trans-2b-s117755-v2-llama2 / trainer_state.json
hellomyoh's picture
Upload folder using huggingface_hub
7c682cd
raw
history blame contribute delete
No virus
89.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1179438864315028,
"eval_steps": 500,
"global_step": 7386,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.790036723614881e-07,
"loss": 1.5083,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 9.580073447229762e-07,
"loss": 1.4983,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 1.437011017084464e-06,
"loss": 1.4938,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 1.9160146894459524e-06,
"loss": 1.4914,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 2.3950183618074405e-06,
"loss": 1.4758,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 2.874022034168928e-06,
"loss": 1.4549,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 3.3530257065304165e-06,
"loss": 1.4589,
"step": 70
},
{
"epoch": 0.0,
"learning_rate": 3.832029378891905e-06,
"loss": 1.423,
"step": 80
},
{
"epoch": 0.0,
"learning_rate": 4.311033051253392e-06,
"loss": 1.39,
"step": 90
},
{
"epoch": 0.0,
"learning_rate": 4.790036723614881e-06,
"loss": 1.3579,
"step": 100
},
{
"epoch": 0.0,
"learning_rate": 5.269040395976369e-06,
"loss": 1.3309,
"step": 110
},
{
"epoch": 0.0,
"learning_rate": 5.748044068337856e-06,
"loss": 1.3144,
"step": 120
},
{
"epoch": 0.0,
"learning_rate": 6.227047740699345e-06,
"loss": 1.3007,
"step": 130
},
{
"epoch": 0.0,
"learning_rate": 6.706051413060833e-06,
"loss": 1.2618,
"step": 140
},
{
"epoch": 0.0,
"learning_rate": 7.185055085422321e-06,
"loss": 1.2586,
"step": 150
},
{
"epoch": 0.0,
"learning_rate": 7.66405875778381e-06,
"loss": 1.2345,
"step": 160
},
{
"epoch": 0.0,
"learning_rate": 8.143062430145297e-06,
"loss": 1.2088,
"step": 170
},
{
"epoch": 0.0,
"learning_rate": 8.622066102506784e-06,
"loss": 1.1936,
"step": 180
},
{
"epoch": 0.0,
"learning_rate": 9.101069774868273e-06,
"loss": 1.1791,
"step": 190
},
{
"epoch": 0.0,
"learning_rate": 9.580073447229762e-06,
"loss": 1.1724,
"step": 200
},
{
"epoch": 0.0,
"learning_rate": 1.0059077119591249e-05,
"loss": 1.1602,
"step": 210
},
{
"epoch": 0.0,
"learning_rate": 1.0538080791952738e-05,
"loss": 1.1546,
"step": 220
},
{
"epoch": 0.0,
"learning_rate": 1.1017084464314227e-05,
"loss": 1.1434,
"step": 230
},
{
"epoch": 0.0,
"learning_rate": 1.1496088136675712e-05,
"loss": 1.1119,
"step": 240
},
{
"epoch": 0.0,
"learning_rate": 1.1975091809037201e-05,
"loss": 1.0983,
"step": 250
},
{
"epoch": 0.0,
"learning_rate": 1.245409548139869e-05,
"loss": 1.0826,
"step": 260
},
{
"epoch": 0.0,
"learning_rate": 1.2933099153760177e-05,
"loss": 1.0324,
"step": 270
},
{
"epoch": 0.0,
"learning_rate": 1.3412102826121666e-05,
"loss": 1.0157,
"step": 280
},
{
"epoch": 0.0,
"learning_rate": 1.3891106498483155e-05,
"loss": 0.9962,
"step": 290
},
{
"epoch": 0.0,
"learning_rate": 1.4370110170844642e-05,
"loss": 0.9938,
"step": 300
},
{
"epoch": 0.0,
"learning_rate": 1.484911384320613e-05,
"loss": 1.0055,
"step": 310
},
{
"epoch": 0.01,
"learning_rate": 1.532811751556762e-05,
"loss": 0.9723,
"step": 320
},
{
"epoch": 0.01,
"learning_rate": 1.5807121187929107e-05,
"loss": 1.0011,
"step": 330
},
{
"epoch": 0.01,
"learning_rate": 1.6286124860290594e-05,
"loss": 0.9864,
"step": 340
},
{
"epoch": 0.01,
"learning_rate": 1.676512853265208e-05,
"loss": 0.9877,
"step": 350
},
{
"epoch": 0.01,
"learning_rate": 1.7244132205013568e-05,
"loss": 0.9937,
"step": 360
},
{
"epoch": 0.01,
"learning_rate": 1.772313587737506e-05,
"loss": 0.99,
"step": 370
},
{
"epoch": 0.01,
"learning_rate": 1.8202139549736546e-05,
"loss": 0.9943,
"step": 380
},
{
"epoch": 0.01,
"learning_rate": 1.8681143222098033e-05,
"loss": 0.9744,
"step": 390
},
{
"epoch": 0.01,
"learning_rate": 1.9160146894459524e-05,
"loss": 0.9678,
"step": 400
},
{
"epoch": 0.01,
"learning_rate": 1.9639150566821007e-05,
"loss": 0.9756,
"step": 410
},
{
"epoch": 0.01,
"learning_rate": 2.0118154239182498e-05,
"loss": 0.9665,
"step": 420
},
{
"epoch": 0.01,
"learning_rate": 2.0597157911543985e-05,
"loss": 0.9528,
"step": 430
},
{
"epoch": 0.01,
"learning_rate": 2.1076161583905476e-05,
"loss": 0.9609,
"step": 440
},
{
"epoch": 0.01,
"learning_rate": 2.1555165256266963e-05,
"loss": 0.9616,
"step": 450
},
{
"epoch": 0.01,
"learning_rate": 2.2034168928628453e-05,
"loss": 0.9685,
"step": 460
},
{
"epoch": 0.01,
"learning_rate": 2.2513172600989937e-05,
"loss": 0.9523,
"step": 470
},
{
"epoch": 0.01,
"learning_rate": 2.2992176273351424e-05,
"loss": 0.9581,
"step": 480
},
{
"epoch": 0.01,
"learning_rate": 2.3471179945712915e-05,
"loss": 0.9551,
"step": 490
},
{
"epoch": 0.01,
"learning_rate": 2.3950183618074402e-05,
"loss": 0.9697,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 2.4429187290435893e-05,
"loss": 0.9729,
"step": 510
},
{
"epoch": 0.01,
"learning_rate": 2.490819096279738e-05,
"loss": 0.9724,
"step": 520
},
{
"epoch": 0.01,
"learning_rate": 2.5387194635158867e-05,
"loss": 0.9709,
"step": 530
},
{
"epoch": 0.01,
"learning_rate": 2.5866198307520354e-05,
"loss": 0.9707,
"step": 540
},
{
"epoch": 0.01,
"learning_rate": 2.634520197988184e-05,
"loss": 0.9615,
"step": 550
},
{
"epoch": 0.01,
"learning_rate": 2.6824205652243332e-05,
"loss": 0.9586,
"step": 560
},
{
"epoch": 0.01,
"learning_rate": 2.730320932460482e-05,
"loss": 0.9723,
"step": 570
},
{
"epoch": 0.01,
"learning_rate": 2.778221299696631e-05,
"loss": 0.9537,
"step": 580
},
{
"epoch": 0.01,
"learning_rate": 2.8261216669327797e-05,
"loss": 0.9701,
"step": 590
},
{
"epoch": 0.01,
"learning_rate": 2.8740220341689284e-05,
"loss": 0.9648,
"step": 600
},
{
"epoch": 0.01,
"learning_rate": 2.921922401405077e-05,
"loss": 0.9469,
"step": 610
},
{
"epoch": 0.01,
"learning_rate": 2.969822768641226e-05,
"loss": 0.9543,
"step": 620
},
{
"epoch": 0.01,
"learning_rate": 3.017723135877375e-05,
"loss": 0.9705,
"step": 630
},
{
"epoch": 0.01,
"learning_rate": 3.065623503113524e-05,
"loss": 0.9661,
"step": 640
},
{
"epoch": 0.01,
"learning_rate": 3.1135238703496726e-05,
"loss": 0.979,
"step": 650
},
{
"epoch": 0.01,
"learning_rate": 3.1614242375858214e-05,
"loss": 0.9702,
"step": 660
},
{
"epoch": 0.01,
"learning_rate": 3.20932460482197e-05,
"loss": 0.9859,
"step": 670
},
{
"epoch": 0.01,
"learning_rate": 3.257224972058119e-05,
"loss": 0.9815,
"step": 680
},
{
"epoch": 0.01,
"learning_rate": 3.3051253392942675e-05,
"loss": 0.9949,
"step": 690
},
{
"epoch": 0.01,
"learning_rate": 3.353025706530416e-05,
"loss": 0.9808,
"step": 700
},
{
"epoch": 0.01,
"learning_rate": 3.4009260737665656e-05,
"loss": 0.9637,
"step": 710
},
{
"epoch": 0.01,
"learning_rate": 3.4488264410027136e-05,
"loss": 0.9975,
"step": 720
},
{
"epoch": 0.01,
"learning_rate": 3.496726808238863e-05,
"loss": 1.0081,
"step": 730
},
{
"epoch": 0.01,
"learning_rate": 3.544627175475012e-05,
"loss": 1.006,
"step": 740
},
{
"epoch": 0.01,
"learning_rate": 3.5925275427111605e-05,
"loss": 0.9949,
"step": 750
},
{
"epoch": 0.01,
"learning_rate": 3.640427909947309e-05,
"loss": 0.9723,
"step": 760
},
{
"epoch": 0.01,
"learning_rate": 3.6883282771834586e-05,
"loss": 0.9761,
"step": 770
},
{
"epoch": 0.01,
"learning_rate": 3.7362286444196066e-05,
"loss": 0.9877,
"step": 780
},
{
"epoch": 0.01,
"learning_rate": 3.784129011655756e-05,
"loss": 0.9878,
"step": 790
},
{
"epoch": 0.01,
"learning_rate": 3.832029378891905e-05,
"loss": 0.9703,
"step": 800
},
{
"epoch": 0.01,
"learning_rate": 3.879929746128053e-05,
"loss": 0.9863,
"step": 810
},
{
"epoch": 0.01,
"learning_rate": 3.9278301133642015e-05,
"loss": 0.9522,
"step": 820
},
{
"epoch": 0.01,
"learning_rate": 3.975730480600351e-05,
"loss": 0.9087,
"step": 830
},
{
"epoch": 0.01,
"learning_rate": 4.0236308478364996e-05,
"loss": 0.9289,
"step": 840
},
{
"epoch": 0.01,
"learning_rate": 4.071531215072648e-05,
"loss": 0.9115,
"step": 850
},
{
"epoch": 0.01,
"learning_rate": 4.119431582308797e-05,
"loss": 0.931,
"step": 860
},
{
"epoch": 0.01,
"learning_rate": 4.1673319495449464e-05,
"loss": 0.909,
"step": 870
},
{
"epoch": 0.01,
"learning_rate": 4.215232316781095e-05,
"loss": 0.9239,
"step": 880
},
{
"epoch": 0.01,
"learning_rate": 4.263132684017244e-05,
"loss": 0.9346,
"step": 890
},
{
"epoch": 0.01,
"learning_rate": 4.3110330512533926e-05,
"loss": 0.9121,
"step": 900
},
{
"epoch": 0.01,
"learning_rate": 4.358933418489542e-05,
"loss": 0.9179,
"step": 910
},
{
"epoch": 0.01,
"learning_rate": 4.406833785725691e-05,
"loss": 0.9212,
"step": 920
},
{
"epoch": 0.01,
"learning_rate": 4.4547341529618394e-05,
"loss": 0.9025,
"step": 930
},
{
"epoch": 0.02,
"learning_rate": 4.5026345201979874e-05,
"loss": 0.9307,
"step": 940
},
{
"epoch": 0.02,
"learning_rate": 4.550534887434136e-05,
"loss": 0.9262,
"step": 950
},
{
"epoch": 0.02,
"learning_rate": 4.598435254670285e-05,
"loss": 0.9053,
"step": 960
},
{
"epoch": 0.02,
"learning_rate": 4.646335621906434e-05,
"loss": 0.9079,
"step": 970
},
{
"epoch": 0.02,
"learning_rate": 4.694235989142583e-05,
"loss": 0.9104,
"step": 980
},
{
"epoch": 0.02,
"learning_rate": 4.742136356378732e-05,
"loss": 0.9131,
"step": 990
},
{
"epoch": 0.02,
"learning_rate": 4.7900367236148804e-05,
"loss": 0.9434,
"step": 1000
},
{
"epoch": 0.02,
"learning_rate": 4.83793709085103e-05,
"loss": 0.9321,
"step": 1010
},
{
"epoch": 0.02,
"learning_rate": 4.8858374580871785e-05,
"loss": 0.9411,
"step": 1020
},
{
"epoch": 0.02,
"learning_rate": 4.933737825323327e-05,
"loss": 0.9419,
"step": 1030
},
{
"epoch": 0.02,
"learning_rate": 4.981638192559476e-05,
"loss": 0.9285,
"step": 1040
},
{
"epoch": 0.02,
"learning_rate": 5.029538559795625e-05,
"loss": 0.9529,
"step": 1050
},
{
"epoch": 0.02,
"learning_rate": 5.0774389270317734e-05,
"loss": 0.9518,
"step": 1060
},
{
"epoch": 0.02,
"learning_rate": 5.125339294267922e-05,
"loss": 0.941,
"step": 1070
},
{
"epoch": 0.02,
"learning_rate": 5.173239661504071e-05,
"loss": 0.9399,
"step": 1080
},
{
"epoch": 0.02,
"learning_rate": 5.2211400287402195e-05,
"loss": 0.9463,
"step": 1090
},
{
"epoch": 0.02,
"learning_rate": 5.269040395976368e-05,
"loss": 0.922,
"step": 1100
},
{
"epoch": 0.02,
"learning_rate": 5.3169407632125176e-05,
"loss": 0.9496,
"step": 1110
},
{
"epoch": 0.02,
"learning_rate": 5.3648411304486663e-05,
"loss": 0.9239,
"step": 1120
},
{
"epoch": 0.02,
"learning_rate": 5.412741497684815e-05,
"loss": 0.941,
"step": 1130
},
{
"epoch": 0.02,
"learning_rate": 5.460641864920964e-05,
"loss": 0.9189,
"step": 1140
},
{
"epoch": 0.02,
"learning_rate": 5.508542232157113e-05,
"loss": 0.9228,
"step": 1150
},
{
"epoch": 0.02,
"learning_rate": 5.556442599393262e-05,
"loss": 0.9792,
"step": 1160
},
{
"epoch": 0.02,
"learning_rate": 5.6043429666294106e-05,
"loss": 0.9682,
"step": 1170
},
{
"epoch": 0.02,
"learning_rate": 5.652243333865559e-05,
"loss": 0.9293,
"step": 1180
},
{
"epoch": 0.02,
"learning_rate": 5.7001437011017074e-05,
"loss": 0.96,
"step": 1190
},
{
"epoch": 0.02,
"learning_rate": 5.748044068337857e-05,
"loss": 0.9288,
"step": 1200
},
{
"epoch": 0.02,
"learning_rate": 5.7959444355740055e-05,
"loss": 0.955,
"step": 1210
},
{
"epoch": 0.02,
"learning_rate": 5.843844802810154e-05,
"loss": 0.9591,
"step": 1220
},
{
"epoch": 0.02,
"learning_rate": 5.891745170046303e-05,
"loss": 0.9684,
"step": 1230
},
{
"epoch": 0.02,
"learning_rate": 5.939645537282452e-05,
"loss": 0.9338,
"step": 1240
},
{
"epoch": 0.02,
"learning_rate": 5.987545904518601e-05,
"loss": 0.9663,
"step": 1250
},
{
"epoch": 0.02,
"learning_rate": 6.03544627175475e-05,
"loss": 0.9623,
"step": 1260
},
{
"epoch": 0.02,
"learning_rate": 6.0833466389908984e-05,
"loss": 0.9567,
"step": 1270
},
{
"epoch": 0.02,
"learning_rate": 6.131247006227048e-05,
"loss": 0.9332,
"step": 1280
},
{
"epoch": 0.02,
"learning_rate": 6.179147373463196e-05,
"loss": 0.9558,
"step": 1290
},
{
"epoch": 0.02,
"learning_rate": 6.227047740699345e-05,
"loss": 0.9696,
"step": 1300
},
{
"epoch": 0.02,
"learning_rate": 6.274948107935493e-05,
"loss": 0.955,
"step": 1310
},
{
"epoch": 0.02,
"learning_rate": 6.322848475171643e-05,
"loss": 0.9765,
"step": 1320
},
{
"epoch": 0.02,
"learning_rate": 6.370748842407791e-05,
"loss": 1.0007,
"step": 1330
},
{
"epoch": 0.02,
"learning_rate": 6.41864920964394e-05,
"loss": 1.0083,
"step": 1340
},
{
"epoch": 0.02,
"learning_rate": 6.466549576880088e-05,
"loss": 0.9953,
"step": 1350
},
{
"epoch": 0.02,
"learning_rate": 6.514449944116238e-05,
"loss": 0.9801,
"step": 1360
},
{
"epoch": 0.02,
"learning_rate": 6.562350311352387e-05,
"loss": 0.996,
"step": 1370
},
{
"epoch": 0.02,
"learning_rate": 6.610250678588535e-05,
"loss": 1.0034,
"step": 1380
},
{
"epoch": 0.02,
"learning_rate": 6.658151045824684e-05,
"loss": 1.0063,
"step": 1390
},
{
"epoch": 0.02,
"learning_rate": 6.706051413060832e-05,
"loss": 0.9886,
"step": 1400
},
{
"epoch": 0.02,
"learning_rate": 6.753951780296982e-05,
"loss": 1.0168,
"step": 1410
},
{
"epoch": 0.02,
"learning_rate": 6.801852147533131e-05,
"loss": 0.9977,
"step": 1420
},
{
"epoch": 0.02,
"learning_rate": 6.849752514769279e-05,
"loss": 0.9931,
"step": 1430
},
{
"epoch": 0.02,
"learning_rate": 6.897652882005427e-05,
"loss": 0.9978,
"step": 1440
},
{
"epoch": 0.02,
"learning_rate": 6.945553249241577e-05,
"loss": 0.9907,
"step": 1450
},
{
"epoch": 0.02,
"learning_rate": 6.993453616477726e-05,
"loss": 0.989,
"step": 1460
},
{
"epoch": 0.02,
"learning_rate": 7.041353983713874e-05,
"loss": 0.9947,
"step": 1470
},
{
"epoch": 0.02,
"learning_rate": 7.089254350950024e-05,
"loss": 1.0033,
"step": 1480
},
{
"epoch": 0.02,
"learning_rate": 7.137154718186172e-05,
"loss": 0.9806,
"step": 1490
},
{
"epoch": 0.02,
"learning_rate": 7.185055085422321e-05,
"loss": 0.999,
"step": 1500
},
{
"epoch": 0.02,
"learning_rate": 7.23295545265847e-05,
"loss": 0.9932,
"step": 1510
},
{
"epoch": 0.02,
"learning_rate": 7.280855819894618e-05,
"loss": 0.9771,
"step": 1520
},
{
"epoch": 0.02,
"learning_rate": 7.328756187130768e-05,
"loss": 0.9791,
"step": 1530
},
{
"epoch": 0.02,
"learning_rate": 7.376656554366917e-05,
"loss": 0.978,
"step": 1540
},
{
"epoch": 0.02,
"learning_rate": 7.424556921603065e-05,
"loss": 0.9864,
"step": 1550
},
{
"epoch": 0.02,
"learning_rate": 7.472457288839213e-05,
"loss": 0.9846,
"step": 1560
},
{
"epoch": 0.03,
"learning_rate": 7.520357656075363e-05,
"loss": 0.9796,
"step": 1570
},
{
"epoch": 0.03,
"learning_rate": 7.568258023311512e-05,
"loss": 0.9704,
"step": 1580
},
{
"epoch": 0.03,
"learning_rate": 7.616158390547661e-05,
"loss": 0.983,
"step": 1590
},
{
"epoch": 0.03,
"learning_rate": 7.66405875778381e-05,
"loss": 0.982,
"step": 1600
},
{
"epoch": 0.03,
"learning_rate": 7.711959125019959e-05,
"loss": 0.9753,
"step": 1610
},
{
"epoch": 0.03,
"learning_rate": 7.759859492256106e-05,
"loss": 0.9864,
"step": 1620
},
{
"epoch": 0.03,
"learning_rate": 7.807759859492255e-05,
"loss": 0.983,
"step": 1630
},
{
"epoch": 0.03,
"learning_rate": 7.855660226728403e-05,
"loss": 0.9886,
"step": 1640
},
{
"epoch": 0.03,
"learning_rate": 7.903560593964552e-05,
"loss": 0.9821,
"step": 1650
},
{
"epoch": 0.03,
"learning_rate": 7.951460961200702e-05,
"loss": 0.9844,
"step": 1660
},
{
"epoch": 0.03,
"learning_rate": 7.99936132843685e-05,
"loss": 0.9787,
"step": 1670
},
{
"epoch": 0.03,
"learning_rate": 8.047261695672999e-05,
"loss": 0.9659,
"step": 1680
},
{
"epoch": 0.03,
"learning_rate": 8.095162062909149e-05,
"loss": 0.9648,
"step": 1690
},
{
"epoch": 0.03,
"learning_rate": 8.143062430145297e-05,
"loss": 0.9602,
"step": 1700
},
{
"epoch": 0.03,
"learning_rate": 8.190962797381446e-05,
"loss": 0.9656,
"step": 1710
},
{
"epoch": 0.03,
"learning_rate": 8.238863164617594e-05,
"loss": 0.9728,
"step": 1720
},
{
"epoch": 0.03,
"learning_rate": 8.286763531853743e-05,
"loss": 0.959,
"step": 1730
},
{
"epoch": 0.03,
"learning_rate": 8.334663899089893e-05,
"loss": 0.9482,
"step": 1740
},
{
"epoch": 0.03,
"learning_rate": 8.382564266326041e-05,
"loss": 0.9641,
"step": 1750
},
{
"epoch": 0.03,
"learning_rate": 8.43046463356219e-05,
"loss": 0.9603,
"step": 1760
},
{
"epoch": 0.03,
"learning_rate": 8.478365000798338e-05,
"loss": 0.9799,
"step": 1770
},
{
"epoch": 0.03,
"learning_rate": 8.526265368034488e-05,
"loss": 0.9651,
"step": 1780
},
{
"epoch": 0.03,
"learning_rate": 8.574165735270637e-05,
"loss": 0.9652,
"step": 1790
},
{
"epoch": 0.03,
"learning_rate": 8.622066102506785e-05,
"loss": 0.9668,
"step": 1800
},
{
"epoch": 0.03,
"learning_rate": 8.669966469742935e-05,
"loss": 0.9676,
"step": 1810
},
{
"epoch": 0.03,
"learning_rate": 8.717866836979084e-05,
"loss": 0.9762,
"step": 1820
},
{
"epoch": 0.03,
"learning_rate": 8.765767204215232e-05,
"loss": 0.9732,
"step": 1830
},
{
"epoch": 0.03,
"learning_rate": 8.813667571451381e-05,
"loss": 0.9772,
"step": 1840
},
{
"epoch": 0.03,
"learning_rate": 8.86156793868753e-05,
"loss": 0.9786,
"step": 1850
},
{
"epoch": 0.03,
"learning_rate": 8.909468305923679e-05,
"loss": 0.9826,
"step": 1860
},
{
"epoch": 0.03,
"learning_rate": 8.957368673159825e-05,
"loss": 0.952,
"step": 1870
},
{
"epoch": 0.03,
"learning_rate": 9.005269040395975e-05,
"loss": 0.9508,
"step": 1880
},
{
"epoch": 0.03,
"learning_rate": 9.053169407632124e-05,
"loss": 0.9569,
"step": 1890
},
{
"epoch": 0.03,
"learning_rate": 9.101069774868272e-05,
"loss": 0.9701,
"step": 1900
},
{
"epoch": 0.03,
"learning_rate": 9.148970142104422e-05,
"loss": 0.9704,
"step": 1910
},
{
"epoch": 0.03,
"learning_rate": 9.19687050934057e-05,
"loss": 0.9765,
"step": 1920
},
{
"epoch": 0.03,
"learning_rate": 9.244770876576719e-05,
"loss": 0.9759,
"step": 1930
},
{
"epoch": 0.03,
"learning_rate": 9.292671243812869e-05,
"loss": 0.969,
"step": 1940
},
{
"epoch": 0.03,
"learning_rate": 9.340571611049017e-05,
"loss": 0.9616,
"step": 1950
},
{
"epoch": 0.03,
"learning_rate": 9.388471978285166e-05,
"loss": 0.9539,
"step": 1960
},
{
"epoch": 0.03,
"learning_rate": 9.436372345521315e-05,
"loss": 0.9596,
"step": 1970
},
{
"epoch": 0.03,
"learning_rate": 9.484272712757463e-05,
"loss": 0.9699,
"step": 1980
},
{
"epoch": 0.03,
"learning_rate": 9.532173079993613e-05,
"loss": 0.9642,
"step": 1990
},
{
"epoch": 0.03,
"learning_rate": 9.580073447229761e-05,
"loss": 0.9636,
"step": 2000
},
{
"epoch": 0.03,
"learning_rate": 9.62797381446591e-05,
"loss": 0.9776,
"step": 2010
},
{
"epoch": 0.03,
"learning_rate": 9.67587418170206e-05,
"loss": 0.9632,
"step": 2020
},
{
"epoch": 0.03,
"learning_rate": 9.723774548938208e-05,
"loss": 0.9675,
"step": 2030
},
{
"epoch": 0.03,
"learning_rate": 9.771674916174357e-05,
"loss": 0.9642,
"step": 2040
},
{
"epoch": 0.03,
"learning_rate": 9.819575283410505e-05,
"loss": 0.9616,
"step": 2050
},
{
"epoch": 0.03,
"learning_rate": 9.867475650646654e-05,
"loss": 0.9667,
"step": 2060
},
{
"epoch": 0.03,
"learning_rate": 9.915376017882804e-05,
"loss": 0.9635,
"step": 2070
},
{
"epoch": 0.03,
"learning_rate": 9.963276385118952e-05,
"loss": 0.941,
"step": 2080
},
{
"epoch": 0.03,
"learning_rate": 0.00010011176752355101,
"loss": 0.9553,
"step": 2090
},
{
"epoch": 0.03,
"learning_rate": 0.0001005907711959125,
"loss": 0.9669,
"step": 2100
},
{
"epoch": 0.03,
"learning_rate": 0.00010106977486827399,
"loss": 0.9673,
"step": 2110
},
{
"epoch": 0.03,
"learning_rate": 0.00010154877854063547,
"loss": 0.9783,
"step": 2120
},
{
"epoch": 0.03,
"learning_rate": 0.00010202778221299695,
"loss": 0.9594,
"step": 2130
},
{
"epoch": 0.03,
"learning_rate": 0.00010250678588535844,
"loss": 0.9636,
"step": 2140
},
{
"epoch": 0.03,
"learning_rate": 0.00010298578955771992,
"loss": 0.963,
"step": 2150
},
{
"epoch": 0.03,
"learning_rate": 0.00010346479323008142,
"loss": 0.9771,
"step": 2160
},
{
"epoch": 0.03,
"learning_rate": 0.00010394379690244291,
"loss": 0.9802,
"step": 2170
},
{
"epoch": 0.03,
"learning_rate": 0.00010442280057480439,
"loss": 0.96,
"step": 2180
},
{
"epoch": 0.03,
"learning_rate": 0.00010490180424716588,
"loss": 0.9759,
"step": 2190
},
{
"epoch": 0.04,
"learning_rate": 0.00010538080791952736,
"loss": 0.978,
"step": 2200
},
{
"epoch": 0.04,
"learning_rate": 0.00010585981159188886,
"loss": 0.9755,
"step": 2210
},
{
"epoch": 0.04,
"learning_rate": 0.00010633881526425035,
"loss": 0.9742,
"step": 2220
},
{
"epoch": 0.04,
"learning_rate": 0.00010681781893661183,
"loss": 0.9685,
"step": 2230
},
{
"epoch": 0.04,
"learning_rate": 0.00010729682260897333,
"loss": 0.9637,
"step": 2240
},
{
"epoch": 0.04,
"learning_rate": 0.00010777582628133482,
"loss": 0.9647,
"step": 2250
},
{
"epoch": 0.04,
"learning_rate": 0.0001082548299536963,
"loss": 0.9566,
"step": 2260
},
{
"epoch": 0.04,
"learning_rate": 0.0001087338336260578,
"loss": 0.9579,
"step": 2270
},
{
"epoch": 0.04,
"learning_rate": 0.00010921283729841928,
"loss": 0.9746,
"step": 2280
},
{
"epoch": 0.04,
"learning_rate": 0.00010969184097078077,
"loss": 0.967,
"step": 2290
},
{
"epoch": 0.04,
"learning_rate": 0.00011017084464314226,
"loss": 0.9884,
"step": 2300
},
{
"epoch": 0.04,
"learning_rate": 0.00011064984831550374,
"loss": 0.9649,
"step": 2310
},
{
"epoch": 0.04,
"learning_rate": 0.00011112885198786524,
"loss": 0.9534,
"step": 2320
},
{
"epoch": 0.04,
"learning_rate": 0.00011160785566022672,
"loss": 0.9706,
"step": 2330
},
{
"epoch": 0.04,
"learning_rate": 0.00011208685933258821,
"loss": 0.9747,
"step": 2340
},
{
"epoch": 0.04,
"learning_rate": 0.0001125658630049497,
"loss": 0.9532,
"step": 2350
},
{
"epoch": 0.04,
"learning_rate": 0.00011304486667731119,
"loss": 0.9733,
"step": 2360
},
{
"epoch": 0.04,
"learning_rate": 0.00011352387034967267,
"loss": 0.9648,
"step": 2370
},
{
"epoch": 0.04,
"learning_rate": 0.00011400287402203415,
"loss": 0.9651,
"step": 2380
},
{
"epoch": 0.04,
"learning_rate": 0.00011448187769439564,
"loss": 0.9597,
"step": 2390
},
{
"epoch": 0.04,
"learning_rate": 0.00011496088136675714,
"loss": 0.9757,
"step": 2400
},
{
"epoch": 0.04,
"learning_rate": 0.00011543988503911862,
"loss": 0.9621,
"step": 2410
},
{
"epoch": 0.04,
"learning_rate": 0.00011591888871148011,
"loss": 0.9515,
"step": 2420
},
{
"epoch": 0.04,
"learning_rate": 0.00011639789238384159,
"loss": 0.952,
"step": 2430
},
{
"epoch": 0.04,
"learning_rate": 0.00011687689605620308,
"loss": 0.9683,
"step": 2440
},
{
"epoch": 0.04,
"learning_rate": 0.00011735589972856458,
"loss": 0.9534,
"step": 2450
},
{
"epoch": 0.04,
"learning_rate": 0.00011783490340092606,
"loss": 0.9654,
"step": 2460
},
{
"epoch": 0.04,
"learning_rate": 0.00011831390707328755,
"loss": 0.9595,
"step": 2470
},
{
"epoch": 0.04,
"learning_rate": 0.00011879291074564905,
"loss": 0.987,
"step": 2480
},
{
"epoch": 0.04,
"learning_rate": 0.00011927191441801053,
"loss": 0.9746,
"step": 2490
},
{
"epoch": 0.04,
"learning_rate": 0.00011975091809037202,
"loss": 0.9632,
"step": 2500
},
{
"epoch": 0.04,
"learning_rate": 0.0001202299217627335,
"loss": 0.9565,
"step": 2510
},
{
"epoch": 0.04,
"learning_rate": 0.000120708925435095,
"loss": 0.9493,
"step": 2520
},
{
"epoch": 0.04,
"learning_rate": 0.00012118792910745649,
"loss": 0.9449,
"step": 2530
},
{
"epoch": 0.04,
"learning_rate": 0.00012166693277981797,
"loss": 0.9456,
"step": 2540
},
{
"epoch": 0.04,
"learning_rate": 0.00012214593645217946,
"loss": 0.9386,
"step": 2550
},
{
"epoch": 0.04,
"learning_rate": 0.00012262494012454096,
"loss": 0.938,
"step": 2560
},
{
"epoch": 0.04,
"learning_rate": 0.00012310394379690245,
"loss": 0.9372,
"step": 2570
},
{
"epoch": 0.04,
"learning_rate": 0.00012358294746926392,
"loss": 0.9377,
"step": 2580
},
{
"epoch": 0.04,
"learning_rate": 0.0001240619511416254,
"loss": 0.9312,
"step": 2590
},
{
"epoch": 0.04,
"learning_rate": 0.0001245409548139869,
"loss": 0.9323,
"step": 2600
},
{
"epoch": 0.04,
"learning_rate": 0.00012501995848634837,
"loss": 0.9278,
"step": 2610
},
{
"epoch": 0.04,
"learning_rate": 0.00012549896215870987,
"loss": 0.9291,
"step": 2620
},
{
"epoch": 0.04,
"learning_rate": 0.00012597796583107136,
"loss": 0.93,
"step": 2630
},
{
"epoch": 0.04,
"learning_rate": 0.00012645696950343285,
"loss": 0.9262,
"step": 2640
},
{
"epoch": 0.04,
"learning_rate": 0.00012693597317579432,
"loss": 0.9385,
"step": 2650
},
{
"epoch": 0.04,
"learning_rate": 0.00012741497684815581,
"loss": 0.9323,
"step": 2660
},
{
"epoch": 0.04,
"learning_rate": 0.0001278939805205173,
"loss": 0.9129,
"step": 2670
},
{
"epoch": 0.04,
"learning_rate": 0.0001283729841928788,
"loss": 0.924,
"step": 2680
},
{
"epoch": 0.04,
"learning_rate": 0.0001288519878652403,
"loss": 0.928,
"step": 2690
},
{
"epoch": 0.04,
"learning_rate": 0.00012933099153760176,
"loss": 0.9291,
"step": 2700
},
{
"epoch": 0.04,
"learning_rate": 0.00012980999520996326,
"loss": 0.9111,
"step": 2710
},
{
"epoch": 0.04,
"learning_rate": 0.00013028899888232475,
"loss": 0.9201,
"step": 2720
},
{
"epoch": 0.04,
"learning_rate": 0.00013076800255468625,
"loss": 0.9274,
"step": 2730
},
{
"epoch": 0.04,
"learning_rate": 0.00013124700622704774,
"loss": 0.9095,
"step": 2740
},
{
"epoch": 0.04,
"learning_rate": 0.0001317260098994092,
"loss": 0.9146,
"step": 2750
},
{
"epoch": 0.04,
"learning_rate": 0.0001322050135717707,
"loss": 0.9186,
"step": 2760
},
{
"epoch": 0.04,
"learning_rate": 0.0001326840172441322,
"loss": 0.9149,
"step": 2770
},
{
"epoch": 0.04,
"learning_rate": 0.0001331630209164937,
"loss": 0.9221,
"step": 2780
},
{
"epoch": 0.04,
"learning_rate": 0.00013364202458885518,
"loss": 0.9153,
"step": 2790
},
{
"epoch": 0.04,
"learning_rate": 0.00013412102826121665,
"loss": 0.9145,
"step": 2800
},
{
"epoch": 0.04,
"learning_rate": 0.00013460003193357814,
"loss": 0.9252,
"step": 2810
},
{
"epoch": 0.05,
"learning_rate": 0.00013507903560593964,
"loss": 0.9038,
"step": 2820
},
{
"epoch": 0.05,
"learning_rate": 0.00013555803927830113,
"loss": 0.9119,
"step": 2830
},
{
"epoch": 0.05,
"learning_rate": 0.00013603704295066262,
"loss": 0.9126,
"step": 2840
},
{
"epoch": 0.05,
"learning_rate": 0.00013651604662302412,
"loss": 0.9093,
"step": 2850
},
{
"epoch": 0.05,
"learning_rate": 0.00013699505029538559,
"loss": 0.9104,
"step": 2860
},
{
"epoch": 0.05,
"learning_rate": 0.00013747405396774708,
"loss": 0.916,
"step": 2870
},
{
"epoch": 0.05,
"learning_rate": 0.00013795305764010855,
"loss": 0.9114,
"step": 2880
},
{
"epoch": 0.05,
"learning_rate": 0.00013843206131247004,
"loss": 0.9037,
"step": 2890
},
{
"epoch": 0.05,
"learning_rate": 0.00013891106498483153,
"loss": 0.9133,
"step": 2900
},
{
"epoch": 0.05,
"learning_rate": 0.00013939006865719303,
"loss": 0.9001,
"step": 2910
},
{
"epoch": 0.05,
"learning_rate": 0.00013986907232955452,
"loss": 0.9088,
"step": 2920
},
{
"epoch": 0.05,
"learning_rate": 0.000140348076001916,
"loss": 0.9102,
"step": 2930
},
{
"epoch": 0.05,
"learning_rate": 0.00014082707967427748,
"loss": 0.9181,
"step": 2940
},
{
"epoch": 0.05,
"learning_rate": 0.00014130608334663898,
"loss": 0.8853,
"step": 2950
},
{
"epoch": 0.05,
"learning_rate": 0.00014178508701900047,
"loss": 0.8549,
"step": 2960
},
{
"epoch": 0.05,
"learning_rate": 0.00014226409069136196,
"loss": 0.8592,
"step": 2970
},
{
"epoch": 0.05,
"learning_rate": 0.00014274309436372343,
"loss": 0.8436,
"step": 2980
},
{
"epoch": 0.05,
"learning_rate": 0.00014322209803608492,
"loss": 0.8454,
"step": 2990
},
{
"epoch": 0.05,
"learning_rate": 0.00014370110170844642,
"loss": 0.8489,
"step": 3000
},
{
"epoch": 0.05,
"learning_rate": 0.0001441801053808079,
"loss": 0.8522,
"step": 3010
},
{
"epoch": 0.05,
"learning_rate": 0.0001446591090531694,
"loss": 0.8418,
"step": 3020
},
{
"epoch": 0.05,
"learning_rate": 0.00014513811272553087,
"loss": 0.8377,
"step": 3030
},
{
"epoch": 0.05,
"learning_rate": 0.00014561711639789237,
"loss": 0.8273,
"step": 3040
},
{
"epoch": 0.05,
"learning_rate": 0.00014609612007025386,
"loss": 0.8356,
"step": 3050
},
{
"epoch": 0.05,
"learning_rate": 0.00014657512374261536,
"loss": 0.8503,
"step": 3060
},
{
"epoch": 0.05,
"learning_rate": 0.00014705412741497685,
"loss": 0.8378,
"step": 3070
},
{
"epoch": 0.05,
"learning_rate": 0.00014753313108733834,
"loss": 0.8313,
"step": 3080
},
{
"epoch": 0.05,
"learning_rate": 0.0001480121347596998,
"loss": 0.8395,
"step": 3090
},
{
"epoch": 0.05,
"learning_rate": 0.0001484911384320613,
"loss": 0.8229,
"step": 3100
},
{
"epoch": 0.05,
"learning_rate": 0.00014897014210442277,
"loss": 0.7687,
"step": 3110
},
{
"epoch": 0.05,
"learning_rate": 0.00014944914577678426,
"loss": 0.7637,
"step": 3120
},
{
"epoch": 0.05,
"learning_rate": 0.00014992814944914576,
"loss": 0.7688,
"step": 3130
},
{
"epoch": 0.05,
"learning_rate": 0.00015040715312150725,
"loss": 0.7523,
"step": 3140
},
{
"epoch": 0.05,
"learning_rate": 0.00015088615679386875,
"loss": 0.7575,
"step": 3150
},
{
"epoch": 0.05,
"learning_rate": 0.00015136516046623024,
"loss": 0.7491,
"step": 3160
},
{
"epoch": 0.05,
"learning_rate": 0.00015184416413859173,
"loss": 0.7557,
"step": 3170
},
{
"epoch": 0.05,
"learning_rate": 0.00015232316781095323,
"loss": 0.7449,
"step": 3180
},
{
"epoch": 0.05,
"learning_rate": 0.0001528021714833147,
"loss": 0.7556,
"step": 3190
},
{
"epoch": 0.05,
"learning_rate": 0.0001532811751556762,
"loss": 0.744,
"step": 3200
},
{
"epoch": 0.05,
"learning_rate": 0.00015376017882803768,
"loss": 0.74,
"step": 3210
},
{
"epoch": 0.05,
"learning_rate": 0.00015423918250039918,
"loss": 0.7443,
"step": 3220
},
{
"epoch": 0.05,
"learning_rate": 0.00015471818617276067,
"loss": 0.7399,
"step": 3230
},
{
"epoch": 0.05,
"learning_rate": 0.0001551971898451221,
"loss": 0.7388,
"step": 3240
},
{
"epoch": 0.05,
"learning_rate": 0.0001556761935174836,
"loss": 0.7432,
"step": 3250
},
{
"epoch": 0.05,
"learning_rate": 0.0001561551971898451,
"loss": 0.7448,
"step": 3260
},
{
"epoch": 0.05,
"learning_rate": 0.0001566342008622066,
"loss": 0.7394,
"step": 3270
},
{
"epoch": 0.05,
"learning_rate": 0.00015711320453456806,
"loss": 0.7402,
"step": 3280
},
{
"epoch": 0.05,
"learning_rate": 0.00015759220820692955,
"loss": 0.7484,
"step": 3290
},
{
"epoch": 0.05,
"learning_rate": 0.00015807121187929105,
"loss": 0.7378,
"step": 3300
},
{
"epoch": 0.05,
"learning_rate": 0.00015855021555165254,
"loss": 0.7319,
"step": 3310
},
{
"epoch": 0.05,
"learning_rate": 0.00015902921922401404,
"loss": 0.73,
"step": 3320
},
{
"epoch": 0.05,
"learning_rate": 0.0001595082228963755,
"loss": 0.7327,
"step": 3330
},
{
"epoch": 0.05,
"learning_rate": 0.000159987226568737,
"loss": 0.7346,
"step": 3340
},
{
"epoch": 0.05,
"learning_rate": 0.0001604662302410985,
"loss": 0.7285,
"step": 3350
},
{
"epoch": 0.05,
"learning_rate": 0.00016094523391345998,
"loss": 0.7335,
"step": 3360
},
{
"epoch": 0.05,
"learning_rate": 0.00016142423758582148,
"loss": 0.7379,
"step": 3370
},
{
"epoch": 0.05,
"learning_rate": 0.00016190324125818297,
"loss": 0.7285,
"step": 3380
},
{
"epoch": 0.05,
"learning_rate": 0.00016238224493054444,
"loss": 0.7344,
"step": 3390
},
{
"epoch": 0.05,
"learning_rate": 0.00016286124860290593,
"loss": 0.7179,
"step": 3400
},
{
"epoch": 0.05,
"learning_rate": 0.00016334025227526743,
"loss": 0.7285,
"step": 3410
},
{
"epoch": 0.05,
"learning_rate": 0.00016381925594762892,
"loss": 0.7282,
"step": 3420
},
{
"epoch": 0.05,
"learning_rate": 0.00016429825961999041,
"loss": 0.7149,
"step": 3430
},
{
"epoch": 0.05,
"learning_rate": 0.00016477726329235188,
"loss": 0.7404,
"step": 3440
},
{
"epoch": 0.06,
"learning_rate": 0.00016525626696471337,
"loss": 0.7565,
"step": 3450
},
{
"epoch": 0.06,
"learning_rate": 0.00016573527063707487,
"loss": 0.7382,
"step": 3460
},
{
"epoch": 0.06,
"learning_rate": 0.00016621427430943636,
"loss": 0.7543,
"step": 3470
},
{
"epoch": 0.06,
"learning_rate": 0.00016669327798179786,
"loss": 0.7501,
"step": 3480
},
{
"epoch": 0.06,
"learning_rate": 0.00016717228165415932,
"loss": 0.74,
"step": 3490
},
{
"epoch": 0.06,
"learning_rate": 0.00016765128532652082,
"loss": 0.747,
"step": 3500
},
{
"epoch": 0.06,
"learning_rate": 0.0001681302889988823,
"loss": 0.7308,
"step": 3510
},
{
"epoch": 0.06,
"learning_rate": 0.0001686092926712438,
"loss": 0.7444,
"step": 3520
},
{
"epoch": 0.06,
"learning_rate": 0.0001690882963436053,
"loss": 0.732,
"step": 3530
},
{
"epoch": 0.06,
"learning_rate": 0.00016956730001596677,
"loss": 0.7448,
"step": 3540
},
{
"epoch": 0.06,
"learning_rate": 0.00017004630368832826,
"loss": 0.7336,
"step": 3550
},
{
"epoch": 0.06,
"learning_rate": 0.00017052530736068975,
"loss": 0.7263,
"step": 3560
},
{
"epoch": 0.06,
"learning_rate": 0.00017100431103305125,
"loss": 0.7273,
"step": 3570
},
{
"epoch": 0.06,
"learning_rate": 0.00017148331470541274,
"loss": 0.7248,
"step": 3580
},
{
"epoch": 0.06,
"learning_rate": 0.0001719623183777742,
"loss": 0.7319,
"step": 3590
},
{
"epoch": 0.06,
"learning_rate": 0.0001724413220501357,
"loss": 0.7584,
"step": 3600
},
{
"epoch": 0.06,
"learning_rate": 0.0001729203257224972,
"loss": 0.8264,
"step": 3610
},
{
"epoch": 0.06,
"learning_rate": 0.0001733993293948587,
"loss": 0.8127,
"step": 3620
},
{
"epoch": 0.06,
"learning_rate": 0.00017387833306722018,
"loss": 0.8102,
"step": 3630
},
{
"epoch": 0.06,
"learning_rate": 0.00017435733673958168,
"loss": 0.8068,
"step": 3640
},
{
"epoch": 0.06,
"learning_rate": 0.00017483634041194315,
"loss": 0.8134,
"step": 3650
},
{
"epoch": 0.06,
"learning_rate": 0.00017531534408430464,
"loss": 0.7994,
"step": 3660
},
{
"epoch": 0.06,
"learning_rate": 0.00017579434775666613,
"loss": 0.8169,
"step": 3670
},
{
"epoch": 0.06,
"learning_rate": 0.00017627335142902763,
"loss": 0.8135,
"step": 3680
},
{
"epoch": 0.06,
"learning_rate": 0.00017675235510138912,
"loss": 0.8074,
"step": 3690
},
{
"epoch": 0.06,
"learning_rate": 0.0001772313587737506,
"loss": 0.7948,
"step": 3700
},
{
"epoch": 0.06,
"learning_rate": 0.00017771036244611208,
"loss": 0.7862,
"step": 3710
},
{
"epoch": 0.06,
"learning_rate": 0.00017818936611847358,
"loss": 0.7942,
"step": 3720
},
{
"epoch": 0.06,
"learning_rate": 0.00017866836979083504,
"loss": 0.782,
"step": 3730
},
{
"epoch": 0.06,
"learning_rate": 0.0001791473734631965,
"loss": 0.8037,
"step": 3740
},
{
"epoch": 0.06,
"learning_rate": 0.000179626377135558,
"loss": 0.7926,
"step": 3750
},
{
"epoch": 0.06,
"learning_rate": 0.0001801053808079195,
"loss": 0.7788,
"step": 3760
},
{
"epoch": 0.06,
"learning_rate": 0.000180584384480281,
"loss": 0.7084,
"step": 3770
},
{
"epoch": 0.06,
"learning_rate": 0.00018106338815264249,
"loss": 0.6898,
"step": 3780
},
{
"epoch": 0.06,
"learning_rate": 0.00018154239182500395,
"loss": 0.6993,
"step": 3790
},
{
"epoch": 0.06,
"learning_rate": 0.00018202139549736545,
"loss": 0.6843,
"step": 3800
},
{
"epoch": 0.06,
"learning_rate": 0.00018250039916972694,
"loss": 0.6912,
"step": 3810
},
{
"epoch": 0.06,
"learning_rate": 0.00018297940284208843,
"loss": 0.6959,
"step": 3820
},
{
"epoch": 0.06,
"learning_rate": 0.00018345840651444993,
"loss": 0.6788,
"step": 3830
},
{
"epoch": 0.06,
"learning_rate": 0.0001839374101868114,
"loss": 0.6802,
"step": 3840
},
{
"epoch": 0.06,
"learning_rate": 0.0001844164138591729,
"loss": 0.6682,
"step": 3850
},
{
"epoch": 0.06,
"learning_rate": 0.00018489541753153438,
"loss": 0.6739,
"step": 3860
},
{
"epoch": 0.06,
"learning_rate": 0.00018537442120389588,
"loss": 0.667,
"step": 3870
},
{
"epoch": 0.06,
"learning_rate": 0.00018585342487625737,
"loss": 0.6771,
"step": 3880
},
{
"epoch": 0.06,
"learning_rate": 0.00018633242854861886,
"loss": 0.6815,
"step": 3890
},
{
"epoch": 0.06,
"learning_rate": 0.00018681143222098033,
"loss": 0.6649,
"step": 3900
},
{
"epoch": 0.06,
"learning_rate": 0.00018729043589334182,
"loss": 0.6694,
"step": 3910
},
{
"epoch": 0.06,
"learning_rate": 0.00018776943956570332,
"loss": 0.6558,
"step": 3920
},
{
"epoch": 0.06,
"learning_rate": 0.0001882484432380648,
"loss": 0.6611,
"step": 3930
},
{
"epoch": 0.06,
"learning_rate": 0.0001887274469104263,
"loss": 0.6879,
"step": 3940
},
{
"epoch": 0.06,
"learning_rate": 0.00018920645058278777,
"loss": 0.6766,
"step": 3950
},
{
"epoch": 0.06,
"learning_rate": 0.00018968545425514927,
"loss": 0.6872,
"step": 3960
},
{
"epoch": 0.06,
"learning_rate": 0.00019016445792751076,
"loss": 0.6774,
"step": 3970
},
{
"epoch": 0.06,
"learning_rate": 0.00019064346159987226,
"loss": 0.682,
"step": 3980
},
{
"epoch": 0.06,
"learning_rate": 0.00019112246527223375,
"loss": 0.6762,
"step": 3990
},
{
"epoch": 0.06,
"learning_rate": 0.00019160146894459522,
"loss": 0.676,
"step": 4000
},
{
"epoch": 0.06,
"learning_rate": 0.0001920804726169567,
"loss": 0.6767,
"step": 4010
},
{
"epoch": 0.06,
"learning_rate": 0.0001925594762893182,
"loss": 0.6728,
"step": 4020
},
{
"epoch": 0.06,
"learning_rate": 0.0001930384799616797,
"loss": 0.6719,
"step": 4030
},
{
"epoch": 0.06,
"learning_rate": 0.0001935174836340412,
"loss": 0.663,
"step": 4040
},
{
"epoch": 0.06,
"learning_rate": 0.00019399648730640266,
"loss": 0.6789,
"step": 4050
},
{
"epoch": 0.06,
"learning_rate": 0.00019447549097876415,
"loss": 0.6626,
"step": 4060
},
{
"epoch": 0.06,
"learning_rate": 0.00019495449465112565,
"loss": 0.6738,
"step": 4070
},
{
"epoch": 0.07,
"learning_rate": 0.00019543349832348714,
"loss": 0.6737,
"step": 4080
},
{
"epoch": 0.07,
"learning_rate": 0.00019591250199584863,
"loss": 0.6771,
"step": 4090
},
{
"epoch": 0.07,
"learning_rate": 0.0001963915056682101,
"loss": 0.6779,
"step": 4100
},
{
"epoch": 0.07,
"learning_rate": 0.0001968705093405716,
"loss": 0.6969,
"step": 4110
},
{
"epoch": 0.07,
"learning_rate": 0.0001973495130129331,
"loss": 0.68,
"step": 4120
},
{
"epoch": 0.07,
"learning_rate": 0.00019782851668529458,
"loss": 0.6753,
"step": 4130
},
{
"epoch": 0.07,
"learning_rate": 0.00019830752035765608,
"loss": 0.6769,
"step": 4140
},
{
"epoch": 0.07,
"learning_rate": 0.00019878652403001757,
"loss": 0.6719,
"step": 4150
},
{
"epoch": 0.07,
"learning_rate": 0.00019926552770237904,
"loss": 0.674,
"step": 4160
},
{
"epoch": 0.07,
"learning_rate": 0.00019974453137474053,
"loss": 0.6635,
"step": 4170
},
{
"epoch": 0.07,
"learning_rate": 0.00020022353504710203,
"loss": 0.6671,
"step": 4180
},
{
"epoch": 0.07,
"learning_rate": 0.00020070253871946352,
"loss": 0.668,
"step": 4190
},
{
"epoch": 0.07,
"learning_rate": 0.000201181542391825,
"loss": 0.6654,
"step": 4200
},
{
"epoch": 0.07,
"learning_rate": 0.00020166054606418648,
"loss": 0.6505,
"step": 4210
},
{
"epoch": 0.07,
"learning_rate": 0.00020213954973654797,
"loss": 0.6583,
"step": 4220
},
{
"epoch": 0.07,
"learning_rate": 0.00020261855340890944,
"loss": 0.6616,
"step": 4230
},
{
"epoch": 0.07,
"learning_rate": 0.00020309755708127094,
"loss": 0.6618,
"step": 4240
},
{
"epoch": 0.07,
"learning_rate": 0.0002035765607536324,
"loss": 0.6524,
"step": 4250
},
{
"epoch": 0.07,
"learning_rate": 0.0002040555644259939,
"loss": 0.662,
"step": 4260
},
{
"epoch": 0.07,
"learning_rate": 0.0002045345680983554,
"loss": 0.647,
"step": 4270
},
{
"epoch": 0.07,
"learning_rate": 0.00020501357177071688,
"loss": 0.6381,
"step": 4280
},
{
"epoch": 0.07,
"learning_rate": 0.00020549257544307838,
"loss": 0.6357,
"step": 4290
},
{
"epoch": 0.07,
"learning_rate": 0.00020597157911543984,
"loss": 0.6382,
"step": 4300
},
{
"epoch": 0.07,
"learning_rate": 0.00020645058278780134,
"loss": 0.6332,
"step": 4310
},
{
"epoch": 0.07,
"learning_rate": 0.00020692958646016283,
"loss": 0.6315,
"step": 4320
},
{
"epoch": 0.07,
"learning_rate": 0.00020740859013252433,
"loss": 0.6352,
"step": 4330
},
{
"epoch": 0.07,
"learning_rate": 0.00020788759380488582,
"loss": 0.6309,
"step": 4340
},
{
"epoch": 0.07,
"learning_rate": 0.0002083665974772473,
"loss": 0.6198,
"step": 4350
},
{
"epoch": 0.07,
"learning_rate": 0.00020884560114960878,
"loss": 0.6222,
"step": 4360
},
{
"epoch": 0.07,
"learning_rate": 0.00020932460482197027,
"loss": 0.6282,
"step": 4370
},
{
"epoch": 0.07,
"learning_rate": 0.00020980360849433177,
"loss": 0.6213,
"step": 4380
},
{
"epoch": 0.07,
"learning_rate": 0.00021028261216669326,
"loss": 0.6237,
"step": 4390
},
{
"epoch": 0.07,
"learning_rate": 0.00021076161583905473,
"loss": 0.6325,
"step": 4400
},
{
"epoch": 0.07,
"learning_rate": 0.00021124061951141622,
"loss": 0.6247,
"step": 4410
},
{
"epoch": 0.07,
"learning_rate": 0.00021171962318377772,
"loss": 0.6229,
"step": 4420
},
{
"epoch": 0.07,
"learning_rate": 0.0002121986268561392,
"loss": 0.672,
"step": 4430
},
{
"epoch": 0.07,
"learning_rate": 0.0002126776305285007,
"loss": 0.958,
"step": 4440
},
{
"epoch": 0.07,
"learning_rate": 0.0002131566342008622,
"loss": 0.9283,
"step": 4450
},
{
"epoch": 0.07,
"learning_rate": 0.00021363563787322367,
"loss": 0.8836,
"step": 4460
},
{
"epoch": 0.07,
"learning_rate": 0.00021411464154558516,
"loss": 0.9024,
"step": 4470
},
{
"epoch": 0.07,
"learning_rate": 0.00021459364521794665,
"loss": 0.8943,
"step": 4480
},
{
"epoch": 0.07,
"learning_rate": 0.00021507264889030815,
"loss": 0.8709,
"step": 4490
},
{
"epoch": 0.07,
"learning_rate": 0.00021555165256266964,
"loss": 0.8923,
"step": 4500
},
{
"epoch": 0.07,
"learning_rate": 0.0002160306562350311,
"loss": 0.8864,
"step": 4510
},
{
"epoch": 0.07,
"learning_rate": 0.0002165096599073926,
"loss": 0.8725,
"step": 4520
},
{
"epoch": 0.07,
"learning_rate": 0.0002169886635797541,
"loss": 0.8794,
"step": 4530
},
{
"epoch": 0.07,
"learning_rate": 0.0002174676672521156,
"loss": 0.8599,
"step": 4540
},
{
"epoch": 0.07,
"learning_rate": 0.00021794667092447708,
"loss": 0.883,
"step": 4550
},
{
"epoch": 0.07,
"learning_rate": 0.00021842567459683855,
"loss": 0.8507,
"step": 4560
},
{
"epoch": 0.07,
"learning_rate": 0.00021890467826920005,
"loss": 0.8668,
"step": 4570
},
{
"epoch": 0.07,
"learning_rate": 0.00021938368194156154,
"loss": 0.8604,
"step": 4580
},
{
"epoch": 0.07,
"learning_rate": 0.00021986268561392303,
"loss": 0.9212,
"step": 4590
},
{
"epoch": 0.07,
"learning_rate": 0.00022034168928628453,
"loss": 0.9333,
"step": 4600
},
{
"epoch": 0.07,
"learning_rate": 0.000220820692958646,
"loss": 0.9508,
"step": 4610
},
{
"epoch": 0.07,
"learning_rate": 0.0002212996966310075,
"loss": 0.9529,
"step": 4620
},
{
"epoch": 0.07,
"learning_rate": 0.00022177870030336898,
"loss": 0.937,
"step": 4630
},
{
"epoch": 0.07,
"learning_rate": 0.00022225770397573048,
"loss": 0.9439,
"step": 4640
},
{
"epoch": 0.07,
"learning_rate": 0.00022273670764809197,
"loss": 0.9287,
"step": 4650
},
{
"epoch": 0.07,
"learning_rate": 0.00022321571132045344,
"loss": 0.9313,
"step": 4660
},
{
"epoch": 0.07,
"learning_rate": 0.00022369471499281493,
"loss": 0.9196,
"step": 4670
},
{
"epoch": 0.07,
"learning_rate": 0.00022417371866517642,
"loss": 0.9217,
"step": 4680
},
{
"epoch": 0.07,
"learning_rate": 0.00022465272233753792,
"loss": 0.9251,
"step": 4690
},
{
"epoch": 0.08,
"learning_rate": 0.0002251317260098994,
"loss": 0.9357,
"step": 4700
},
{
"epoch": 0.08,
"learning_rate": 0.0002256107296822609,
"loss": 0.9199,
"step": 4710
},
{
"epoch": 0.08,
"learning_rate": 0.00022608973335462237,
"loss": 0.9208,
"step": 4720
},
{
"epoch": 0.08,
"learning_rate": 0.00022656873702698384,
"loss": 0.924,
"step": 4730
},
{
"epoch": 0.08,
"learning_rate": 0.00022704774069934533,
"loss": 0.9353,
"step": 4740
},
{
"epoch": 0.08,
"learning_rate": 0.00022752674437170683,
"loss": 1.0033,
"step": 4750
},
{
"epoch": 0.08,
"learning_rate": 0.0002280057480440683,
"loss": 0.9979,
"step": 4760
},
{
"epoch": 0.08,
"learning_rate": 0.0002284847517164298,
"loss": 0.9915,
"step": 4770
},
{
"epoch": 0.08,
"learning_rate": 0.00022896375538879128,
"loss": 0.9785,
"step": 4780
},
{
"epoch": 0.08,
"learning_rate": 0.00022944275906115278,
"loss": 0.9813,
"step": 4790
},
{
"epoch": 0.08,
"learning_rate": 0.00022992176273351427,
"loss": 0.9785,
"step": 4800
},
{
"epoch": 0.08,
"learning_rate": 0.00023040076640587574,
"loss": 0.984,
"step": 4810
},
{
"epoch": 0.08,
"learning_rate": 0.00023087977007823723,
"loss": 0.9657,
"step": 4820
},
{
"epoch": 0.08,
"learning_rate": 0.00023135877375059872,
"loss": 0.9531,
"step": 4830
},
{
"epoch": 0.08,
"learning_rate": 0.00023183777742296022,
"loss": 0.9606,
"step": 4840
},
{
"epoch": 0.08,
"learning_rate": 0.0002323167810953217,
"loss": 0.9686,
"step": 4850
},
{
"epoch": 0.08,
"learning_rate": 0.00023279578476768318,
"loss": 0.968,
"step": 4860
},
{
"epoch": 0.08,
"learning_rate": 0.00023327478844004467,
"loss": 0.9517,
"step": 4870
},
{
"epoch": 0.08,
"learning_rate": 0.00023375379211240617,
"loss": 0.9517,
"step": 4880
},
{
"epoch": 0.08,
"learning_rate": 0.00023423279578476766,
"loss": 0.9465,
"step": 4890
},
{
"epoch": 0.08,
"learning_rate": 0.00023471179945712916,
"loss": 0.9635,
"step": 4900
},
{
"epoch": 0.08,
"learning_rate": 0.00023519080312949062,
"loss": 0.9523,
"step": 4910
},
{
"epoch": 0.08,
"learning_rate": 0.00023566980680185212,
"loss": 0.953,
"step": 4920
},
{
"epoch": 0.08,
"learning_rate": 0.0002361488104742136,
"loss": 0.9455,
"step": 4930
},
{
"epoch": 0.08,
"learning_rate": 0.0002366278141465751,
"loss": 0.9318,
"step": 4940
},
{
"epoch": 0.08,
"learning_rate": 0.0002371068178189366,
"loss": 0.9487,
"step": 4950
},
{
"epoch": 0.08,
"learning_rate": 0.0002375858214912981,
"loss": 0.9319,
"step": 4960
},
{
"epoch": 0.08,
"learning_rate": 0.00023806482516365956,
"loss": 0.9357,
"step": 4970
},
{
"epoch": 0.08,
"learning_rate": 0.00023854382883602105,
"loss": 0.9402,
"step": 4980
},
{
"epoch": 0.08,
"learning_rate": 0.00023902283250838255,
"loss": 0.9298,
"step": 4990
},
{
"epoch": 0.08,
"learning_rate": 0.00023950183618074404,
"loss": 0.9387,
"step": 5000
},
{
"epoch": 0.08,
"learning_rate": 0.00023998083985310553,
"loss": 0.9283,
"step": 5010
},
{
"epoch": 0.08,
"learning_rate": 0.000240459843525467,
"loss": 0.9295,
"step": 5020
},
{
"epoch": 0.08,
"learning_rate": 0.0002409388471978285,
"loss": 0.9248,
"step": 5030
},
{
"epoch": 0.08,
"learning_rate": 0.00024141785087019,
"loss": 0.92,
"step": 5040
},
{
"epoch": 0.08,
"learning_rate": 0.00024189685454255148,
"loss": 0.9262,
"step": 5050
},
{
"epoch": 0.08,
"learning_rate": 0.00024237585821491298,
"loss": 0.9404,
"step": 5060
},
{
"epoch": 0.08,
"learning_rate": 0.00024285486188727444,
"loss": 0.9296,
"step": 5070
},
{
"epoch": 0.08,
"learning_rate": 0.00024333386555963594,
"loss": 0.9182,
"step": 5080
},
{
"epoch": 0.08,
"learning_rate": 0.00024381286923199743,
"loss": 0.9129,
"step": 5090
},
{
"epoch": 0.08,
"learning_rate": 0.0002442918729043589,
"loss": 0.9244,
"step": 5100
},
{
"epoch": 0.08,
"learning_rate": 0.0002447708765767204,
"loss": 0.9113,
"step": 5110
},
{
"epoch": 0.08,
"learning_rate": 0.0002452498802490819,
"loss": 0.8955,
"step": 5120
},
{
"epoch": 0.08,
"learning_rate": 0.0002457288839214434,
"loss": 0.901,
"step": 5130
},
{
"epoch": 0.08,
"learning_rate": 0.0002462078875938049,
"loss": 0.9069,
"step": 5140
},
{
"epoch": 0.08,
"learning_rate": 0.00024668689126616637,
"loss": 0.8934,
"step": 5150
},
{
"epoch": 0.08,
"learning_rate": 0.00024716589493852784,
"loss": 0.8879,
"step": 5160
},
{
"epoch": 0.08,
"learning_rate": 0.00024764489861088936,
"loss": 0.8909,
"step": 5170
},
{
"epoch": 0.08,
"learning_rate": 0.0002481239022832508,
"loss": 0.9004,
"step": 5180
},
{
"epoch": 0.08,
"learning_rate": 0.00024860290595561234,
"loss": 0.8819,
"step": 5190
},
{
"epoch": 0.08,
"learning_rate": 0.0002490819096279738,
"loss": 0.8925,
"step": 5200
},
{
"epoch": 0.08,
"learning_rate": 0.0002495609133003353,
"loss": 0.8959,
"step": 5210
},
{
"epoch": 0.08,
"learning_rate": 0.00025003991697269674,
"loss": 0.9681,
"step": 5220
},
{
"epoch": 0.08,
"learning_rate": 0.00025051892064505827,
"loss": 0.9684,
"step": 5230
},
{
"epoch": 0.08,
"learning_rate": 0.00025099792431741973,
"loss": 0.9552,
"step": 5240
},
{
"epoch": 0.08,
"learning_rate": 0.0002514769279897812,
"loss": 0.9704,
"step": 5250
},
{
"epoch": 0.08,
"learning_rate": 0.0002519559316621427,
"loss": 0.9671,
"step": 5260
},
{
"epoch": 0.08,
"learning_rate": 0.0002524349353345042,
"loss": 0.963,
"step": 5270
},
{
"epoch": 0.08,
"learning_rate": 0.0002529139390068657,
"loss": 0.9612,
"step": 5280
},
{
"epoch": 0.08,
"learning_rate": 0.0002533929426792272,
"loss": 0.9592,
"step": 5290
},
{
"epoch": 0.08,
"learning_rate": 0.00025387194635158864,
"loss": 0.9516,
"step": 5300
},
{
"epoch": 0.08,
"learning_rate": 0.00025435095002395016,
"loss": 0.9569,
"step": 5310
},
{
"epoch": 0.08,
"learning_rate": 0.00025482995369631163,
"loss": 0.9553,
"step": 5320
},
{
"epoch": 0.09,
"learning_rate": 0.00025530895736867315,
"loss": 0.9678,
"step": 5330
},
{
"epoch": 0.09,
"learning_rate": 0.0002557879610410346,
"loss": 0.9645,
"step": 5340
},
{
"epoch": 0.09,
"learning_rate": 0.0002562669647133961,
"loss": 0.9569,
"step": 5350
},
{
"epoch": 0.09,
"learning_rate": 0.0002567459683857576,
"loss": 0.9448,
"step": 5360
},
{
"epoch": 0.09,
"learning_rate": 0.00025722497205811907,
"loss": 0.9755,
"step": 5370
},
{
"epoch": 0.09,
"learning_rate": 0.0002577039757304806,
"loss": 0.9914,
"step": 5380
},
{
"epoch": 0.09,
"learning_rate": 0.00025818297940284206,
"loss": 0.9916,
"step": 5390
},
{
"epoch": 0.09,
"learning_rate": 0.0002586619830752035,
"loss": 0.9896,
"step": 5400
},
{
"epoch": 0.09,
"learning_rate": 0.00025914098674756505,
"loss": 0.9998,
"step": 5410
},
{
"epoch": 0.09,
"learning_rate": 0.0002596199904199265,
"loss": 0.9861,
"step": 5420
},
{
"epoch": 0.09,
"learning_rate": 0.00026009899409228804,
"loss": 0.9857,
"step": 5430
},
{
"epoch": 0.09,
"learning_rate": 0.0002605779977646495,
"loss": 0.9788,
"step": 5440
},
{
"epoch": 0.09,
"learning_rate": 0.00026105700143701097,
"loss": 0.9827,
"step": 5450
},
{
"epoch": 0.09,
"learning_rate": 0.0002615360051093725,
"loss": 0.995,
"step": 5460
},
{
"epoch": 0.09,
"learning_rate": 0.00026201500878173396,
"loss": 0.9898,
"step": 5470
},
{
"epoch": 0.09,
"learning_rate": 0.0002624940124540955,
"loss": 0.9771,
"step": 5480
},
{
"epoch": 0.09,
"learning_rate": 0.00026297301612645695,
"loss": 0.9728,
"step": 5490
},
{
"epoch": 0.09,
"learning_rate": 0.0002634520197988184,
"loss": 0.9766,
"step": 5500
},
{
"epoch": 0.09,
"learning_rate": 0.00026393102347117993,
"loss": 0.9803,
"step": 5510
},
{
"epoch": 0.09,
"learning_rate": 0.0002644100271435414,
"loss": 0.9785,
"step": 5520
},
{
"epoch": 0.09,
"learning_rate": 0.0002648890308159029,
"loss": 0.9898,
"step": 5530
},
{
"epoch": 0.09,
"learning_rate": 0.0002653680344882644,
"loss": 0.9976,
"step": 5540
},
{
"epoch": 0.09,
"learning_rate": 0.00026584703816062585,
"loss": 0.9993,
"step": 5550
},
{
"epoch": 0.09,
"learning_rate": 0.0002663260418329874,
"loss": 1.0075,
"step": 5560
},
{
"epoch": 0.09,
"learning_rate": 0.00026680504550534884,
"loss": 1.0011,
"step": 5570
},
{
"epoch": 0.09,
"learning_rate": 0.00026728404917771036,
"loss": 1.0041,
"step": 5580
},
{
"epoch": 0.09,
"learning_rate": 0.00026776305285007183,
"loss": 0.9964,
"step": 5590
},
{
"epoch": 0.09,
"learning_rate": 0.0002682420565224333,
"loss": 0.9956,
"step": 5600
},
{
"epoch": 0.09,
"learning_rate": 0.0002687210601947948,
"loss": 0.9928,
"step": 5610
},
{
"epoch": 0.09,
"learning_rate": 0.0002692000638671563,
"loss": 0.9877,
"step": 5620
},
{
"epoch": 0.09,
"learning_rate": 0.0002696790675395178,
"loss": 0.9948,
"step": 5630
},
{
"epoch": 0.09,
"learning_rate": 0.00027015807121187927,
"loss": 0.9955,
"step": 5640
},
{
"epoch": 0.09,
"learning_rate": 0.0002706370748842408,
"loss": 0.986,
"step": 5650
},
{
"epoch": 0.09,
"learning_rate": 0.00027111607855660226,
"loss": 0.9942,
"step": 5660
},
{
"epoch": 0.09,
"learning_rate": 0.00027159508222896373,
"loss": 0.9883,
"step": 5670
},
{
"epoch": 0.09,
"learning_rate": 0.00027207408590132525,
"loss": 1.0043,
"step": 5680
},
{
"epoch": 0.09,
"learning_rate": 0.0002725530895736867,
"loss": 0.997,
"step": 5690
},
{
"epoch": 0.09,
"learning_rate": 0.00027303209324604824,
"loss": 1.0037,
"step": 5700
},
{
"epoch": 0.09,
"learning_rate": 0.0002735110969184097,
"loss": 1.0123,
"step": 5710
},
{
"epoch": 0.09,
"learning_rate": 0.00027399010059077117,
"loss": 1.0016,
"step": 5720
},
{
"epoch": 0.09,
"learning_rate": 0.00027446910426313264,
"loss": 1.0128,
"step": 5730
},
{
"epoch": 0.09,
"learning_rate": 0.00027494810793549416,
"loss": 0.9919,
"step": 5740
},
{
"epoch": 0.09,
"learning_rate": 0.0002754271116078556,
"loss": 0.9995,
"step": 5750
},
{
"epoch": 0.09,
"learning_rate": 0.0002759061152802171,
"loss": 1.0071,
"step": 5760
},
{
"epoch": 0.09,
"learning_rate": 0.0002763851189525786,
"loss": 0.9988,
"step": 5770
},
{
"epoch": 0.09,
"learning_rate": 0.0002768641226249401,
"loss": 1.0016,
"step": 5780
},
{
"epoch": 0.09,
"learning_rate": 0.0002773431262973016,
"loss": 1.0005,
"step": 5790
},
{
"epoch": 0.09,
"learning_rate": 0.00027782212996966307,
"loss": 0.9998,
"step": 5800
},
{
"epoch": 0.09,
"learning_rate": 0.00027830113364202453,
"loss": 0.9881,
"step": 5810
},
{
"epoch": 0.09,
"learning_rate": 0.00027878013731438606,
"loss": 0.9985,
"step": 5820
},
{
"epoch": 0.09,
"learning_rate": 0.0002792591409867475,
"loss": 1.0091,
"step": 5830
},
{
"epoch": 0.09,
"learning_rate": 0.00027973814465910904,
"loss": 1.005,
"step": 5840
},
{
"epoch": 0.09,
"learning_rate": 0.0002802171483314705,
"loss": 0.9998,
"step": 5850
},
{
"epoch": 0.09,
"learning_rate": 0.000280696152003832,
"loss": 1.0121,
"step": 5860
},
{
"epoch": 0.09,
"learning_rate": 0.0002811751556761935,
"loss": 1.0055,
"step": 5870
},
{
"epoch": 0.09,
"learning_rate": 0.00028165415934855496,
"loss": 1.0139,
"step": 5880
},
{
"epoch": 0.09,
"learning_rate": 0.0002821331630209165,
"loss": 0.9987,
"step": 5890
},
{
"epoch": 0.09,
"learning_rate": 0.00028261216669327795,
"loss": 1.0034,
"step": 5900
},
{
"epoch": 0.09,
"learning_rate": 0.0002830911703656394,
"loss": 1.0107,
"step": 5910
},
{
"epoch": 0.09,
"learning_rate": 0.00028357017403800094,
"loss": 1.0041,
"step": 5920
},
{
"epoch": 0.09,
"learning_rate": 0.0002840491777103624,
"loss": 1.0114,
"step": 5930
},
{
"epoch": 0.09,
"learning_rate": 0.00028452818138272393,
"loss": 1.0142,
"step": 5940
},
{
"epoch": 0.1,
"learning_rate": 0.0002850071850550854,
"loss": 0.9973,
"step": 5950
},
{
"epoch": 0.1,
"learning_rate": 0.00028548618872744686,
"loss": 0.9952,
"step": 5960
},
{
"epoch": 0.1,
"learning_rate": 0.0002859651923998084,
"loss": 0.9993,
"step": 5970
},
{
"epoch": 0.1,
"learning_rate": 0.00028644419607216985,
"loss": 1.0018,
"step": 5980
},
{
"epoch": 0.1,
"learning_rate": 0.00028692319974453137,
"loss": 0.9958,
"step": 5990
},
{
"epoch": 0.1,
"learning_rate": 0.00028740220341689284,
"loss": 0.999,
"step": 6000
},
{
"epoch": 0.1,
"learning_rate": 0.0002878812070892543,
"loss": 1.018,
"step": 6010
},
{
"epoch": 0.1,
"learning_rate": 0.0002883602107616158,
"loss": 1.0012,
"step": 6020
},
{
"epoch": 0.1,
"learning_rate": 0.0002888392144339773,
"loss": 0.9982,
"step": 6030
},
{
"epoch": 0.1,
"learning_rate": 0.0002893182181063388,
"loss": 1.0085,
"step": 6040
},
{
"epoch": 0.1,
"learning_rate": 0.0002897972217787003,
"loss": 0.9975,
"step": 6050
},
{
"epoch": 0.1,
"learning_rate": 0.00029027622545106175,
"loss": 1.0067,
"step": 6060
},
{
"epoch": 0.1,
"learning_rate": 0.00029075522912342327,
"loss": 1.0052,
"step": 6070
},
{
"epoch": 0.1,
"learning_rate": 0.00029123423279578473,
"loss": 0.997,
"step": 6080
},
{
"epoch": 0.1,
"learning_rate": 0.00029171323646814626,
"loss": 0.9969,
"step": 6090
},
{
"epoch": 0.1,
"learning_rate": 0.0002921922401405077,
"loss": 0.9922,
"step": 6100
},
{
"epoch": 0.1,
"learning_rate": 0.0002926712438128692,
"loss": 0.9941,
"step": 6110
},
{
"epoch": 0.1,
"learning_rate": 0.0002931502474852307,
"loss": 1.0063,
"step": 6120
},
{
"epoch": 0.1,
"learning_rate": 0.0002936292511575922,
"loss": 1.0138,
"step": 6130
},
{
"epoch": 0.1,
"learning_rate": 0.0002941082548299537,
"loss": 1.0033,
"step": 6140
},
{
"epoch": 0.1,
"learning_rate": 0.00029458725850231517,
"loss": 1.0086,
"step": 6150
},
{
"epoch": 0.1,
"learning_rate": 0.0002950662621746767,
"loss": 1.0169,
"step": 6160
},
{
"epoch": 0.1,
"learning_rate": 0.00029554526584703815,
"loss": 1.02,
"step": 6170
},
{
"epoch": 0.1,
"learning_rate": 0.0002960242695193996,
"loss": 1.0146,
"step": 6180
},
{
"epoch": 0.1,
"learning_rate": 0.00029650327319176114,
"loss": 1.0217,
"step": 6190
},
{
"epoch": 0.1,
"learning_rate": 0.0002969822768641226,
"loss": 1.0076,
"step": 6200
},
{
"epoch": 0.1,
"learning_rate": 0.00029746128053648413,
"loss": 1.0176,
"step": 6210
},
{
"epoch": 0.1,
"learning_rate": 0.00029794028420884554,
"loss": 0.9997,
"step": 6220
},
{
"epoch": 0.1,
"learning_rate": 0.00029841928788120706,
"loss": 1.0161,
"step": 6230
},
{
"epoch": 0.1,
"learning_rate": 0.00029889829155356853,
"loss": 1.0054,
"step": 6240
},
{
"epoch": 0.1,
"learning_rate": 0.00029937729522593005,
"loss": 1.0074,
"step": 6250
},
{
"epoch": 0.1,
"learning_rate": 0.0002998562988982915,
"loss": 1.0096,
"step": 6260
},
{
"epoch": 0.1,
"learning_rate": 0.00029996273953158265,
"loss": 1.0126,
"step": 6270
},
{
"epoch": 0.1,
"learning_rate": 0.0002999095102909865,
"loss": 1.0195,
"step": 6280
},
{
"epoch": 0.1,
"learning_rate": 0.0002998562810503903,
"loss": 1.0131,
"step": 6290
},
{
"epoch": 0.1,
"learning_rate": 0.00029980305180979416,
"loss": 1.0222,
"step": 6300
},
{
"epoch": 0.1,
"learning_rate": 0.000299749822569198,
"loss": 1.0131,
"step": 6310
},
{
"epoch": 0.1,
"learning_rate": 0.0002996965933286018,
"loss": 1.0123,
"step": 6320
},
{
"epoch": 0.1,
"learning_rate": 0.00029964336408800567,
"loss": 1.0195,
"step": 6330
},
{
"epoch": 0.1,
"learning_rate": 0.00029959013484740947,
"loss": 1.0154,
"step": 6340
},
{
"epoch": 0.1,
"learning_rate": 0.0002995369056068133,
"loss": 1.0246,
"step": 6350
},
{
"epoch": 0.1,
"learning_rate": 0.0002994836763662172,
"loss": 1.0102,
"step": 6360
},
{
"epoch": 0.1,
"learning_rate": 0.000299430447125621,
"loss": 1.001,
"step": 6370
},
{
"epoch": 0.1,
"learning_rate": 0.00029937721788502483,
"loss": 1.0246,
"step": 6380
},
{
"epoch": 0.1,
"learning_rate": 0.00029932398864442863,
"loss": 1.0219,
"step": 6390
},
{
"epoch": 0.1,
"learning_rate": 0.0002992707594038325,
"loss": 1.012,
"step": 6400
},
{
"epoch": 0.1,
"learning_rate": 0.00029921753016323634,
"loss": 1.0151,
"step": 6410
},
{
"epoch": 0.1,
"learning_rate": 0.00029916430092264014,
"loss": 1.0256,
"step": 6420
},
{
"epoch": 0.1,
"learning_rate": 0.000299111071682044,
"loss": 1.0214,
"step": 6430
},
{
"epoch": 0.1,
"learning_rate": 0.0002990578424414478,
"loss": 1.0275,
"step": 6440
},
{
"epoch": 0.1,
"learning_rate": 0.00029900461320085165,
"loss": 1.0189,
"step": 6450
},
{
"epoch": 0.1,
"learning_rate": 0.0002989513839602555,
"loss": 1.0078,
"step": 6460
},
{
"epoch": 0.1,
"learning_rate": 0.0002988981547196593,
"loss": 1.0091,
"step": 6470
},
{
"epoch": 0.1,
"learning_rate": 0.00029884492547906316,
"loss": 1.0082,
"step": 6480
},
{
"epoch": 0.1,
"learning_rate": 0.00029879169623846696,
"loss": 1.0128,
"step": 6490
},
{
"epoch": 0.1,
"learning_rate": 0.0002987384669978708,
"loss": 1.0299,
"step": 6500
},
{
"epoch": 0.1,
"learning_rate": 0.0002986852377572746,
"loss": 1.0142,
"step": 6510
},
{
"epoch": 0.1,
"learning_rate": 0.0002986320085166785,
"loss": 1.009,
"step": 6520
},
{
"epoch": 0.1,
"learning_rate": 0.00029857877927608233,
"loss": 1.0204,
"step": 6530
},
{
"epoch": 0.1,
"learning_rate": 0.00029852555003548613,
"loss": 1.0201,
"step": 6540
},
{
"epoch": 0.1,
"learning_rate": 0.00029847232079489,
"loss": 1.0111,
"step": 6550
},
{
"epoch": 0.1,
"learning_rate": 0.0002984190915542938,
"loss": 1.0296,
"step": 6560
},
{
"epoch": 0.1,
"learning_rate": 0.00029836586231369764,
"loss": 1.0169,
"step": 6570
},
{
"epoch": 0.11,
"learning_rate": 0.00029831263307310144,
"loss": 1.0175,
"step": 6580
},
{
"epoch": 0.11,
"learning_rate": 0.0002982594038325053,
"loss": 1.0181,
"step": 6590
},
{
"epoch": 0.11,
"learning_rate": 0.00029820617459190915,
"loss": 1.0091,
"step": 6600
},
{
"epoch": 0.11,
"learning_rate": 0.00029815294535131295,
"loss": 1.0253,
"step": 6610
},
{
"epoch": 0.11,
"learning_rate": 0.0002980997161107168,
"loss": 1.0158,
"step": 6620
},
{
"epoch": 0.11,
"learning_rate": 0.0002980464868701206,
"loss": 1.0082,
"step": 6630
},
{
"epoch": 0.11,
"learning_rate": 0.00029799325762952446,
"loss": 1.023,
"step": 6640
},
{
"epoch": 0.11,
"learning_rate": 0.00029794002838892826,
"loss": 1.0094,
"step": 6650
},
{
"epoch": 0.11,
"learning_rate": 0.0002978867991483321,
"loss": 1.0106,
"step": 6660
},
{
"epoch": 0.11,
"learning_rate": 0.00029783356990773597,
"loss": 1.0131,
"step": 6670
},
{
"epoch": 0.11,
"learning_rate": 0.0002977803406671398,
"loss": 1.0325,
"step": 6680
},
{
"epoch": 0.11,
"learning_rate": 0.00029772711142654363,
"loss": 1.021,
"step": 6690
},
{
"epoch": 0.11,
"learning_rate": 0.00029767388218594743,
"loss": 1.022,
"step": 6700
},
{
"epoch": 0.11,
"learning_rate": 0.0002976206529453513,
"loss": 1.0157,
"step": 6710
},
{
"epoch": 0.11,
"learning_rate": 0.0002975674237047551,
"loss": 1.0253,
"step": 6720
},
{
"epoch": 0.11,
"learning_rate": 0.00029751419446415894,
"loss": 1.0178,
"step": 6730
},
{
"epoch": 0.11,
"learning_rate": 0.0002974609652235628,
"loss": 1.0079,
"step": 6740
},
{
"epoch": 0.11,
"learning_rate": 0.0002974077359829666,
"loss": 1.0097,
"step": 6750
},
{
"epoch": 0.11,
"learning_rate": 0.00029735450674237045,
"loss": 1.0082,
"step": 6760
},
{
"epoch": 0.11,
"learning_rate": 0.00029730127750177425,
"loss": 1.0111,
"step": 6770
},
{
"epoch": 0.11,
"learning_rate": 0.0002972480482611781,
"loss": 1.028,
"step": 6780
},
{
"epoch": 0.11,
"learning_rate": 0.0002971948190205819,
"loss": 1.0176,
"step": 6790
},
{
"epoch": 0.11,
"learning_rate": 0.00029714158977998576,
"loss": 1.0292,
"step": 6800
},
{
"epoch": 0.11,
"learning_rate": 0.0002970883605393896,
"loss": 1.0249,
"step": 6810
},
{
"epoch": 0.11,
"learning_rate": 0.0002970351312987934,
"loss": 1.0161,
"step": 6820
},
{
"epoch": 0.11,
"learning_rate": 0.00029698190205819727,
"loss": 1.0332,
"step": 6830
},
{
"epoch": 0.11,
"learning_rate": 0.00029692867281760107,
"loss": 1.0401,
"step": 6840
},
{
"epoch": 0.11,
"learning_rate": 0.0002968754435770049,
"loss": 1.0431,
"step": 6850
},
{
"epoch": 0.11,
"learning_rate": 0.0002968222143364088,
"loss": 1.0207,
"step": 6860
},
{
"epoch": 0.11,
"learning_rate": 0.0002967689850958126,
"loss": 1.0405,
"step": 6870
},
{
"epoch": 0.11,
"learning_rate": 0.00029671575585521644,
"loss": 1.0123,
"step": 6880
},
{
"epoch": 0.11,
"learning_rate": 0.0002966625266146203,
"loss": 1.0382,
"step": 6890
},
{
"epoch": 0.11,
"learning_rate": 0.0002966092973740241,
"loss": 1.0264,
"step": 6900
},
{
"epoch": 0.11,
"learning_rate": 0.00029655606813342795,
"loss": 1.0187,
"step": 6910
},
{
"epoch": 0.11,
"learning_rate": 0.00029650283889283175,
"loss": 1.0317,
"step": 6920
},
{
"epoch": 0.11,
"learning_rate": 0.0002964496096522356,
"loss": 1.0163,
"step": 6930
},
{
"epoch": 0.11,
"learning_rate": 0.00029639638041163946,
"loss": 1.0273,
"step": 6940
},
{
"epoch": 0.11,
"learning_rate": 0.00029634315117104326,
"loss": 1.0163,
"step": 6950
},
{
"epoch": 0.11,
"learning_rate": 0.0002962899219304471,
"loss": 1.1661,
"step": 6960
},
{
"epoch": 0.11,
"learning_rate": 0.0002962366926898509,
"loss": 1.1242,
"step": 6970
},
{
"epoch": 0.11,
"learning_rate": 0.00029618346344925477,
"loss": 1.0727,
"step": 6980
},
{
"epoch": 0.11,
"learning_rate": 0.0002961302342086586,
"loss": 1.0681,
"step": 6990
},
{
"epoch": 0.11,
"learning_rate": 0.0002960770049680624,
"loss": 1.0341,
"step": 7000
},
{
"epoch": 0.11,
"learning_rate": 0.0002960237757274663,
"loss": 1.0658,
"step": 7010
},
{
"epoch": 0.11,
"learning_rate": 0.00029597054648687013,
"loss": 1.0571,
"step": 7020
},
{
"epoch": 0.11,
"learning_rate": 0.00029591731724627393,
"loss": 1.0424,
"step": 7030
},
{
"epoch": 0.11,
"learning_rate": 0.0002958640880056778,
"loss": 1.0132,
"step": 7040
},
{
"epoch": 0.11,
"learning_rate": 0.0002958108587650816,
"loss": 1.013,
"step": 7050
},
{
"epoch": 0.11,
"learning_rate": 0.00029575762952448545,
"loss": 1.0305,
"step": 7060
},
{
"epoch": 0.11,
"learning_rate": 0.00029570440028388925,
"loss": 1.0169,
"step": 7070
},
{
"epoch": 0.11,
"learning_rate": 0.0002956511710432931,
"loss": 1.0077,
"step": 7080
},
{
"epoch": 0.11,
"learning_rate": 0.00029559794180269696,
"loss": 1.0245,
"step": 7090
},
{
"epoch": 0.11,
"learning_rate": 0.00029554471256210076,
"loss": 0.9795,
"step": 7100
},
{
"epoch": 0.11,
"learning_rate": 0.0002954914833215046,
"loss": 0.9896,
"step": 7110
},
{
"epoch": 0.11,
"learning_rate": 0.0002954382540809084,
"loss": 1.0317,
"step": 7120
},
{
"epoch": 0.11,
"learning_rate": 0.00029538502484031227,
"loss": 1.0483,
"step": 7130
},
{
"epoch": 0.11,
"learning_rate": 0.00029533179559971607,
"loss": 1.081,
"step": 7140
},
{
"epoch": 0.11,
"learning_rate": 0.0002952785663591199,
"loss": 1.0491,
"step": 7150
},
{
"epoch": 0.11,
"learning_rate": 0.0002952253371185238,
"loss": 1.0396,
"step": 7160
},
{
"epoch": 0.11,
"learning_rate": 0.0002951721078779276,
"loss": 1.0584,
"step": 7170
},
{
"epoch": 0.11,
"learning_rate": 0.00029511887863733143,
"loss": 1.0595,
"step": 7180
},
{
"epoch": 0.11,
"learning_rate": 0.00029506564939673523,
"loss": 1.0468,
"step": 7190
},
{
"epoch": 0.11,
"learning_rate": 0.0002950124201561391,
"loss": 1.0235,
"step": 7200
},
{
"epoch": 0.12,
"learning_rate": 0.0002949591909155429,
"loss": 1.0191,
"step": 7210
},
{
"epoch": 0.12,
"learning_rate": 0.00029490596167494674,
"loss": 1.0417,
"step": 7220
},
{
"epoch": 0.12,
"learning_rate": 0.0002948527324343506,
"loss": 1.0059,
"step": 7230
},
{
"epoch": 0.12,
"learning_rate": 0.0002947995031937544,
"loss": 1.0449,
"step": 7240
},
{
"epoch": 0.12,
"learning_rate": 0.00029474627395315825,
"loss": 0.9896,
"step": 7250
},
{
"epoch": 0.12,
"learning_rate": 0.00029469304471256205,
"loss": 1.0022,
"step": 7260
},
{
"epoch": 0.12,
"learning_rate": 0.0002946398154719659,
"loss": 1.0225,
"step": 7270
},
{
"epoch": 0.12,
"learning_rate": 0.0002945865862313697,
"loss": 1.0086,
"step": 7280
},
{
"epoch": 0.12,
"learning_rate": 0.00029453335699077357,
"loss": 1.0692,
"step": 7290
},
{
"epoch": 0.12,
"learning_rate": 0.0002944801277501774,
"loss": 1.0995,
"step": 7300
},
{
"epoch": 0.12,
"learning_rate": 0.0002944268985095812,
"loss": 1.0794,
"step": 7310
},
{
"epoch": 0.12,
"learning_rate": 0.0002943736692689851,
"loss": 1.0765,
"step": 7320
},
{
"epoch": 0.12,
"learning_rate": 0.0002943204400283889,
"loss": 1.0532,
"step": 7330
},
{
"epoch": 0.12,
"learning_rate": 0.00029426721078779273,
"loss": 1.0671,
"step": 7340
},
{
"epoch": 0.12,
"learning_rate": 0.00029421398154719653,
"loss": 1.0371,
"step": 7350
},
{
"epoch": 0.12,
"learning_rate": 0.0002941607523066004,
"loss": 1.0449,
"step": 7360
},
{
"epoch": 0.12,
"learning_rate": 0.00029410752306600424,
"loss": 1.0338,
"step": 7370
},
{
"epoch": 0.12,
"learning_rate": 0.00029405429382540804,
"loss": 1.0312,
"step": 7380
}
],
"logging_steps": 10,
"max_steps": 62623,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 4.80334442885913e+18,
"trial_name": null,
"trial_params": null
}