wangrongsheng's picture
commit from root
a97d6fd
raw
history blame contribute delete
No virus
60.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.1590171534538711,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999983427462679e-05,
"loss": 1.3476,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 4.999933710070436e-05,
"loss": 1.1454,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 4.999850848482424e-05,
"loss": 1.0263,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4.999734843797226e-05,
"loss": 1.0283,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 4.9995856975528347e-05,
"loss": 0.9733,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 4.999403411726636e-05,
"loss": 0.9591,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 4.999187988735381e-05,
"loss": 0.9617,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 4.998939431435153e-05,
"loss": 0.9414,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 4.998657743121333e-05,
"loss": 0.9233,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 4.998342927528553e-05,
"loss": 0.9236,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 4.997994988830648e-05,
"loss": 0.8743,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 4.997613931640598e-05,
"loss": 0.895,
"step": 120
},
{
"epoch": 0.03,
"learning_rate": 4.997199761010472e-05,
"loss": 0.8831,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 4.996752482431356e-05,
"loss": 0.8799,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 4.996272101833284e-05,
"loss": 0.877,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 4.995758625585155e-05,
"loss": 0.8745,
"step": 160
},
{
"epoch": 0.04,
"learning_rate": 4.995212060494653e-05,
"loss": 0.8716,
"step": 170
},
{
"epoch": 0.04,
"learning_rate": 4.9946324138081534e-05,
"loss": 0.8534,
"step": 180
},
{
"epoch": 0.04,
"learning_rate": 4.99401969321063e-05,
"loss": 0.8449,
"step": 190
},
{
"epoch": 0.05,
"learning_rate": 4.9933739068255513e-05,
"loss": 0.8588,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 4.992695063214772e-05,
"loss": 0.8409,
"step": 210
},
{
"epoch": 0.05,
"learning_rate": 4.99198317137842e-05,
"loss": 0.8517,
"step": 220
},
{
"epoch": 0.05,
"learning_rate": 4.99123824075478e-05,
"loss": 0.8698,
"step": 230
},
{
"epoch": 0.06,
"learning_rate": 4.990460281220164e-05,
"loss": 0.848,
"step": 240
},
{
"epoch": 0.06,
"learning_rate": 4.9896493030887815e-05,
"loss": 0.8322,
"step": 250
},
{
"epoch": 0.06,
"learning_rate": 4.988805317112607e-05,
"loss": 0.8376,
"step": 260
},
{
"epoch": 0.06,
"learning_rate": 4.98792833448123e-05,
"loss": 0.8309,
"step": 270
},
{
"epoch": 0.06,
"learning_rate": 4.987018366821713e-05,
"loss": 0.8195,
"step": 280
},
{
"epoch": 0.07,
"learning_rate": 4.9860754261984346e-05,
"loss": 0.8313,
"step": 290
},
{
"epoch": 0.07,
"learning_rate": 4.98509952511293e-05,
"loss": 0.8115,
"step": 300
},
{
"epoch": 0.07,
"learning_rate": 4.984090676503723e-05,
"loss": 0.8224,
"step": 310
},
{
"epoch": 0.07,
"learning_rate": 4.983048893746162e-05,
"loss": 0.8157,
"step": 320
},
{
"epoch": 0.08,
"learning_rate": 4.9819741906522306e-05,
"loss": 0.8165,
"step": 330
},
{
"epoch": 0.08,
"learning_rate": 4.980866581470376e-05,
"loss": 0.8144,
"step": 340
},
{
"epoch": 0.08,
"learning_rate": 4.979726080885314e-05,
"loss": 0.8147,
"step": 350
},
{
"epoch": 0.08,
"learning_rate": 4.978552704017835e-05,
"loss": 0.7894,
"step": 360
},
{
"epoch": 0.09,
"learning_rate": 4.977346466424605e-05,
"loss": 0.8144,
"step": 370
},
{
"epoch": 0.09,
"learning_rate": 4.976107384097957e-05,
"loss": 0.7984,
"step": 380
},
{
"epoch": 0.09,
"learning_rate": 4.974835473465682e-05,
"loss": 0.8188,
"step": 390
},
{
"epoch": 0.09,
"learning_rate": 4.97353075139081e-05,
"loss": 0.8049,
"step": 400
},
{
"epoch": 0.1,
"learning_rate": 4.9721932351713846e-05,
"loss": 0.8154,
"step": 410
},
{
"epoch": 0.1,
"learning_rate": 4.9708229425402354e-05,
"loss": 0.7953,
"step": 420
},
{
"epoch": 0.1,
"learning_rate": 4.9694198916647425e-05,
"loss": 0.7996,
"step": 430
},
{
"epoch": 0.1,
"learning_rate": 4.967984101146598e-05,
"loss": 0.7979,
"step": 440
},
{
"epoch": 0.1,
"learning_rate": 4.966515590021554e-05,
"loss": 0.8106,
"step": 450
},
{
"epoch": 0.11,
"learning_rate": 4.965014377759176e-05,
"loss": 0.8008,
"step": 460
},
{
"epoch": 0.11,
"learning_rate": 4.9634804842625807e-05,
"loss": 0.8045,
"step": 470
},
{
"epoch": 0.11,
"learning_rate": 4.961913929868172e-05,
"loss": 0.786,
"step": 480
},
{
"epoch": 0.11,
"learning_rate": 4.960314735345377e-05,
"loss": 0.7897,
"step": 490
},
{
"epoch": 0.12,
"learning_rate": 4.958682921896365e-05,
"loss": 0.7855,
"step": 500
},
{
"epoch": 0.12,
"learning_rate": 4.957018511155765e-05,
"loss": 0.7657,
"step": 510
},
{
"epoch": 0.12,
"learning_rate": 4.955321525190386e-05,
"loss": 0.779,
"step": 520
},
{
"epoch": 0.12,
"learning_rate": 4.953591986498918e-05,
"loss": 0.7923,
"step": 530
},
{
"epoch": 0.13,
"learning_rate": 4.9518299180116366e-05,
"loss": 0.7732,
"step": 540
},
{
"epoch": 0.13,
"learning_rate": 4.9500353430900984e-05,
"loss": 0.7898,
"step": 550
},
{
"epoch": 0.13,
"learning_rate": 4.948208285526832e-05,
"loss": 0.7796,
"step": 560
},
{
"epoch": 0.13,
"learning_rate": 4.94634876954502e-05,
"loss": 0.7819,
"step": 570
},
{
"epoch": 0.13,
"learning_rate": 4.944456819798182e-05,
"loss": 0.7777,
"step": 580
},
{
"epoch": 0.14,
"learning_rate": 4.942532461369843e-05,
"loss": 0.7815,
"step": 590
},
{
"epoch": 0.14,
"learning_rate": 4.940575719773205e-05,
"loss": 0.7807,
"step": 600
},
{
"epoch": 0.14,
"learning_rate": 4.938586620950807e-05,
"loss": 0.7836,
"step": 610
},
{
"epoch": 0.14,
"learning_rate": 4.9365651912741806e-05,
"loss": 0.7795,
"step": 620
},
{
"epoch": 0.15,
"learning_rate": 4.934511457543499e-05,
"loss": 0.7844,
"step": 630
},
{
"epoch": 0.15,
"learning_rate": 4.932425446987228e-05,
"loss": 0.7865,
"step": 640
},
{
"epoch": 0.15,
"learning_rate": 4.930307187261757e-05,
"loss": 0.7751,
"step": 650
},
{
"epoch": 0.15,
"learning_rate": 4.928156706451035e-05,
"loss": 0.7705,
"step": 660
},
{
"epoch": 0.16,
"learning_rate": 4.925974033066202e-05,
"loss": 0.773,
"step": 670
},
{
"epoch": 0.16,
"learning_rate": 4.923759196045208e-05,
"loss": 0.7714,
"step": 680
},
{
"epoch": 0.16,
"learning_rate": 4.921512224752426e-05,
"loss": 0.7788,
"step": 690
},
{
"epoch": 0.16,
"learning_rate": 4.9192331489782705e-05,
"loss": 0.7755,
"step": 700
},
{
"epoch": 0.16,
"learning_rate": 4.9169219989387956e-05,
"loss": 0.7682,
"step": 710
},
{
"epoch": 0.17,
"learning_rate": 4.9145788052752975e-05,
"loss": 0.788,
"step": 720
},
{
"epoch": 0.17,
"learning_rate": 4.912203599053907e-05,
"loss": 0.7752,
"step": 730
},
{
"epoch": 0.17,
"learning_rate": 4.90979641176518e-05,
"loss": 0.7786,
"step": 740
},
{
"epoch": 0.17,
"learning_rate": 4.907357275323677e-05,
"loss": 0.7848,
"step": 750
},
{
"epoch": 0.18,
"learning_rate": 4.904886222067542e-05,
"loss": 0.7747,
"step": 760
},
{
"epoch": 0.18,
"learning_rate": 4.9023832847580724e-05,
"loss": 0.7784,
"step": 770
},
{
"epoch": 0.18,
"learning_rate": 4.899848496579287e-05,
"loss": 0.768,
"step": 780
},
{
"epoch": 0.18,
"learning_rate": 4.897281891137481e-05,
"loss": 0.7684,
"step": 790
},
{
"epoch": 0.19,
"learning_rate": 4.8946835024607885e-05,
"loss": 0.7696,
"step": 800
},
{
"epoch": 0.19,
"learning_rate": 4.892053364998722e-05,
"loss": 0.7552,
"step": 810
},
{
"epoch": 0.19,
"learning_rate": 4.889391513621725e-05,
"loss": 0.7584,
"step": 820
},
{
"epoch": 0.19,
"learning_rate": 4.886697983620699e-05,
"loss": 0.7682,
"step": 830
},
{
"epoch": 0.19,
"learning_rate": 4.883972810706548e-05,
"loss": 0.7701,
"step": 840
},
{
"epoch": 0.2,
"learning_rate": 4.881216031009696e-05,
"loss": 0.7637,
"step": 850
},
{
"epoch": 0.2,
"learning_rate": 4.878427681079608e-05,
"loss": 0.7673,
"step": 860
},
{
"epoch": 0.2,
"learning_rate": 4.875607797884312e-05,
"loss": 0.7579,
"step": 870
},
{
"epoch": 0.2,
"learning_rate": 4.8727564188099054e-05,
"loss": 0.7629,
"step": 880
},
{
"epoch": 0.21,
"learning_rate": 4.8698735816600535e-05,
"loss": 0.7766,
"step": 890
},
{
"epoch": 0.21,
"learning_rate": 4.866959324655501e-05,
"loss": 0.7604,
"step": 900
},
{
"epoch": 0.21,
"learning_rate": 4.864013686433552e-05,
"loss": 0.7515,
"step": 910
},
{
"epoch": 0.21,
"learning_rate": 4.861036706047566e-05,
"loss": 0.7508,
"step": 920
},
{
"epoch": 0.22,
"learning_rate": 4.858028422966439e-05,
"loss": 0.7559,
"step": 930
},
{
"epoch": 0.22,
"learning_rate": 4.854988877074076e-05,
"loss": 0.7684,
"step": 940
},
{
"epoch": 0.22,
"learning_rate": 4.8519181086688695e-05,
"loss": 0.7514,
"step": 950
},
{
"epoch": 0.22,
"learning_rate": 4.8488161584631574e-05,
"loss": 0.7543,
"step": 960
},
{
"epoch": 0.22,
"learning_rate": 4.845683067582689e-05,
"loss": 0.7651,
"step": 970
},
{
"epoch": 0.23,
"learning_rate": 4.842518877566076e-05,
"loss": 0.7634,
"step": 980
},
{
"epoch": 0.23,
"learning_rate": 4.839323630364243e-05,
"loss": 0.7477,
"step": 990
},
{
"epoch": 0.23,
"learning_rate": 4.836097368339875e-05,
"loss": 0.7559,
"step": 1000
},
{
"epoch": 0.23,
"learning_rate": 4.832840134266849e-05,
"loss": 0.7729,
"step": 1010
},
{
"epoch": 0.24,
"learning_rate": 4.829551971329672e-05,
"loss": 0.7518,
"step": 1020
},
{
"epoch": 0.24,
"learning_rate": 4.826232923122907e-05,
"loss": 0.7551,
"step": 1030
},
{
"epoch": 0.24,
"learning_rate": 4.8228830336505926e-05,
"loss": 0.7613,
"step": 1040
},
{
"epoch": 0.24,
"learning_rate": 4.819502347325665e-05,
"loss": 0.7529,
"step": 1050
},
{
"epoch": 0.25,
"learning_rate": 4.816090908969363e-05,
"loss": 0.7476,
"step": 1060
},
{
"epoch": 0.25,
"learning_rate": 4.81264876381064e-05,
"loss": 0.765,
"step": 1070
},
{
"epoch": 0.25,
"learning_rate": 4.809175957485558e-05,
"loss": 0.7417,
"step": 1080
},
{
"epoch": 0.25,
"learning_rate": 4.805672536036686e-05,
"loss": 0.7398,
"step": 1090
},
{
"epoch": 0.25,
"learning_rate": 4.8021385459124925e-05,
"loss": 0.7489,
"step": 1100
},
{
"epoch": 0.26,
"learning_rate": 4.798574033966723e-05,
"loss": 0.7546,
"step": 1110
},
{
"epoch": 0.26,
"learning_rate": 4.794979047457783e-05,
"loss": 0.738,
"step": 1120
},
{
"epoch": 0.26,
"learning_rate": 4.79135363404811e-05,
"loss": 0.7495,
"step": 1130
},
{
"epoch": 0.26,
"learning_rate": 4.7876978418035455e-05,
"loss": 0.7622,
"step": 1140
},
{
"epoch": 0.27,
"learning_rate": 4.7840117191926915e-05,
"loss": 0.7465,
"step": 1150
},
{
"epoch": 0.27,
"learning_rate": 4.780295315086271e-05,
"loss": 0.7446,
"step": 1160
},
{
"epoch": 0.27,
"learning_rate": 4.7765486787564814e-05,
"loss": 0.7425,
"step": 1170
},
{
"epoch": 0.27,
"learning_rate": 4.772771859876338e-05,
"loss": 0.7583,
"step": 1180
},
{
"epoch": 0.28,
"learning_rate": 4.768964908519019e-05,
"loss": 0.7579,
"step": 1190
},
{
"epoch": 0.28,
"learning_rate": 4.7651278751571984e-05,
"loss": 0.7509,
"step": 1200
},
{
"epoch": 0.28,
"learning_rate": 4.76126081066238e-05,
"loss": 0.7358,
"step": 1210
},
{
"epoch": 0.28,
"learning_rate": 4.7573637663042195e-05,
"loss": 0.7409,
"step": 1220
},
{
"epoch": 0.29,
"learning_rate": 4.753436793749848e-05,
"loss": 0.7289,
"step": 1230
},
{
"epoch": 0.29,
"learning_rate": 4.749479945063186e-05,
"loss": 0.7488,
"step": 1240
},
{
"epoch": 0.29,
"learning_rate": 4.745493272704249e-05,
"loss": 0.7514,
"step": 1250
},
{
"epoch": 0.29,
"learning_rate": 4.7414768295284594e-05,
"loss": 0.7384,
"step": 1260
},
{
"epoch": 0.29,
"learning_rate": 4.7374306687859405e-05,
"loss": 0.739,
"step": 1270
},
{
"epoch": 0.3,
"learning_rate": 4.7333548441208134e-05,
"loss": 0.7494,
"step": 1280
},
{
"epoch": 0.3,
"learning_rate": 4.729249409570481e-05,
"loss": 0.7503,
"step": 1290
},
{
"epoch": 0.3,
"learning_rate": 4.725114419564919e-05,
"loss": 0.7388,
"step": 1300
},
{
"epoch": 0.3,
"learning_rate": 4.720949928925948e-05,
"loss": 0.7601,
"step": 1310
},
{
"epoch": 0.31,
"learning_rate": 4.716755992866509e-05,
"loss": 0.7416,
"step": 1320
},
{
"epoch": 0.31,
"learning_rate": 4.712532666989931e-05,
"loss": 0.7365,
"step": 1330
},
{
"epoch": 0.31,
"learning_rate": 4.708280007289195e-05,
"loss": 0.7455,
"step": 1340
},
{
"epoch": 0.31,
"learning_rate": 4.703998070146191e-05,
"loss": 0.7342,
"step": 1350
},
{
"epoch": 0.32,
"learning_rate": 4.699686912330969e-05,
"loss": 0.7374,
"step": 1360
},
{
"epoch": 0.32,
"learning_rate": 4.695346591000986e-05,
"loss": 0.7312,
"step": 1370
},
{
"epoch": 0.32,
"learning_rate": 4.6909771637003556e-05,
"loss": 0.7446,
"step": 1380
},
{
"epoch": 0.32,
"learning_rate": 4.686578688359072e-05,
"loss": 0.7387,
"step": 1390
},
{
"epoch": 0.32,
"learning_rate": 4.6821512232922546e-05,
"loss": 0.73,
"step": 1400
},
{
"epoch": 0.33,
"learning_rate": 4.677694827199367e-05,
"loss": 0.7357,
"step": 1410
},
{
"epoch": 0.33,
"learning_rate": 4.673209559163442e-05,
"loss": 0.7441,
"step": 1420
},
{
"epoch": 0.33,
"learning_rate": 4.668695478650296e-05,
"loss": 0.7359,
"step": 1430
},
{
"epoch": 0.33,
"learning_rate": 4.664152645507744e-05,
"loss": 0.7467,
"step": 1440
},
{
"epoch": 0.34,
"learning_rate": 4.659581119964803e-05,
"loss": 0.7221,
"step": 1450
},
{
"epoch": 0.34,
"learning_rate": 4.654980962630896e-05,
"loss": 0.7334,
"step": 1460
},
{
"epoch": 0.34,
"learning_rate": 4.6503522344950454e-05,
"loss": 0.7405,
"step": 1470
},
{
"epoch": 0.34,
"learning_rate": 4.6456949969250674e-05,
"loss": 0.7424,
"step": 1480
},
{
"epoch": 0.35,
"learning_rate": 4.6410093116667566e-05,
"loss": 0.7378,
"step": 1490
},
{
"epoch": 0.35,
"learning_rate": 4.636295240843068e-05,
"loss": 0.7479,
"step": 1500
},
{
"epoch": 0.35,
"learning_rate": 4.6315528469532945e-05,
"loss": 0.7479,
"step": 1510
},
{
"epoch": 0.35,
"learning_rate": 4.6267821928722345e-05,
"loss": 0.7337,
"step": 1520
},
{
"epoch": 0.35,
"learning_rate": 4.621983341849362e-05,
"loss": 0.7403,
"step": 1530
},
{
"epoch": 0.36,
"learning_rate": 4.6171563575079876e-05,
"loss": 0.7353,
"step": 1540
},
{
"epoch": 0.36,
"learning_rate": 4.612301303844415e-05,
"loss": 0.7237,
"step": 1550
},
{
"epoch": 0.36,
"learning_rate": 4.607418245227089e-05,
"loss": 0.739,
"step": 1560
},
{
"epoch": 0.36,
"learning_rate": 4.602507246395747e-05,
"loss": 0.7292,
"step": 1570
},
{
"epoch": 0.37,
"learning_rate": 4.5975683724605584e-05,
"loss": 0.745,
"step": 1580
},
{
"epoch": 0.37,
"learning_rate": 4.5926016889012616e-05,
"loss": 0.7276,
"step": 1590
},
{
"epoch": 0.37,
"learning_rate": 4.587607261566294e-05,
"loss": 0.7481,
"step": 1600
},
{
"epoch": 0.37,
"learning_rate": 4.582585156671925e-05,
"loss": 0.7362,
"step": 1610
},
{
"epoch": 0.38,
"learning_rate": 4.577535440801368e-05,
"loss": 0.734,
"step": 1620
},
{
"epoch": 0.38,
"learning_rate": 4.572458180903909e-05,
"loss": 0.7428,
"step": 1630
},
{
"epoch": 0.38,
"learning_rate": 4.5673534442940113e-05,
"loss": 0.732,
"step": 1640
},
{
"epoch": 0.38,
"learning_rate": 4.5622212986504245e-05,
"loss": 0.7191,
"step": 1650
},
{
"epoch": 0.38,
"learning_rate": 4.557061812015289e-05,
"loss": 0.727,
"step": 1660
},
{
"epoch": 0.39,
"learning_rate": 4.551875052793232e-05,
"loss": 0.728,
"step": 1670
},
{
"epoch": 0.39,
"learning_rate": 4.546661089750462e-05,
"loss": 0.7366,
"step": 1680
},
{
"epoch": 0.39,
"learning_rate": 4.541419992013859e-05,
"loss": 0.7274,
"step": 1690
},
{
"epoch": 0.39,
"learning_rate": 4.536151829070052e-05,
"loss": 0.7185,
"step": 1700
},
{
"epoch": 0.4,
"learning_rate": 4.530856670764502e-05,
"loss": 0.7463,
"step": 1710
},
{
"epoch": 0.4,
"learning_rate": 4.525534587300575e-05,
"loss": 0.734,
"step": 1720
},
{
"epoch": 0.4,
"learning_rate": 4.520185649238615e-05,
"loss": 0.7325,
"step": 1730
},
{
"epoch": 0.4,
"learning_rate": 4.5148099274950005e-05,
"loss": 0.7429,
"step": 1740
},
{
"epoch": 0.41,
"learning_rate": 4.509407493341212e-05,
"loss": 0.7333,
"step": 1750
},
{
"epoch": 0.41,
"learning_rate": 4.503978418402883e-05,
"loss": 0.7227,
"step": 1760
},
{
"epoch": 0.41,
"learning_rate": 4.49852277465885e-05,
"loss": 0.7139,
"step": 1770
},
{
"epoch": 0.41,
"learning_rate": 4.4930406344402006e-05,
"loss": 0.7387,
"step": 1780
},
{
"epoch": 0.41,
"learning_rate": 4.487532070429315e-05,
"loss": 0.7276,
"step": 1790
},
{
"epoch": 0.42,
"learning_rate": 4.481997155658898e-05,
"loss": 0.7251,
"step": 1800
},
{
"epoch": 0.42,
"learning_rate": 4.476435963511015e-05,
"loss": 0.7287,
"step": 1810
},
{
"epoch": 0.42,
"learning_rate": 4.470848567716119e-05,
"loss": 0.7169,
"step": 1820
},
{
"epoch": 0.42,
"learning_rate": 4.4652350423520685e-05,
"loss": 0.725,
"step": 1830
},
{
"epoch": 0.43,
"learning_rate": 4.45959546184315e-05,
"loss": 0.7089,
"step": 1840
},
{
"epoch": 0.43,
"learning_rate": 4.4539299009590926e-05,
"loss": 0.722,
"step": 1850
},
{
"epoch": 0.43,
"learning_rate": 4.4482384348140695e-05,
"loss": 0.7197,
"step": 1860
},
{
"epoch": 0.43,
"learning_rate": 4.44252113886571e-05,
"loss": 0.7135,
"step": 1870
},
{
"epoch": 0.44,
"learning_rate": 4.4367780889140945e-05,
"loss": 0.7168,
"step": 1880
},
{
"epoch": 0.44,
"learning_rate": 4.431009361100748e-05,
"loss": 0.7267,
"step": 1890
},
{
"epoch": 0.44,
"learning_rate": 4.4252150319076416e-05,
"loss": 0.7241,
"step": 1900
},
{
"epoch": 0.44,
"learning_rate": 4.419395178156159e-05,
"loss": 0.7294,
"step": 1910
},
{
"epoch": 0.45,
"learning_rate": 4.413549877006099e-05,
"loss": 0.7392,
"step": 1920
},
{
"epoch": 0.45,
"learning_rate": 4.4076792059546365e-05,
"loss": 0.7058,
"step": 1930
},
{
"epoch": 0.45,
"learning_rate": 4.401783242835306e-05,
"loss": 0.721,
"step": 1940
},
{
"epoch": 0.45,
"learning_rate": 4.395862065816959e-05,
"loss": 0.7284,
"step": 1950
},
{
"epoch": 0.45,
"learning_rate": 4.3899157534027396e-05,
"loss": 0.7259,
"step": 1960
},
{
"epoch": 0.46,
"learning_rate": 4.383944384429035e-05,
"loss": 0.7378,
"step": 1970
},
{
"epoch": 0.46,
"learning_rate": 4.3779480380644337e-05,
"loss": 0.7118,
"step": 1980
},
{
"epoch": 0.46,
"learning_rate": 4.3719267938086736e-05,
"loss": 0.7318,
"step": 1990
},
{
"epoch": 0.46,
"learning_rate": 4.3658807314915915e-05,
"loss": 0.7335,
"step": 2000
},
{
"epoch": 0.47,
"learning_rate": 4.359809931272062e-05,
"loss": 0.7162,
"step": 2010
},
{
"epoch": 0.47,
"learning_rate": 4.353714473636937e-05,
"loss": 0.7279,
"step": 2020
},
{
"epoch": 0.47,
"learning_rate": 4.3475944393999736e-05,
"loss": 0.7344,
"step": 2030
},
{
"epoch": 0.47,
"learning_rate": 4.34144990970077e-05,
"loss": 0.7258,
"step": 2040
},
{
"epoch": 0.48,
"learning_rate": 4.335280966003684e-05,
"loss": 0.7202,
"step": 2050
},
{
"epoch": 0.48,
"learning_rate": 4.329087690096755e-05,
"loss": 0.7225,
"step": 2060
},
{
"epoch": 0.48,
"learning_rate": 4.3228701640906197e-05,
"loss": 0.7073,
"step": 2070
},
{
"epoch": 0.48,
"learning_rate": 4.3166284704174244e-05,
"loss": 0.7265,
"step": 2080
},
{
"epoch": 0.48,
"learning_rate": 4.310362691829729e-05,
"loss": 0.7229,
"step": 2090
},
{
"epoch": 0.49,
"learning_rate": 4.304072911399415e-05,
"loss": 0.6985,
"step": 2100
},
{
"epoch": 0.49,
"learning_rate": 4.297759212516577e-05,
"loss": 0.7316,
"step": 2110
},
{
"epoch": 0.49,
"learning_rate": 4.291421678888425e-05,
"loss": 0.7332,
"step": 2120
},
{
"epoch": 0.49,
"learning_rate": 4.285060394538167e-05,
"loss": 0.7162,
"step": 2130
},
{
"epoch": 0.5,
"learning_rate": 4.278675443803903e-05,
"loss": 0.7064,
"step": 2140
},
{
"epoch": 0.5,
"learning_rate": 4.2722669113375e-05,
"loss": 0.7234,
"step": 2150
},
{
"epoch": 0.5,
"learning_rate": 4.2658348821034724e-05,
"loss": 0.7086,
"step": 2160
},
{
"epoch": 0.5,
"learning_rate": 4.2593794413778545e-05,
"loss": 0.7277,
"step": 2170
},
{
"epoch": 0.51,
"learning_rate": 4.2529006747470745e-05,
"loss": 0.6973,
"step": 2180
},
{
"epoch": 0.51,
"learning_rate": 4.2463986681068124e-05,
"loss": 0.7221,
"step": 2190
},
{
"epoch": 0.51,
"learning_rate": 4.2398735076608675e-05,
"loss": 0.7184,
"step": 2200
},
{
"epoch": 0.51,
"learning_rate": 4.233325279920011e-05,
"loss": 0.7132,
"step": 2210
},
{
"epoch": 0.51,
"learning_rate": 4.226754071700841e-05,
"loss": 0.7208,
"step": 2220
},
{
"epoch": 0.52,
"learning_rate": 4.220159970124633e-05,
"loss": 0.7078,
"step": 2230
},
{
"epoch": 0.52,
"learning_rate": 4.2135430626161834e-05,
"loss": 0.7196,
"step": 2240
},
{
"epoch": 0.52,
"learning_rate": 4.206903436902649e-05,
"loss": 0.7239,
"step": 2250
},
{
"epoch": 0.52,
"learning_rate": 4.200241181012385e-05,
"loss": 0.7172,
"step": 2260
},
{
"epoch": 0.53,
"learning_rate": 4.19355638327378e-05,
"loss": 0.7256,
"step": 2270
},
{
"epoch": 0.53,
"learning_rate": 4.1868491323140816e-05,
"loss": 0.7117,
"step": 2280
},
{
"epoch": 0.53,
"learning_rate": 4.180119517058222e-05,
"loss": 0.7199,
"step": 2290
},
{
"epoch": 0.53,
"learning_rate": 4.173367626727643e-05,
"loss": 0.7023,
"step": 2300
},
{
"epoch": 0.54,
"learning_rate": 4.166593550839108e-05,
"loss": 0.7185,
"step": 2310
},
{
"epoch": 0.54,
"learning_rate": 4.159797379203516e-05,
"loss": 0.7167,
"step": 2320
},
{
"epoch": 0.54,
"learning_rate": 4.152979201924715e-05,
"loss": 0.7194,
"step": 2330
},
{
"epoch": 0.54,
"learning_rate": 4.146139109398303e-05,
"loss": 0.717,
"step": 2340
},
{
"epoch": 0.54,
"learning_rate": 4.139277192310429e-05,
"loss": 0.724,
"step": 2350
},
{
"epoch": 0.55,
"learning_rate": 4.1323935416365965e-05,
"loss": 0.6933,
"step": 2360
},
{
"epoch": 0.55,
"learning_rate": 4.125488248640451e-05,
"loss": 0.7074,
"step": 2370
},
{
"epoch": 0.55,
"learning_rate": 4.118561404872574e-05,
"loss": 0.7028,
"step": 2380
},
{
"epoch": 0.55,
"learning_rate": 4.111613102169265e-05,
"loss": 0.7182,
"step": 2390
},
{
"epoch": 0.56,
"learning_rate": 4.1046434326513305e-05,
"loss": 0.7224,
"step": 2400
},
{
"epoch": 0.56,
"learning_rate": 4.097652488722856e-05,
"loss": 0.7065,
"step": 2410
},
{
"epoch": 0.56,
"learning_rate": 4.090640363069986e-05,
"loss": 0.7074,
"step": 2420
},
{
"epoch": 0.56,
"learning_rate": 4.08360714865969e-05,
"loss": 0.7246,
"step": 2430
},
{
"epoch": 0.57,
"learning_rate": 4.076552938738537e-05,
"loss": 0.7071,
"step": 2440
},
{
"epoch": 0.57,
"learning_rate": 4.069477826831451e-05,
"loss": 0.7082,
"step": 2450
},
{
"epoch": 0.57,
"learning_rate": 4.062381906740477e-05,
"loss": 0.7042,
"step": 2460
},
{
"epoch": 0.57,
"learning_rate": 4.055265272543536e-05,
"loss": 0.7011,
"step": 2470
},
{
"epoch": 0.57,
"learning_rate": 4.048128018593177e-05,
"loss": 0.7155,
"step": 2480
},
{
"epoch": 0.58,
"learning_rate": 4.040970239515325e-05,
"loss": 0.7149,
"step": 2490
},
{
"epoch": 0.58,
"learning_rate": 4.033792030208029e-05,
"loss": 0.717,
"step": 2500
},
{
"epoch": 0.58,
"learning_rate": 4.026593485840203e-05,
"loss": 0.7237,
"step": 2510
},
{
"epoch": 0.58,
"learning_rate": 4.019374701850362e-05,
"loss": 0.7251,
"step": 2520
},
{
"epoch": 0.59,
"learning_rate": 4.0121357739453604e-05,
"loss": 0.7179,
"step": 2530
},
{
"epoch": 0.59,
"learning_rate": 4.0048767980991206e-05,
"loss": 0.7171,
"step": 2540
},
{
"epoch": 0.59,
"learning_rate": 3.997597870551361e-05,
"loss": 0.7124,
"step": 2550
},
{
"epoch": 0.59,
"learning_rate": 3.990299087806319e-05,
"loss": 0.7206,
"step": 2560
},
{
"epoch": 0.6,
"learning_rate": 3.9829805466314775e-05,
"loss": 0.72,
"step": 2570
},
{
"epoch": 0.6,
"learning_rate": 3.975642344056271e-05,
"loss": 0.6972,
"step": 2580
},
{
"epoch": 0.6,
"learning_rate": 3.9682845773708085e-05,
"loss": 0.7158,
"step": 2590
},
{
"epoch": 0.6,
"learning_rate": 3.960907344124581e-05,
"loss": 0.7083,
"step": 2600
},
{
"epoch": 0.61,
"learning_rate": 3.9535107421251676e-05,
"loss": 0.7069,
"step": 2610
},
{
"epoch": 0.61,
"learning_rate": 3.946094869436938e-05,
"loss": 0.7018,
"step": 2620
},
{
"epoch": 0.61,
"learning_rate": 3.938659824379754e-05,
"loss": 0.6973,
"step": 2630
},
{
"epoch": 0.61,
"learning_rate": 3.931205705527664e-05,
"loss": 0.7064,
"step": 2640
},
{
"epoch": 0.61,
"learning_rate": 3.9237326117075995e-05,
"loss": 0.702,
"step": 2650
},
{
"epoch": 0.62,
"learning_rate": 3.9162406419980605e-05,
"loss": 0.713,
"step": 2660
},
{
"epoch": 0.62,
"learning_rate": 3.908729895727806e-05,
"loss": 0.7054,
"step": 2670
},
{
"epoch": 0.62,
"learning_rate": 3.9012004724745347e-05,
"loss": 0.7056,
"step": 2680
},
{
"epoch": 0.62,
"learning_rate": 3.893652472063562e-05,
"loss": 0.7047,
"step": 2690
},
{
"epoch": 0.63,
"learning_rate": 3.886085994566506e-05,
"loss": 0.705,
"step": 2700
},
{
"epoch": 0.63,
"learning_rate": 3.87850114029995e-05,
"loss": 0.6996,
"step": 2710
},
{
"epoch": 0.63,
"learning_rate": 3.870898009824118e-05,
"loss": 0.6986,
"step": 2720
},
{
"epoch": 0.63,
"learning_rate": 3.863276703941542e-05,
"loss": 0.7054,
"step": 2730
},
{
"epoch": 0.64,
"learning_rate": 3.855637323695721e-05,
"loss": 0.7094,
"step": 2740
},
{
"epoch": 0.64,
"learning_rate": 3.8479799703697884e-05,
"loss": 0.7103,
"step": 2750
},
{
"epoch": 0.64,
"learning_rate": 3.840304745485162e-05,
"loss": 0.6921,
"step": 2760
},
{
"epoch": 0.64,
"learning_rate": 3.8326117508002025e-05,
"loss": 0.7177,
"step": 2770
},
{
"epoch": 0.64,
"learning_rate": 3.8249010883088646e-05,
"loss": 0.7163,
"step": 2780
},
{
"epoch": 0.65,
"learning_rate": 3.817172860239339e-05,
"loss": 0.7135,
"step": 2790
},
{
"epoch": 0.65,
"learning_rate": 3.8094271690527076e-05,
"loss": 0.7141,
"step": 2800
},
{
"epoch": 0.65,
"learning_rate": 3.801664117441572e-05,
"loss": 0.704,
"step": 2810
},
{
"epoch": 0.65,
"learning_rate": 3.7938838083287056e-05,
"loss": 0.7092,
"step": 2820
},
{
"epoch": 0.66,
"learning_rate": 3.7860863448656765e-05,
"loss": 0.6986,
"step": 2830
},
{
"epoch": 0.66,
"learning_rate": 3.778271830431488e-05,
"loss": 0.7153,
"step": 2840
},
{
"epoch": 0.66,
"learning_rate": 3.770440368631207e-05,
"loss": 0.7048,
"step": 2850
},
{
"epoch": 0.66,
"learning_rate": 3.762592063294588e-05,
"loss": 0.7103,
"step": 2860
},
{
"epoch": 0.67,
"learning_rate": 3.7547270184746976e-05,
"loss": 0.7048,
"step": 2870
},
{
"epoch": 0.67,
"learning_rate": 3.746845338446533e-05,
"loss": 0.7083,
"step": 2880
},
{
"epoch": 0.67,
"learning_rate": 3.738947127705644e-05,
"loss": 0.7011,
"step": 2890
},
{
"epoch": 0.67,
"learning_rate": 3.731032490966746e-05,
"loss": 0.6959,
"step": 2900
},
{
"epoch": 0.67,
"learning_rate": 3.723101533162329e-05,
"loss": 0.7043,
"step": 2910
},
{
"epoch": 0.68,
"learning_rate": 3.715154359441265e-05,
"loss": 0.7101,
"step": 2920
},
{
"epoch": 0.68,
"learning_rate": 3.7071910751674256e-05,
"loss": 0.7071,
"step": 2930
},
{
"epoch": 0.68,
"learning_rate": 3.6992117859182674e-05,
"loss": 0.7158,
"step": 2940
},
{
"epoch": 0.68,
"learning_rate": 3.691216597483447e-05,
"loss": 0.7046,
"step": 2950
},
{
"epoch": 0.69,
"learning_rate": 3.683205615863412e-05,
"loss": 0.7003,
"step": 2960
},
{
"epoch": 0.69,
"learning_rate": 3.6751789472679946e-05,
"loss": 0.7067,
"step": 2970
},
{
"epoch": 0.69,
"learning_rate": 3.667136698115008e-05,
"loss": 0.7002,
"step": 2980
},
{
"epoch": 0.69,
"learning_rate": 3.65907897502883e-05,
"loss": 0.707,
"step": 2990
},
{
"epoch": 0.7,
"learning_rate": 3.651005884838995e-05,
"loss": 0.7069,
"step": 3000
},
{
"epoch": 0.7,
"learning_rate": 3.6429175345787735e-05,
"loss": 0.7023,
"step": 3010
},
{
"epoch": 0.7,
"learning_rate": 3.6348140314837553e-05,
"loss": 0.6921,
"step": 3020
},
{
"epoch": 0.7,
"learning_rate": 3.626695482990425e-05,
"loss": 0.6896,
"step": 3030
},
{
"epoch": 0.7,
"learning_rate": 3.618561996734743e-05,
"loss": 0.7025,
"step": 3040
},
{
"epoch": 0.71,
"learning_rate": 3.610413680550711e-05,
"loss": 0.7057,
"step": 3050
},
{
"epoch": 0.71,
"learning_rate": 3.6022506424689485e-05,
"loss": 0.6988,
"step": 3060
},
{
"epoch": 0.71,
"learning_rate": 3.594072990715258e-05,
"loss": 0.722,
"step": 3070
},
{
"epoch": 0.71,
"learning_rate": 3.5858808337091925e-05,
"loss": 0.7108,
"step": 3080
},
{
"epoch": 0.72,
"learning_rate": 3.577674280062612e-05,
"loss": 0.7075,
"step": 3090
},
{
"epoch": 0.72,
"learning_rate": 3.569453438578251e-05,
"loss": 0.7048,
"step": 3100
},
{
"epoch": 0.72,
"learning_rate": 3.561218418248271e-05,
"loss": 0.6934,
"step": 3110
},
{
"epoch": 0.72,
"learning_rate": 3.552969328252817e-05,
"loss": 0.7007,
"step": 3120
},
{
"epoch": 0.73,
"learning_rate": 3.544706277958572e-05,
"loss": 0.7221,
"step": 3130
},
{
"epoch": 0.73,
"learning_rate": 3.5364293769173e-05,
"loss": 0.7069,
"step": 3140
},
{
"epoch": 0.73,
"learning_rate": 3.528138734864406e-05,
"loss": 0.7013,
"step": 3150
},
{
"epoch": 0.73,
"learning_rate": 3.5198344617174685e-05,
"loss": 0.7161,
"step": 3160
},
{
"epoch": 0.73,
"learning_rate": 3.511516667574788e-05,
"loss": 0.6995,
"step": 3170
},
{
"epoch": 0.74,
"learning_rate": 3.5031854627139284e-05,
"loss": 0.7157,
"step": 3180
},
{
"epoch": 0.74,
"learning_rate": 3.4948409575902516e-05,
"loss": 0.6929,
"step": 3190
},
{
"epoch": 0.74,
"learning_rate": 3.486483262835457e-05,
"loss": 0.6973,
"step": 3200
},
{
"epoch": 0.74,
"learning_rate": 3.478112489256111e-05,
"loss": 0.6941,
"step": 3210
},
{
"epoch": 0.75,
"learning_rate": 3.4697287478321784e-05,
"loss": 0.7059,
"step": 3220
},
{
"epoch": 0.75,
"learning_rate": 3.4613321497155546e-05,
"loss": 0.6833,
"step": 3230
},
{
"epoch": 0.75,
"learning_rate": 3.452922806228587e-05,
"loss": 0.6766,
"step": 3240
},
{
"epoch": 0.75,
"learning_rate": 3.444500828862604e-05,
"loss": 0.7001,
"step": 3250
},
{
"epoch": 0.76,
"learning_rate": 3.436066329276432e-05,
"loss": 0.7082,
"step": 3260
},
{
"epoch": 0.76,
"learning_rate": 3.4276194192949185e-05,
"loss": 0.7035,
"step": 3270
},
{
"epoch": 0.76,
"learning_rate": 3.4191602109074484e-05,
"loss": 0.6948,
"step": 3280
},
{
"epoch": 0.76,
"learning_rate": 3.4106888162664584e-05,
"loss": 0.7041,
"step": 3290
},
{
"epoch": 0.76,
"learning_rate": 3.402205347685953e-05,
"loss": 0.7004,
"step": 3300
},
{
"epoch": 0.77,
"learning_rate": 3.39370991764001e-05,
"loss": 0.7003,
"step": 3310
},
{
"epoch": 0.77,
"learning_rate": 3.385202638761297e-05,
"loss": 0.6908,
"step": 3320
},
{
"epoch": 0.77,
"learning_rate": 3.376683623839569e-05,
"loss": 0.7059,
"step": 3330
},
{
"epoch": 0.77,
"learning_rate": 3.3681529858201814e-05,
"loss": 0.7027,
"step": 3340
},
{
"epoch": 0.78,
"learning_rate": 3.3596108378025875e-05,
"loss": 0.6984,
"step": 3350
},
{
"epoch": 0.78,
"learning_rate": 3.351057293038841e-05,
"loss": 0.7054,
"step": 3360
},
{
"epoch": 0.78,
"learning_rate": 3.342492464932094e-05,
"loss": 0.6803,
"step": 3370
},
{
"epoch": 0.78,
"learning_rate": 3.333916467035092e-05,
"loss": 0.6924,
"step": 3380
},
{
"epoch": 0.79,
"learning_rate": 3.325329413048673e-05,
"loss": 0.7143,
"step": 3390
},
{
"epoch": 0.79,
"learning_rate": 3.316731416820254e-05,
"loss": 0.6986,
"step": 3400
},
{
"epoch": 0.79,
"learning_rate": 3.308122592342326e-05,
"loss": 0.6875,
"step": 3410
},
{
"epoch": 0.79,
"learning_rate": 3.2995030537509396e-05,
"loss": 0.6934,
"step": 3420
},
{
"epoch": 0.8,
"learning_rate": 3.290872915324197e-05,
"loss": 0.698,
"step": 3430
},
{
"epoch": 0.8,
"learning_rate": 3.2822322914807305e-05,
"loss": 0.6976,
"step": 3440
},
{
"epoch": 0.8,
"learning_rate": 3.273581296778188e-05,
"loss": 0.6914,
"step": 3450
},
{
"epoch": 0.8,
"learning_rate": 3.264920045911716e-05,
"loss": 0.6902,
"step": 3460
},
{
"epoch": 0.8,
"learning_rate": 3.256248653712437e-05,
"loss": 0.6993,
"step": 3470
},
{
"epoch": 0.81,
"learning_rate": 3.247567235145929e-05,
"loss": 0.679,
"step": 3480
},
{
"epoch": 0.81,
"learning_rate": 3.2388759053106965e-05,
"loss": 0.6851,
"step": 3490
},
{
"epoch": 0.81,
"learning_rate": 3.230174779436651e-05,
"loss": 0.6802,
"step": 3500
},
{
"epoch": 0.81,
"learning_rate": 3.22146397288358e-05,
"loss": 0.7058,
"step": 3510
},
{
"epoch": 0.82,
"learning_rate": 3.2127436011396156e-05,
"loss": 0.6926,
"step": 3520
},
{
"epoch": 0.82,
"learning_rate": 3.2040137798197066e-05,
"loss": 0.7031,
"step": 3530
},
{
"epoch": 0.82,
"learning_rate": 3.195274624664086e-05,
"loss": 0.7132,
"step": 3540
},
{
"epoch": 0.82,
"learning_rate": 3.186526251536733e-05,
"loss": 0.6929,
"step": 3550
},
{
"epoch": 0.83,
"learning_rate": 3.177768776423839e-05,
"loss": 0.6959,
"step": 3560
},
{
"epoch": 0.83,
"learning_rate": 3.1690023154322714e-05,
"loss": 0.7035,
"step": 3570
},
{
"epoch": 0.83,
"learning_rate": 3.1602269847880315e-05,
"loss": 0.6965,
"step": 3580
},
{
"epoch": 0.83,
"learning_rate": 3.1514429008347154e-05,
"loss": 0.679,
"step": 3590
},
{
"epoch": 0.83,
"learning_rate": 3.14265018003197e-05,
"loss": 0.6861,
"step": 3600
},
{
"epoch": 0.84,
"learning_rate": 3.13384893895395e-05,
"loss": 0.6964,
"step": 3610
},
{
"epoch": 0.84,
"learning_rate": 3.125039294287773e-05,
"loss": 0.7003,
"step": 3620
},
{
"epoch": 0.84,
"learning_rate": 3.11622136283197e-05,
"loss": 0.6845,
"step": 3630
},
{
"epoch": 0.84,
"learning_rate": 3.1073952614949406e-05,
"loss": 0.6926,
"step": 3640
},
{
"epoch": 0.85,
"learning_rate": 3.0985611072934e-05,
"loss": 0.6953,
"step": 3650
},
{
"epoch": 0.85,
"learning_rate": 3.089719017350828e-05,
"loss": 0.6821,
"step": 3660
},
{
"epoch": 0.85,
"learning_rate": 3.080869108895915e-05,
"loss": 0.6903,
"step": 3670
},
{
"epoch": 0.85,
"learning_rate": 3.072011499261016e-05,
"loss": 0.7159,
"step": 3680
},
{
"epoch": 0.86,
"learning_rate": 3.0631463058805796e-05,
"loss": 0.6961,
"step": 3690
},
{
"epoch": 0.86,
"learning_rate": 3.0542736462896065e-05,
"loss": 0.7061,
"step": 3700
},
{
"epoch": 0.86,
"learning_rate": 3.045393638122082e-05,
"loss": 0.7089,
"step": 3710
},
{
"epoch": 0.86,
"learning_rate": 3.03650639910942e-05,
"loss": 0.672,
"step": 3720
},
{
"epoch": 0.86,
"learning_rate": 3.0276120470789004e-05,
"loss": 0.7006,
"step": 3730
},
{
"epoch": 0.87,
"learning_rate": 3.0187106999521074e-05,
"loss": 0.6945,
"step": 3740
},
{
"epoch": 0.87,
"learning_rate": 3.0098024757433675e-05,
"loss": 0.6957,
"step": 3750
},
{
"epoch": 0.87,
"learning_rate": 3.000887492558183e-05,
"loss": 0.6819,
"step": 3760
},
{
"epoch": 0.87,
"learning_rate": 2.991965868591668e-05,
"loss": 0.6861,
"step": 3770
},
{
"epoch": 0.88,
"learning_rate": 2.983037722126978e-05,
"loss": 0.7015,
"step": 3780
},
{
"epoch": 0.88,
"learning_rate": 2.9741031715337464e-05,
"loss": 0.6852,
"step": 3790
},
{
"epoch": 0.88,
"learning_rate": 2.9651623352665114e-05,
"loss": 0.7009,
"step": 3800
},
{
"epoch": 0.88,
"learning_rate": 2.9562153318631468e-05,
"loss": 0.6885,
"step": 3810
},
{
"epoch": 0.89,
"learning_rate": 2.947262279943292e-05,
"loss": 0.6701,
"step": 3820
},
{
"epoch": 0.89,
"learning_rate": 2.9383032982067753e-05,
"loss": 0.6847,
"step": 3830
},
{
"epoch": 0.89,
"learning_rate": 2.929338505432045e-05,
"loss": 0.6903,
"step": 3840
},
{
"epoch": 0.89,
"learning_rate": 2.9203680204745914e-05,
"loss": 0.6992,
"step": 3850
},
{
"epoch": 0.89,
"learning_rate": 2.9113919622653707e-05,
"loss": 0.7075,
"step": 3860
},
{
"epoch": 0.9,
"learning_rate": 2.902410449809232e-05,
"loss": 0.7072,
"step": 3870
},
{
"epoch": 0.9,
"learning_rate": 2.8934236021833348e-05,
"loss": 0.6897,
"step": 3880
},
{
"epoch": 0.9,
"learning_rate": 2.8844315385355737e-05,
"loss": 0.7081,
"step": 3890
},
{
"epoch": 0.9,
"learning_rate": 2.8754343780829968e-05,
"loss": 0.7032,
"step": 3900
},
{
"epoch": 0.91,
"learning_rate": 2.866432240110226e-05,
"loss": 0.6811,
"step": 3910
},
{
"epoch": 0.91,
"learning_rate": 2.857425243967875e-05,
"loss": 0.6911,
"step": 3920
},
{
"epoch": 0.91,
"learning_rate": 2.8484135090709686e-05,
"loss": 0.6862,
"step": 3930
},
{
"epoch": 0.91,
"learning_rate": 2.839397154897356e-05,
"loss": 0.6785,
"step": 3940
},
{
"epoch": 0.92,
"learning_rate": 2.83037630098613e-05,
"loss": 0.7007,
"step": 3950
},
{
"epoch": 0.92,
"learning_rate": 2.821351066936043e-05,
"loss": 0.675,
"step": 3960
},
{
"epoch": 0.92,
"learning_rate": 2.812321572403915e-05,
"loss": 0.6969,
"step": 3970
},
{
"epoch": 0.92,
"learning_rate": 2.803287937103055e-05,
"loss": 0.694,
"step": 3980
},
{
"epoch": 0.92,
"learning_rate": 2.7942502808016703e-05,
"loss": 0.6951,
"step": 3990
},
{
"epoch": 0.93,
"learning_rate": 2.7852087233212763e-05,
"loss": 0.679,
"step": 4000
},
{
"epoch": 0.93,
"learning_rate": 2.7761633845351142e-05,
"loss": 0.7046,
"step": 4010
},
{
"epoch": 0.93,
"learning_rate": 2.767114384366555e-05,
"loss": 0.6803,
"step": 4020
},
{
"epoch": 0.93,
"learning_rate": 2.758061842787511e-05,
"loss": 0.6927,
"step": 4030
},
{
"epoch": 0.94,
"learning_rate": 2.7490058798168523e-05,
"loss": 0.7024,
"step": 4040
},
{
"epoch": 0.94,
"learning_rate": 2.7399466155188035e-05,
"loss": 0.6839,
"step": 4050
},
{
"epoch": 0.94,
"learning_rate": 2.7308841700013622e-05,
"loss": 0.6846,
"step": 4060
},
{
"epoch": 0.94,
"learning_rate": 2.721818663414702e-05,
"loss": 0.6835,
"step": 4070
},
{
"epoch": 0.95,
"learning_rate": 2.7127502159495782e-05,
"loss": 0.6879,
"step": 4080
},
{
"epoch": 0.95,
"learning_rate": 2.703678947835741e-05,
"loss": 0.6936,
"step": 4090
},
{
"epoch": 0.95,
"learning_rate": 2.694604979340331e-05,
"loss": 0.7074,
"step": 4100
},
{
"epoch": 0.95,
"learning_rate": 2.6855284307662952e-05,
"loss": 0.7018,
"step": 4110
},
{
"epoch": 0.96,
"learning_rate": 2.6764494224507846e-05,
"loss": 0.6998,
"step": 4120
},
{
"epoch": 0.96,
"learning_rate": 2.6673680747635637e-05,
"loss": 0.6834,
"step": 4130
},
{
"epoch": 0.96,
"learning_rate": 2.6582845081054096e-05,
"loss": 0.6906,
"step": 4140
},
{
"epoch": 0.96,
"learning_rate": 2.6491988429065224e-05,
"loss": 0.6902,
"step": 4150
},
{
"epoch": 0.96,
"learning_rate": 2.64011119962492e-05,
"loss": 0.6787,
"step": 4160
},
{
"epoch": 0.97,
"learning_rate": 2.6310216987448504e-05,
"loss": 0.696,
"step": 4170
},
{
"epoch": 0.97,
"learning_rate": 2.6219304607751865e-05,
"loss": 0.6971,
"step": 4180
},
{
"epoch": 0.97,
"learning_rate": 2.612837606247834e-05,
"loss": 0.7099,
"step": 4190
},
{
"epoch": 0.97,
"learning_rate": 2.6037432557161285e-05,
"loss": 0.6855,
"step": 4200
},
{
"epoch": 0.98,
"learning_rate": 2.5946475297532413e-05,
"loss": 0.679,
"step": 4210
},
{
"epoch": 0.98,
"learning_rate": 2.585550548950579e-05,
"loss": 0.6911,
"step": 4220
},
{
"epoch": 0.98,
"learning_rate": 2.5764524339161837e-05,
"loss": 0.6831,
"step": 4230
},
{
"epoch": 0.98,
"learning_rate": 2.567353305273138e-05,
"loss": 0.6788,
"step": 4240
},
{
"epoch": 0.99,
"learning_rate": 2.5582532836579587e-05,
"loss": 0.6832,
"step": 4250
},
{
"epoch": 0.99,
"learning_rate": 2.5491524897190068e-05,
"loss": 0.6939,
"step": 4260
},
{
"epoch": 0.99,
"learning_rate": 2.540051044114877e-05,
"loss": 0.6848,
"step": 4270
},
{
"epoch": 0.99,
"learning_rate": 2.53094906751281e-05,
"loss": 0.6914,
"step": 4280
},
{
"epoch": 0.99,
"learning_rate": 2.521846680587081e-05,
"loss": 0.6926,
"step": 4290
},
{
"epoch": 1.0,
"learning_rate": 2.5127440040174087e-05,
"loss": 0.686,
"step": 4300
},
{
"epoch": 1.0,
"learning_rate": 2.503641158487351e-05,
"loss": 0.6789,
"step": 4310
},
{
"epoch": 1.0,
"learning_rate": 2.4945382646827058e-05,
"loss": 0.6505,
"step": 4320
},
{
"epoch": 1.0,
"learning_rate": 2.48543544328991e-05,
"loss": 0.6762,
"step": 4330
},
{
"epoch": 1.01,
"learning_rate": 2.476332814994441e-05,
"loss": 0.6765,
"step": 4340
},
{
"epoch": 1.01,
"learning_rate": 2.4672305004792192e-05,
"loss": 0.6742,
"step": 4350
},
{
"epoch": 1.01,
"learning_rate": 2.458128620422999e-05,
"loss": 0.6881,
"step": 4360
},
{
"epoch": 1.01,
"learning_rate": 2.4490272954987796e-05,
"loss": 0.6686,
"step": 4370
},
{
"epoch": 1.02,
"learning_rate": 2.4399266463721993e-05,
"loss": 0.6996,
"step": 4380
},
{
"epoch": 1.02,
"learning_rate": 2.430826793699934e-05,
"loss": 0.6819,
"step": 4390
},
{
"epoch": 1.02,
"learning_rate": 2.4217278581281035e-05,
"loss": 0.685,
"step": 4400
},
{
"epoch": 1.02,
"learning_rate": 2.4126299602906665e-05,
"loss": 0.685,
"step": 4410
},
{
"epoch": 1.02,
"learning_rate": 2.4035332208078252e-05,
"loss": 0.7007,
"step": 4420
},
{
"epoch": 1.03,
"learning_rate": 2.3944377602844226e-05,
"loss": 0.6671,
"step": 4430
},
{
"epoch": 1.03,
"learning_rate": 2.3853436993083453e-05,
"loss": 0.6851,
"step": 4440
},
{
"epoch": 1.03,
"learning_rate": 2.3762511584489256e-05,
"loss": 0.6677,
"step": 4450
},
{
"epoch": 1.03,
"learning_rate": 2.3671602582553436e-05,
"loss": 0.6871,
"step": 4460
},
{
"epoch": 1.04,
"learning_rate": 2.3580711192550216e-05,
"loss": 0.6797,
"step": 4470
},
{
"epoch": 1.04,
"learning_rate": 2.348983861952039e-05,
"loss": 0.6835,
"step": 4480
},
{
"epoch": 1.04,
"learning_rate": 2.3398986068255235e-05,
"loss": 0.6762,
"step": 4490
},
{
"epoch": 1.04,
"learning_rate": 2.3308154743280595e-05,
"loss": 0.6751,
"step": 4500
},
{
"epoch": 1.05,
"learning_rate": 2.3217345848840873e-05,
"loss": 0.6891,
"step": 4510
},
{
"epoch": 1.05,
"learning_rate": 2.3126560588883113e-05,
"loss": 0.6641,
"step": 4520
},
{
"epoch": 1.05,
"learning_rate": 2.3035800167041007e-05,
"loss": 0.6741,
"step": 4530
},
{
"epoch": 1.05,
"learning_rate": 2.2945065786618925e-05,
"loss": 0.6742,
"step": 4540
},
{
"epoch": 1.05,
"learning_rate": 2.2854358650575996e-05,
"loss": 0.6875,
"step": 4550
},
{
"epoch": 1.06,
"learning_rate": 2.2763679961510137e-05,
"loss": 0.6836,
"step": 4560
},
{
"epoch": 1.06,
"learning_rate": 2.267303092164213e-05,
"loss": 0.6688,
"step": 4570
},
{
"epoch": 1.06,
"learning_rate": 2.2582412732799626e-05,
"loss": 0.6831,
"step": 4580
},
{
"epoch": 1.06,
"learning_rate": 2.2491826596401297e-05,
"loss": 0.682,
"step": 4590
},
{
"epoch": 1.07,
"learning_rate": 2.2401273713440837e-05,
"loss": 0.6814,
"step": 4600
},
{
"epoch": 1.07,
"learning_rate": 2.231075528447108e-05,
"loss": 0.6753,
"step": 4610
},
{
"epoch": 1.07,
"learning_rate": 2.222027250958805e-05,
"loss": 0.6776,
"step": 4620
},
{
"epoch": 1.07,
"learning_rate": 2.212982658841508e-05,
"loss": 0.6726,
"step": 4630
},
{
"epoch": 1.08,
"learning_rate": 2.2039418720086887e-05,
"loss": 0.6769,
"step": 4640
},
{
"epoch": 1.08,
"learning_rate": 2.1949050103233715e-05,
"loss": 0.6828,
"step": 4650
},
{
"epoch": 1.08,
"learning_rate": 2.185872193596535e-05,
"loss": 0.6581,
"step": 4660
},
{
"epoch": 1.08,
"learning_rate": 2.176843541585535e-05,
"loss": 0.6853,
"step": 4670
},
{
"epoch": 1.08,
"learning_rate": 2.1678191739925107e-05,
"loss": 0.6925,
"step": 4680
},
{
"epoch": 1.09,
"learning_rate": 2.158799210462793e-05,
"loss": 0.6778,
"step": 4690
},
{
"epoch": 1.09,
"learning_rate": 2.149783770583331e-05,
"loss": 0.6912,
"step": 4700
},
{
"epoch": 1.09,
"learning_rate": 2.140772973881095e-05,
"loss": 0.6981,
"step": 4710
},
{
"epoch": 1.09,
"learning_rate": 2.1317669398214972e-05,
"loss": 0.6911,
"step": 4720
},
{
"epoch": 1.1,
"learning_rate": 2.122765787806805e-05,
"loss": 0.6765,
"step": 4730
},
{
"epoch": 1.1,
"learning_rate": 2.1137696371745608e-05,
"loss": 0.6822,
"step": 4740
},
{
"epoch": 1.1,
"learning_rate": 2.1047786071959983e-05,
"loss": 0.6796,
"step": 4750
},
{
"epoch": 1.1,
"learning_rate": 2.095792817074463e-05,
"loss": 0.6671,
"step": 4760
},
{
"epoch": 1.11,
"learning_rate": 2.0868123859438257e-05,
"loss": 0.6893,
"step": 4770
},
{
"epoch": 1.11,
"learning_rate": 2.0778374328669126e-05,
"loss": 0.6746,
"step": 4780
},
{
"epoch": 1.11,
"learning_rate": 2.0688680768339185e-05,
"loss": 0.6851,
"step": 4790
},
{
"epoch": 1.11,
"learning_rate": 2.059904436760835e-05,
"loss": 0.6854,
"step": 4800
},
{
"epoch": 1.11,
"learning_rate": 2.0509466314878682e-05,
"loss": 0.6623,
"step": 4810
},
{
"epoch": 1.12,
"learning_rate": 2.041994779777868e-05,
"loss": 0.6776,
"step": 4820
},
{
"epoch": 1.12,
"learning_rate": 2.0330490003147528e-05,
"loss": 0.6803,
"step": 4830
},
{
"epoch": 1.12,
"learning_rate": 2.0241094117019328e-05,
"loss": 0.6808,
"step": 4840
},
{
"epoch": 1.12,
"learning_rate": 2.0151761324607405e-05,
"loss": 0.6666,
"step": 4850
},
{
"epoch": 1.13,
"learning_rate": 2.006249281028859e-05,
"loss": 0.6707,
"step": 4860
},
{
"epoch": 1.13,
"learning_rate": 1.997328975758753e-05,
"loss": 0.6726,
"step": 4870
},
{
"epoch": 1.13,
"learning_rate": 1.9884153349160926e-05,
"loss": 0.672,
"step": 4880
},
{
"epoch": 1.13,
"learning_rate": 1.9795084766781975e-05,
"loss": 0.7034,
"step": 4890
},
{
"epoch": 1.14,
"learning_rate": 1.970608519132458e-05,
"loss": 0.6758,
"step": 4900
},
{
"epoch": 1.14,
"learning_rate": 1.9617155802747787e-05,
"loss": 0.6741,
"step": 4910
},
{
"epoch": 1.14,
"learning_rate": 1.9528297780080067e-05,
"loss": 0.6684,
"step": 4920
},
{
"epoch": 1.14,
"learning_rate": 1.9439512301403747e-05,
"loss": 0.6743,
"step": 4930
},
{
"epoch": 1.15,
"learning_rate": 1.9350800543839355e-05,
"loss": 0.6759,
"step": 4940
},
{
"epoch": 1.15,
"learning_rate": 1.926216368353002e-05,
"loss": 0.6745,
"step": 4950
},
{
"epoch": 1.15,
"learning_rate": 1.917360289562588e-05,
"loss": 0.6712,
"step": 4960
},
{
"epoch": 1.15,
"learning_rate": 1.90851193542685e-05,
"loss": 0.6762,
"step": 4970
},
{
"epoch": 1.15,
"learning_rate": 1.899671423257534e-05,
"loss": 0.6862,
"step": 4980
},
{
"epoch": 1.16,
"learning_rate": 1.8908388702624107e-05,
"loss": 0.6784,
"step": 4990
},
{
"epoch": 1.16,
"learning_rate": 1.8820143935437333e-05,
"loss": 0.684,
"step": 5000
}
],
"max_steps": 8628,
"num_train_epochs": 2,
"total_flos": 1.5789628983890412e+18,
"trial_name": null,
"trial_params": null
}