": 1610
},
{
"epoch": 1.38,
"learning_rate": 2.8271424366429706e-05,
"loss": 0.0115,
"step": 1620
},
{
"epoch": 1.38,
"learning_rate": 2.8050781020823296e-05,
"loss": 0.0001,
"step": 1630
},
{
"epoch": 1.39,
"learning_rate": 2.7829896177804716e-05,
"loss": 0.0003,
"step": 1640
},
{
"epoch": 1.4,
"learning_rate": 2.760878732244339e-05,
"loss": 0.0003,
"step": 1650
},
{
"epoch": 1.41,
"learning_rate": 2.7387471957541405e-05,
"loss": 0.0024,
"step": 1660
},
{
"epoch": 1.42,
"learning_rate": 2.7165967602247964e-05,
"loss": 0.0005,
"step": 1670
},
{
"epoch": 1.43,
"learning_rate": 2.694429179067261e-05,
"loss": 0.0018,
"step": 1680
},
{
"epoch": 1.44,
"learning_rate": 2.6744651468034758e-05,
"loss": 0.002,
"step": 1690
},
{
"epoch": 1.44,
"learning_rate": 2.6522698243485527e-05,
"loss": 0.0001,
"step": 1700
},
{
"epoch": 1.45,
"learning_rate": 2.6300624483347926e-05,
"loss": 0.0058,
"step": 1710
},
{
"epoch": 1.46,
"learning_rate": 2.607844776680513e-05,
"loss": 0.0001,
"step": 1720
},
{
"epoch": 1.47,
"learning_rate": 2.585618568119027e-05,
"loss": 0.0001,
"step": 1730
},
{
"epoch": 1.48,
"learning_rate": 2.56338558205942e-05,
"loss": 0.0008,
"step": 1740
},
{
"epoch": 1.49,
"learning_rate": 2.5411475784472805e-05,
"loss": 0.0002,
"step": 1750
},
{
"epoch": 1.5,
"learning_rate": 2.5189063176253825e-05,
"loss": 0.0001,
"step": 1760
},
{
"epoch": 1.5,
"learning_rate": 2.496663560194338e-05,
"loss": 0.0001,
"step": 1770
},
{
"epoch": 1.51,
"learning_rate": 2.4744210668732295e-05,
"loss": 0.0001,
"step": 1780
},
{
"epoch": 1.52,
"learning_rate": 2.452180598360232e-05,
"loss": 0.0001,
"step": 1790
},
{
"epoch": 1.53,
"learning_rate": 2.429943915193239e-05,
"loss": 0.0,
"step": 1800
},
{
"epoch": 1.54,
"learning_rate": 2.4077127776104984e-05,
"loss": 0.0146,
"step": 1810
},
{
"epoch": 1.55,
"learning_rate": 2.3854889454112748e-05,
"loss": 0.0017,
"step": 1820
},
{
"epoch": 1.55,
"learning_rate": 2.3632741778165442e-05,
"loss": 0.0001,
"step": 1830
},
{
"epoch": 1.56,
"learning_rate": 2.3410702333297356e-05,
"loss": 0.0001,
"step": 1840
},
{
"epoch": 1.57,
"learning_rate": 2.318878869597528e-05,
"loss": 0.0001,
"step": 1850
},
{
"epoch": 1.58,
"learning_rate": 2.2967018432707213e-05,
"loss": 0.0073,
"step": 1860
},
{
"epoch": 1.59,
"learning_rate": 2.2745409098651744e-05,
"loss": 0.0001,
"step": 1870
},
{
"epoch": 1.6,
"learning_rate": 2.2523978236228442e-05,
"loss": 0.0001,
"step": 1880
},
{
"epoch": 1.61,
"learning_rate": 2.2302743373729205e-05,
"loss": 0.0,
"step": 1890
},
{
"epoch": 1.61,
"learning_rate": 2.2081722023930743e-05,
"loss": 0.0136,
"step": 1900
},
{
"epoch": 1.62,
"learning_rate": 2.1860931682708248e-05,
"loss": 0.0051,
"step": 1910
},
{
"epoch": 1.63,
"learning_rate": 2.164038982765047e-05,
"loss": 0.0004,
"step": 1920
},
{
"epoch": 1.64,
"learning_rate": 2.1420113916676183e-05,
"loss": 0.0002,
"step": 1930
},
{
"epoch": 1.65,
"learning_rate": 2.1200121386652246e-05,
"loss": 0.0001,
"step": 1940
},
{
"epoch": 1.66,
"learning_rate": 2.0980429652013297e-05,
"loss": 0.0001,
"step": 1950
},
{
"epoch": 1.67,
"learning_rate": 2.0761056103383258e-05,
"loss": 0.0001,
"step": 1960
},
{
"epoch": 1.67,
"learning_rate": 2.0542018106198697e-05,
"loss": 0.0,
"step": 1970
},
{
"epoch": 1.68,
"learning_rate": 2.0323332999334198e-05,
"loss": 0.005,
"step": 1980
},
{
"epoch": 1.69,
"learning_rate": 2.010501809372981e-05,
"loss": 0.0149,
"step": 1990
},
{
"epoch": 1.7,
"learning_rate": 1.988709067102076e-05,
"loss": 0.0143,
"step": 2000
},
{
"epoch": 1.7,
"eval_loss": 0.013543435372412205,
"eval_runtime": 87.9904,
"eval_samples_per_second": 22.537,
"eval_steps_per_second": 2.818,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 3531,
"num_train_epochs": 3,
"save_steps": 1000,
"total_flos": 3.0084561090831974e+17,
"trial_name": null,
"trial_params": null
}