CareLlama2-7b-chat-sft-multi / trainer_state.json
wangrongsheng's picture
commit from root
a97d6fd
raw
history blame contribute delete
No virus
105 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 8628,
"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
},
{
"epoch": 1.16,
"learning_rate": 1.8731981100966772e-05,
"loss": 0.6814,
"step": 5010
},
{
"epoch": 1.16,
"learning_rate": 1.8643901368077922e-05,
"loss": 0.6986,
"step": 5020
},
{
"epoch": 1.17,
"learning_rate": 1.8555905904534504e-05,
"loss": 0.6711,
"step": 5030
},
{
"epoch": 1.17,
"learning_rate": 1.8467995876983002e-05,
"loss": 0.6643,
"step": 5040
},
{
"epoch": 1.17,
"learning_rate": 1.8380172450937187e-05,
"loss": 0.6649,
"step": 5050
},
{
"epoch": 1.17,
"learning_rate": 1.829243679076267e-05,
"loss": 0.6708,
"step": 5060
},
{
"epoch": 1.18,
"learning_rate": 1.820479005966144e-05,
"loss": 0.6906,
"step": 5070
},
{
"epoch": 1.18,
"learning_rate": 1.811723341965648e-05,
"loss": 0.6809,
"step": 5080
},
{
"epoch": 1.18,
"learning_rate": 1.8029768031576345e-05,
"loss": 0.6758,
"step": 5090
},
{
"epoch": 1.18,
"learning_rate": 1.7942395055039756e-05,
"loss": 0.6791,
"step": 5100
},
{
"epoch": 1.18,
"learning_rate": 1.785511564844024e-05,
"loss": 0.6701,
"step": 5110
},
{
"epoch": 1.19,
"learning_rate": 1.7767930968930785e-05,
"loss": 0.6943,
"step": 5120
},
{
"epoch": 1.19,
"learning_rate": 1.7680842172408468e-05,
"loss": 0.6736,
"step": 5130
},
{
"epoch": 1.19,
"learning_rate": 1.7593850413499158e-05,
"loss": 0.6834,
"step": 5140
},
{
"epoch": 1.19,
"learning_rate": 1.7506956845542183e-05,
"loss": 0.6653,
"step": 5150
},
{
"epoch": 1.2,
"learning_rate": 1.742016262057507e-05,
"loss": 0.6753,
"step": 5160
},
{
"epoch": 1.2,
"learning_rate": 1.733346888931825e-05,
"loss": 0.6826,
"step": 5170
},
{
"epoch": 1.2,
"learning_rate": 1.7246876801159784e-05,
"loss": 0.669,
"step": 5180
},
{
"epoch": 1.2,
"learning_rate": 1.716038750414017e-05,
"loss": 0.6629,
"step": 5190
},
{
"epoch": 1.21,
"learning_rate": 1.707400214493709e-05,
"loss": 0.6745,
"step": 5200
},
{
"epoch": 1.21,
"learning_rate": 1.6987721868850226e-05,
"loss": 0.6929,
"step": 5210
},
{
"epoch": 1.21,
"learning_rate": 1.690154781978604e-05,
"loss": 0.6713,
"step": 5220
},
{
"epoch": 1.21,
"learning_rate": 1.6815481140242655e-05,
"loss": 0.6552,
"step": 5230
},
{
"epoch": 1.21,
"learning_rate": 1.6729522971294676e-05,
"loss": 0.6662,
"step": 5240
},
{
"epoch": 1.22,
"learning_rate": 1.6643674452578073e-05,
"loss": 0.6787,
"step": 5250
},
{
"epoch": 1.22,
"learning_rate": 1.655793672227507e-05,
"loss": 0.6944,
"step": 5260
},
{
"epoch": 1.22,
"learning_rate": 1.6472310917099054e-05,
"loss": 0.6883,
"step": 5270
},
{
"epoch": 1.22,
"learning_rate": 1.638679817227951e-05,
"loss": 0.6855,
"step": 5280
},
{
"epoch": 1.23,
"learning_rate": 1.630139962154696e-05,
"loss": 0.6632,
"step": 5290
},
{
"epoch": 1.23,
"learning_rate": 1.6216116397117932e-05,
"loss": 0.6614,
"step": 5300
},
{
"epoch": 1.23,
"learning_rate": 1.6130949629679976e-05,
"loss": 0.6846,
"step": 5310
},
{
"epoch": 1.23,
"learning_rate": 1.604590044837663e-05,
"loss": 0.68,
"step": 5320
},
{
"epoch": 1.24,
"learning_rate": 1.5960969980792484e-05,
"loss": 0.6709,
"step": 5330
},
{
"epoch": 1.24,
"learning_rate": 1.5876159352938202e-05,
"loss": 0.6579,
"step": 5340
},
{
"epoch": 1.24,
"learning_rate": 1.5791469689235627e-05,
"loss": 0.682,
"step": 5350
},
{
"epoch": 1.24,
"learning_rate": 1.5706902112502858e-05,
"loss": 0.685,
"step": 5360
},
{
"epoch": 1.24,
"learning_rate": 1.5622457743939335e-05,
"loss": 0.6543,
"step": 5370
},
{
"epoch": 1.25,
"learning_rate": 1.5538137703111025e-05,
"loss": 0.6682,
"step": 5380
},
{
"epoch": 1.25,
"learning_rate": 1.5453943107935544e-05,
"loss": 0.6666,
"step": 5390
},
{
"epoch": 1.25,
"learning_rate": 1.5369875074667365e-05,
"loss": 0.6859,
"step": 5400
},
{
"epoch": 1.25,
"learning_rate": 1.5285934717882956e-05,
"loss": 0.6862,
"step": 5410
},
{
"epoch": 1.26,
"learning_rate": 1.5202123150466093e-05,
"loss": 0.6727,
"step": 5420
},
{
"epoch": 1.26,
"learning_rate": 1.5118441483593035e-05,
"loss": 0.6706,
"step": 5430
},
{
"epoch": 1.26,
"learning_rate": 1.5034890826717824e-05,
"loss": 0.6816,
"step": 5440
},
{
"epoch": 1.26,
"learning_rate": 1.4951472287557549e-05,
"loss": 0.6839,
"step": 5450
},
{
"epoch": 1.27,
"learning_rate": 1.4868186972077708e-05,
"loss": 0.6652,
"step": 5460
},
{
"epoch": 1.27,
"learning_rate": 1.4785035984477496e-05,
"loss": 0.6692,
"step": 5470
},
{
"epoch": 1.27,
"learning_rate": 1.470202042717518e-05,
"loss": 0.6829,
"step": 5480
},
{
"epoch": 1.27,
"learning_rate": 1.4619141400793506e-05,
"loss": 0.674,
"step": 5490
},
{
"epoch": 1.27,
"learning_rate": 1.4536400004145081e-05,
"loss": 0.6921,
"step": 5500
},
{
"epoch": 1.28,
"learning_rate": 1.445379733421781e-05,
"loss": 0.6807,
"step": 5510
},
{
"epoch": 1.28,
"learning_rate": 1.4371334486160354e-05,
"loss": 0.6859,
"step": 5520
},
{
"epoch": 1.28,
"learning_rate": 1.4289012553267623e-05,
"loss": 0.6977,
"step": 5530
},
{
"epoch": 1.28,
"learning_rate": 1.4206832626966249e-05,
"loss": 0.6645,
"step": 5540
},
{
"epoch": 1.29,
"learning_rate": 1.4124795796800172e-05,
"loss": 0.6616,
"step": 5550
},
{
"epoch": 1.29,
"learning_rate": 1.4042903150416094e-05,
"loss": 0.6696,
"step": 5560
},
{
"epoch": 1.29,
"learning_rate": 1.3961155773549207e-05,
"loss": 0.6706,
"step": 5570
},
{
"epoch": 1.29,
"learning_rate": 1.3879554750008653e-05,
"loss": 0.6679,
"step": 5580
},
{
"epoch": 1.3,
"learning_rate": 1.3798101161663255e-05,
"loss": 0.6825,
"step": 5590
},
{
"epoch": 1.3,
"learning_rate": 1.3716796088427097e-05,
"loss": 0.6815,
"step": 5600
},
{
"epoch": 1.3,
"learning_rate": 1.363564060824528e-05,
"loss": 0.6701,
"step": 5610
},
{
"epoch": 1.3,
"learning_rate": 1.3554635797079579e-05,
"loss": 0.6691,
"step": 5620
},
{
"epoch": 1.31,
"learning_rate": 1.3473782728894205e-05,
"loss": 0.6871,
"step": 5630
},
{
"epoch": 1.31,
"learning_rate": 1.3393082475641544e-05,
"loss": 0.6655,
"step": 5640
},
{
"epoch": 1.31,
"learning_rate": 1.331253610724797e-05,
"loss": 0.665,
"step": 5650
},
{
"epoch": 1.31,
"learning_rate": 1.323214469159964e-05,
"loss": 0.6748,
"step": 5660
},
{
"epoch": 1.31,
"learning_rate": 1.315190929452832e-05,
"loss": 0.6999,
"step": 5670
},
{
"epoch": 1.32,
"learning_rate": 1.3071830979797331e-05,
"loss": 0.6815,
"step": 5680
},
{
"epoch": 1.32,
"learning_rate": 1.299191080908735e-05,
"loss": 0.6857,
"step": 5690
},
{
"epoch": 1.32,
"learning_rate": 1.2912149841982388e-05,
"loss": 0.6801,
"step": 5700
},
{
"epoch": 1.32,
"learning_rate": 1.2832549135955719e-05,
"loss": 0.6814,
"step": 5710
},
{
"epoch": 1.33,
"learning_rate": 1.2753109746355885e-05,
"loss": 0.6701,
"step": 5720
},
{
"epoch": 1.33,
"learning_rate": 1.2673832726392684e-05,
"loss": 0.6717,
"step": 5730
},
{
"epoch": 1.33,
"learning_rate": 1.2594719127123217e-05,
"loss": 0.6776,
"step": 5740
},
{
"epoch": 1.33,
"learning_rate": 1.2515769997437945e-05,
"loss": 0.6499,
"step": 5750
},
{
"epoch": 1.34,
"learning_rate": 1.2436986384046786e-05,
"loss": 0.6679,
"step": 5760
},
{
"epoch": 1.34,
"learning_rate": 1.2358369331465246e-05,
"loss": 0.6757,
"step": 5770
},
{
"epoch": 1.34,
"learning_rate": 1.2279919882000528e-05,
"loss": 0.6705,
"step": 5780
},
{
"epoch": 1.34,
"learning_rate": 1.2201639075737805e-05,
"loss": 0.6517,
"step": 5790
},
{
"epoch": 1.34,
"learning_rate": 1.2123527950526334e-05,
"loss": 0.6768,
"step": 5800
},
{
"epoch": 1.35,
"learning_rate": 1.2045587541965752e-05,
"loss": 0.6714,
"step": 5810
},
{
"epoch": 1.35,
"learning_rate": 1.1967818883392306e-05,
"loss": 0.6606,
"step": 5820
},
{
"epoch": 1.35,
"learning_rate": 1.1890223005865206e-05,
"loss": 0.6651,
"step": 5830
},
{
"epoch": 1.35,
"learning_rate": 1.1812800938152896e-05,
"loss": 0.6809,
"step": 5840
},
{
"epoch": 1.36,
"learning_rate": 1.1735553706719493e-05,
"loss": 0.6686,
"step": 5850
},
{
"epoch": 1.36,
"learning_rate": 1.1658482335711074e-05,
"loss": 0.6688,
"step": 5860
},
{
"epoch": 1.36,
"learning_rate": 1.158158784694218e-05,
"loss": 0.6957,
"step": 5870
},
{
"epoch": 1.36,
"learning_rate": 1.150487125988224e-05,
"loss": 0.668,
"step": 5880
},
{
"epoch": 1.37,
"learning_rate": 1.142833359164206e-05,
"loss": 0.6889,
"step": 5890
},
{
"epoch": 1.37,
"learning_rate": 1.1351975856960327e-05,
"loss": 0.6612,
"step": 5900
},
{
"epoch": 1.37,
"learning_rate": 1.1275799068190166e-05,
"loss": 0.671,
"step": 5910
},
{
"epoch": 1.37,
"learning_rate": 1.1199804235285727e-05,
"loss": 0.6816,
"step": 5920
},
{
"epoch": 1.37,
"learning_rate": 1.112399236578876e-05,
"loss": 0.6853,
"step": 5930
},
{
"epoch": 1.38,
"learning_rate": 1.1048364464815297e-05,
"loss": 0.6643,
"step": 5940
},
{
"epoch": 1.38,
"learning_rate": 1.0972921535042302e-05,
"loss": 0.6699,
"step": 5950
},
{
"epoch": 1.38,
"learning_rate": 1.0897664576694416e-05,
"loss": 0.677,
"step": 5960
},
{
"epoch": 1.38,
"learning_rate": 1.0822594587530613e-05,
"loss": 0.6809,
"step": 5970
},
{
"epoch": 1.39,
"learning_rate": 1.074771256283106e-05,
"loss": 0.6799,
"step": 5980
},
{
"epoch": 1.39,
"learning_rate": 1.0673019495383876e-05,
"loss": 0.6831,
"step": 5990
},
{
"epoch": 1.39,
"learning_rate": 1.0598516375471978e-05,
"loss": 0.6875,
"step": 6000
},
{
"epoch": 1.39,
"learning_rate": 1.0524204190859956e-05,
"loss": 0.6564,
"step": 6010
},
{
"epoch": 1.4,
"learning_rate": 1.0450083926780974e-05,
"loss": 0.6795,
"step": 6020
},
{
"epoch": 1.4,
"learning_rate": 1.03761565659237e-05,
"loss": 0.6605,
"step": 6030
},
{
"epoch": 1.4,
"learning_rate": 1.0302423088419307e-05,
"loss": 0.6727,
"step": 6040
},
{
"epoch": 1.4,
"learning_rate": 1.0228884471828418e-05,
"loss": 0.6617,
"step": 6050
},
{
"epoch": 1.4,
"learning_rate": 1.0155541691128212e-05,
"loss": 0.6738,
"step": 6060
},
{
"epoch": 1.41,
"learning_rate": 1.0082395718699488e-05,
"loss": 0.6748,
"step": 6070
},
{
"epoch": 1.41,
"learning_rate": 1.000944752431371e-05,
"loss": 0.664,
"step": 6080
},
{
"epoch": 1.41,
"learning_rate": 9.936698075120224e-06,
"loss": 0.6736,
"step": 6090
},
{
"epoch": 1.41,
"learning_rate": 9.864148335633398e-06,
"loss": 0.6761,
"step": 6100
},
{
"epoch": 1.42,
"learning_rate": 9.791799267719846e-06,
"loss": 0.6884,
"step": 6110
},
{
"epoch": 1.42,
"learning_rate": 9.719651830585668e-06,
"loss": 0.6577,
"step": 6120
},
{
"epoch": 1.42,
"learning_rate": 9.647706980763743e-06,
"loss": 0.6572,
"step": 6130
},
{
"epoch": 1.42,
"learning_rate": 9.575965672101034e-06,
"loss": 0.6726,
"step": 6140
},
{
"epoch": 1.43,
"learning_rate": 9.504428855745967e-06,
"loss": 0.6722,
"step": 6150
},
{
"epoch": 1.43,
"learning_rate": 9.433097480135769e-06,
"loss": 0.6708,
"step": 6160
},
{
"epoch": 1.43,
"learning_rate": 9.361972490983947e-06,
"loss": 0.6831,
"step": 6170
},
{
"epoch": 1.43,
"learning_rate": 9.291054831267749e-06,
"loss": 0.6604,
"step": 6180
},
{
"epoch": 1.43,
"learning_rate": 9.220345441215625e-06,
"loss": 0.6737,
"step": 6190
},
{
"epoch": 1.44,
"learning_rate": 9.149845258294762e-06,
"loss": 0.6685,
"step": 6200
},
{
"epoch": 1.44,
"learning_rate": 9.079555217198696e-06,
"loss": 0.6778,
"step": 6210
},
{
"epoch": 1.44,
"learning_rate": 9.009476249834894e-06,
"loss": 0.6738,
"step": 6220
},
{
"epoch": 1.44,
"learning_rate": 8.939609285312397e-06,
"loss": 0.6657,
"step": 6230
},
{
"epoch": 1.45,
"learning_rate": 8.869955249929509e-06,
"loss": 0.6767,
"step": 6240
},
{
"epoch": 1.45,
"learning_rate": 8.800515067161504e-06,
"loss": 0.694,
"step": 6250
},
{
"epoch": 1.45,
"learning_rate": 8.731289657648414e-06,
"loss": 0.6821,
"step": 6260
},
{
"epoch": 1.45,
"learning_rate": 8.662279939182764e-06,
"loss": 0.6992,
"step": 6270
},
{
"epoch": 1.46,
"learning_rate": 8.593486826697462e-06,
"loss": 0.6691,
"step": 6280
},
{
"epoch": 1.46,
"learning_rate": 8.524911232253666e-06,
"loss": 0.6841,
"step": 6290
},
{
"epoch": 1.46,
"learning_rate": 8.456554065028651e-06,
"loss": 0.6856,
"step": 6300
},
{
"epoch": 1.46,
"learning_rate": 8.388416231303769e-06,
"loss": 0.6777,
"step": 6310
},
{
"epoch": 1.46,
"learning_rate": 8.320498634452462e-06,
"loss": 0.6646,
"step": 6320
},
{
"epoch": 1.47,
"learning_rate": 8.252802174928254e-06,
"loss": 0.67,
"step": 6330
},
{
"epoch": 1.47,
"learning_rate": 8.185327750252824e-06,
"loss": 0.6651,
"step": 6340
},
{
"epoch": 1.47,
"learning_rate": 8.118076255004118e-06,
"loss": 0.675,
"step": 6350
},
{
"epoch": 1.47,
"learning_rate": 8.051048580804457e-06,
"loss": 0.6708,
"step": 6360
},
{
"epoch": 1.48,
"learning_rate": 7.984245616308764e-06,
"loss": 0.6802,
"step": 6370
},
{
"epoch": 1.48,
"learning_rate": 7.917668247192716e-06,
"loss": 0.6798,
"step": 6380
},
{
"epoch": 1.48,
"learning_rate": 7.851317356141061e-06,
"loss": 0.6618,
"step": 6390
},
{
"epoch": 1.48,
"learning_rate": 7.78519382283591e-06,
"loss": 0.6652,
"step": 6400
},
{
"epoch": 1.49,
"learning_rate": 7.719298523945042e-06,
"loss": 0.6615,
"step": 6410
},
{
"epoch": 1.49,
"learning_rate": 7.65363233311028e-06,
"loss": 0.6666,
"step": 6420
},
{
"epoch": 1.49,
"learning_rate": 7.588196120935953e-06,
"loss": 0.6679,
"step": 6430
},
{
"epoch": 1.49,
"learning_rate": 7.529500878831333e-06,
"loss": 0.6706,
"step": 6440
},
{
"epoch": 1.5,
"learning_rate": 7.464504013697235e-06,
"loss": 0.6689,
"step": 6450
},
{
"epoch": 1.5,
"learning_rate": 7.399739634692479e-06,
"loss": 0.6771,
"step": 6460
},
{
"epoch": 1.5,
"learning_rate": 7.335208600465129e-06,
"loss": 0.6771,
"step": 6470
},
{
"epoch": 1.5,
"learning_rate": 7.270911766569577e-06,
"loss": 0.6562,
"step": 6480
},
{
"epoch": 1.5,
"learning_rate": 7.206849985455147e-06,
"loss": 0.6683,
"step": 6490
},
{
"epoch": 1.51,
"learning_rate": 7.143024106454857e-06,
"loss": 0.6769,
"step": 6500
},
{
"epoch": 1.51,
"learning_rate": 7.0794349757741075e-06,
"loss": 0.6659,
"step": 6510
},
{
"epoch": 1.51,
"learning_rate": 7.016083436479512e-06,
"loss": 0.6681,
"step": 6520
},
{
"epoch": 1.51,
"learning_rate": 6.952970328487651e-06,
"loss": 0.6643,
"step": 6530
},
{
"epoch": 1.52,
"learning_rate": 6.890096488553999e-06,
"loss": 0.6683,
"step": 6540
},
{
"epoch": 1.52,
"learning_rate": 6.8274627502618035e-06,
"loss": 0.6622,
"step": 6550
},
{
"epoch": 1.52,
"learning_rate": 6.76506994401104e-06,
"loss": 0.665,
"step": 6560
},
{
"epoch": 1.52,
"learning_rate": 6.7029188970073955e-06,
"loss": 0.6804,
"step": 6570
},
{
"epoch": 1.53,
"learning_rate": 6.641010433251302e-06,
"loss": 0.6776,
"step": 6580
},
{
"epoch": 1.53,
"learning_rate": 6.579345373527035e-06,
"loss": 0.6642,
"step": 6590
},
{
"epoch": 1.53,
"learning_rate": 6.517924535391779e-06,
"loss": 0.6748,
"step": 6600
},
{
"epoch": 1.53,
"learning_rate": 6.4567487331648445e-06,
"loss": 0.6778,
"step": 6610
},
{
"epoch": 1.53,
"learning_rate": 6.39581877791684e-06,
"loss": 0.6628,
"step": 6620
},
{
"epoch": 1.54,
"learning_rate": 6.335135477458953e-06,
"loss": 0.6761,
"step": 6630
},
{
"epoch": 1.54,
"learning_rate": 6.274699636332171e-06,
"loss": 0.6643,
"step": 6640
},
{
"epoch": 1.54,
"learning_rate": 6.214512055796687e-06,
"loss": 0.6604,
"step": 6650
},
{
"epoch": 1.54,
"learning_rate": 6.154573533821242e-06,
"loss": 0.6693,
"step": 6660
},
{
"epoch": 1.55,
"learning_rate": 6.094884865072548e-06,
"loss": 0.6601,
"step": 6670
},
{
"epoch": 1.55,
"learning_rate": 6.035446840904757e-06,
"loss": 0.666,
"step": 6680
},
{
"epoch": 1.55,
"learning_rate": 5.9762602493489665e-06,
"loss": 0.6622,
"step": 6690
},
{
"epoch": 1.55,
"learning_rate": 5.917325875102781e-06,
"loss": 0.6758,
"step": 6700
},
{
"epoch": 1.56,
"learning_rate": 5.858644499519897e-06,
"loss": 0.6664,
"step": 6710
},
{
"epoch": 1.56,
"learning_rate": 5.800216900599728e-06,
"loss": 0.6665,
"step": 6720
},
{
"epoch": 1.56,
"learning_rate": 5.7420438529771275e-06,
"loss": 0.6592,
"step": 6730
},
{
"epoch": 1.56,
"learning_rate": 5.684126127912118e-06,
"loss": 0.677,
"step": 6740
},
{
"epoch": 1.56,
"learning_rate": 5.6264644932796065e-06,
"loss": 0.6699,
"step": 6750
},
{
"epoch": 1.57,
"learning_rate": 5.569059713559274e-06,
"loss": 0.6625,
"step": 6760
},
{
"epoch": 1.57,
"learning_rate": 5.511912549825402e-06,
"loss": 0.6681,
"step": 6770
},
{
"epoch": 1.57,
"learning_rate": 5.4550237597367964e-06,
"loss": 0.67,
"step": 6780
},
{
"epoch": 1.57,
"learning_rate": 5.398394097526735e-06,
"loss": 0.6722,
"step": 6790
},
{
"epoch": 1.58,
"learning_rate": 5.342024313992966e-06,
"loss": 0.656,
"step": 6800
},
{
"epoch": 1.58,
"learning_rate": 5.2859151564877665e-06,
"loss": 0.6701,
"step": 6810
},
{
"epoch": 1.58,
"learning_rate": 5.230067368908029e-06,
"loss": 0.6635,
"step": 6820
},
{
"epoch": 1.58,
"learning_rate": 5.174481691685371e-06,
"loss": 0.6827,
"step": 6830
},
{
"epoch": 1.59,
"learning_rate": 5.119158861776366e-06,
"loss": 0.6511,
"step": 6840
},
{
"epoch": 1.59,
"learning_rate": 5.0640996126527535e-06,
"loss": 0.6746,
"step": 6850
},
{
"epoch": 1.59,
"learning_rate": 5.009304674291704e-06,
"loss": 0.6779,
"step": 6860
},
{
"epoch": 1.59,
"learning_rate": 4.954774773166132e-06,
"loss": 0.6666,
"step": 6870
},
{
"epoch": 1.59,
"learning_rate": 4.900510632235103e-06,
"loss": 0.6721,
"step": 6880
},
{
"epoch": 1.6,
"learning_rate": 4.846512970934219e-06,
"loss": 0.6718,
"step": 6890
},
{
"epoch": 1.6,
"learning_rate": 4.7927825051660825e-06,
"loss": 0.6596,
"step": 6900
},
{
"epoch": 1.6,
"learning_rate": 4.739319947290815e-06,
"loss": 0.6685,
"step": 6910
},
{
"epoch": 1.6,
"learning_rate": 4.686126006116604e-06,
"loss": 0.6592,
"step": 6920
},
{
"epoch": 1.61,
"learning_rate": 4.633201386890315e-06,
"loss": 0.6689,
"step": 6930
},
{
"epoch": 1.61,
"learning_rate": 4.58054679128812e-06,
"loss": 0.6784,
"step": 6940
},
{
"epoch": 1.61,
"learning_rate": 4.528162917406218e-06,
"loss": 0.681,
"step": 6950
},
{
"epoch": 1.61,
"learning_rate": 4.476050459751585e-06,
"loss": 0.6717,
"step": 6960
},
{
"epoch": 1.62,
"learning_rate": 4.42421010923274e-06,
"loss": 0.6626,
"step": 6970
},
{
"epoch": 1.62,
"learning_rate": 4.372642553150588e-06,
"loss": 0.6732,
"step": 6980
},
{
"epoch": 1.62,
"learning_rate": 4.321348475189332e-06,
"loss": 0.6689,
"step": 6990
},
{
"epoch": 1.62,
"learning_rate": 4.270328555407388e-06,
"loss": 0.6646,
"step": 7000
},
{
"epoch": 1.62,
"learning_rate": 4.219583470228378e-06,
"loss": 0.6656,
"step": 7010
},
{
"epoch": 1.63,
"learning_rate": 4.169113892432156e-06,
"loss": 0.6829,
"step": 7020
},
{
"epoch": 1.63,
"learning_rate": 4.118920491145889e-06,
"loss": 0.673,
"step": 7030
},
{
"epoch": 1.63,
"learning_rate": 4.069003931835199e-06,
"loss": 0.6842,
"step": 7040
},
{
"epoch": 1.63,
"learning_rate": 4.019364876295304e-06,
"loss": 0.6566,
"step": 7050
},
{
"epoch": 1.64,
"learning_rate": 3.970003982642287e-06,
"loss": 0.66,
"step": 7060
},
{
"epoch": 1.64,
"learning_rate": 3.920921905304362e-06,
"loss": 0.6832,
"step": 7070
},
{
"epoch": 1.64,
"learning_rate": 3.872119295013174e-06,
"loss": 0.6727,
"step": 7080
},
{
"epoch": 1.64,
"learning_rate": 3.823596798795179e-06,
"loss": 0.6661,
"step": 7090
},
{
"epoch": 1.65,
"learning_rate": 3.7753550599630816e-06,
"loss": 0.6629,
"step": 7100
},
{
"epoch": 1.65,
"learning_rate": 3.7273947181072964e-06,
"loss": 0.6591,
"step": 7110
},
{
"epoch": 1.65,
"learning_rate": 3.679716409087472e-06,
"loss": 0.6584,
"step": 7120
},
{
"epoch": 1.65,
"learning_rate": 3.63232076502405e-06,
"loss": 0.6746,
"step": 7130
},
{
"epoch": 1.66,
"learning_rate": 3.585208414289895e-06,
"loss": 0.6554,
"step": 7140
},
{
"epoch": 1.66,
"learning_rate": 3.5383799815019576e-06,
"loss": 0.6673,
"step": 7150
},
{
"epoch": 1.66,
"learning_rate": 3.4918360875129978e-06,
"loss": 0.6706,
"step": 7160
},
{
"epoch": 1.66,
"learning_rate": 3.4455773494033562e-06,
"loss": 0.6883,
"step": 7170
},
{
"epoch": 1.66,
"learning_rate": 3.3996043804727624e-06,
"loss": 0.6492,
"step": 7180
},
{
"epoch": 1.67,
"learning_rate": 3.3539177902322113e-06,
"loss": 0.6421,
"step": 7190
},
{
"epoch": 1.67,
"learning_rate": 3.3085181843958757e-06,
"loss": 0.6688,
"step": 7200
},
{
"epoch": 1.67,
"learning_rate": 3.2634061648730867e-06,
"loss": 0.6544,
"step": 7210
},
{
"epoch": 1.67,
"learning_rate": 3.2185823297603503e-06,
"loss": 0.6695,
"step": 7220
},
{
"epoch": 1.68,
"learning_rate": 3.174047273333405e-06,
"loss": 0.6583,
"step": 7230
},
{
"epoch": 1.68,
"learning_rate": 3.129801586039366e-06,
"loss": 0.6548,
"step": 7240
},
{
"epoch": 1.68,
"learning_rate": 3.085845854488867e-06,
"loss": 0.6555,
"step": 7250
},
{
"epoch": 1.68,
"learning_rate": 3.0421806614483183e-06,
"loss": 0.6743,
"step": 7260
},
{
"epoch": 1.69,
"learning_rate": 2.998806585832148e-06,
"loss": 0.6759,
"step": 7270
},
{
"epoch": 1.69,
"learning_rate": 2.9557242026951454e-06,
"loss": 0.6727,
"step": 7280
},
{
"epoch": 1.69,
"learning_rate": 2.912934083224833e-06,
"loss": 0.6544,
"step": 7290
},
{
"epoch": 1.69,
"learning_rate": 2.870436794733897e-06,
"loss": 0.6669,
"step": 7300
},
{
"epoch": 1.69,
"learning_rate": 2.828232900652655e-06,
"loss": 0.6716,
"step": 7310
},
{
"epoch": 1.7,
"learning_rate": 2.786322960521587e-06,
"loss": 0.6696,
"step": 7320
},
{
"epoch": 1.7,
"learning_rate": 2.744707529983939e-06,
"loss": 0.6733,
"step": 7330
},
{
"epoch": 1.7,
"learning_rate": 2.7033871607783227e-06,
"loss": 0.6547,
"step": 7340
},
{
"epoch": 1.7,
"learning_rate": 2.662362400731444e-06,
"loss": 0.671,
"step": 7350
},
{
"epoch": 1.71,
"learning_rate": 2.6216337937507775e-06,
"loss": 0.6651,
"step": 7360
},
{
"epoch": 1.71,
"learning_rate": 2.5812018798174216e-06,
"loss": 0.68,
"step": 7370
},
{
"epoch": 1.71,
"learning_rate": 2.541067194978894e-06,
"loss": 0.6788,
"step": 7380
},
{
"epoch": 1.71,
"learning_rate": 2.5012302713420477e-06,
"loss": 0.6649,
"step": 7390
},
{
"epoch": 1.72,
"learning_rate": 2.461691637066002e-06,
"loss": 0.6593,
"step": 7400
},
{
"epoch": 1.72,
"learning_rate": 2.4224518163551506e-06,
"loss": 0.6576,
"step": 7410
},
{
"epoch": 1.72,
"learning_rate": 2.383511329452218e-06,
"loss": 0.6683,
"step": 7420
},
{
"epoch": 1.72,
"learning_rate": 2.344870692631329e-06,
"loss": 0.6647,
"step": 7430
},
{
"epoch": 1.72,
"learning_rate": 2.3065304181912053e-06,
"loss": 0.6783,
"step": 7440
},
{
"epoch": 1.73,
"learning_rate": 2.2684910144483457e-06,
"loss": 0.6592,
"step": 7450
},
{
"epoch": 1.73,
"learning_rate": 2.230752985730314e-06,
"loss": 0.6612,
"step": 7460
},
{
"epoch": 1.73,
"learning_rate": 2.1933168323690077e-06,
"loss": 0.6761,
"step": 7470
},
{
"epoch": 1.73,
"learning_rate": 2.156183050694072e-06,
"loss": 0.6496,
"step": 7480
},
{
"epoch": 1.74,
"learning_rate": 2.119352133026292e-06,
"loss": 0.6679,
"step": 7490
},
{
"epoch": 1.74,
"learning_rate": 2.0828245676710738e-06,
"loss": 0.6591,
"step": 7500
},
{
"epoch": 1.74,
"learning_rate": 2.046600838911969e-06,
"loss": 0.6578,
"step": 7510
},
{
"epoch": 1.74,
"learning_rate": 2.0106814270042573e-06,
"loss": 0.6775,
"step": 7520
},
{
"epoch": 1.75,
"learning_rate": 1.975066808168574e-06,
"loss": 0.6709,
"step": 7530
},
{
"epoch": 1.75,
"learning_rate": 1.9397574545845955e-06,
"loss": 0.6833,
"step": 7540
},
{
"epoch": 1.75,
"learning_rate": 1.9047538343847872e-06,
"loss": 0.6416,
"step": 7550
},
{
"epoch": 1.75,
"learning_rate": 1.8700564116481884e-06,
"loss": 0.6823,
"step": 7560
},
{
"epoch": 1.75,
"learning_rate": 1.8356656463942745e-06,
"loss": 0.6617,
"step": 7570
},
{
"epoch": 1.76,
"learning_rate": 1.8015819945768315e-06,
"loss": 0.6743,
"step": 7580
},
{
"epoch": 1.76,
"learning_rate": 1.7678059080779297e-06,
"loss": 0.6749,
"step": 7590
},
{
"epoch": 1.76,
"learning_rate": 1.734337834701938e-06,
"loss": 0.6441,
"step": 7600
},
{
"epoch": 1.76,
"learning_rate": 1.7011782181695719e-06,
"loss": 0.6731,
"step": 7610
},
{
"epoch": 1.77,
"learning_rate": 1.6683274981120156e-06,
"loss": 0.6706,
"step": 7620
},
{
"epoch": 1.77,
"learning_rate": 1.6357861100650963e-06,
"loss": 0.6587,
"step": 7630
},
{
"epoch": 1.77,
"learning_rate": 1.603554485463507e-06,
"loss": 0.6708,
"step": 7640
},
{
"epoch": 1.77,
"learning_rate": 1.571633051635099e-06,
"loss": 0.6694,
"step": 7650
},
{
"epoch": 1.78,
"learning_rate": 1.5400222317951796e-06,
"loss": 0.6672,
"step": 7660
},
{
"epoch": 1.78,
"learning_rate": 1.5087224450409499e-06,
"loss": 0.6642,
"step": 7670
},
{
"epoch": 1.78,
"learning_rate": 1.477734106345921e-06,
"loss": 0.661,
"step": 7680
},
{
"epoch": 1.78,
"learning_rate": 1.4470576265544046e-06,
"loss": 0.6739,
"step": 7690
},
{
"epoch": 1.78,
"learning_rate": 1.416693412376091e-06,
"loss": 0.6772,
"step": 7700
},
{
"epoch": 1.79,
"learning_rate": 1.3866418663806363e-06,
"loss": 0.6753,
"step": 7710
},
{
"epoch": 1.79,
"learning_rate": 1.3569033869923337e-06,
"loss": 0.6652,
"step": 7720
},
{
"epoch": 1.79,
"learning_rate": 1.3274783684848358e-06,
"loss": 0.6571,
"step": 7730
},
{
"epoch": 1.79,
"learning_rate": 1.2983672009759085e-06,
"loss": 0.6758,
"step": 7740
},
{
"epoch": 1.8,
"learning_rate": 1.2695702704222879e-06,
"loss": 0.6521,
"step": 7750
},
{
"epoch": 1.8,
"learning_rate": 1.2410879586145368e-06,
"loss": 0.6671,
"step": 7760
},
{
"epoch": 1.8,
"learning_rate": 1.2129206431719914e-06,
"loss": 0.6439,
"step": 7770
},
{
"epoch": 1.8,
"learning_rate": 1.1850686975377585e-06,
"loss": 0.6704,
"step": 7780
},
{
"epoch": 1.81,
"learning_rate": 1.1575324909737728e-06,
"loss": 0.6691,
"step": 7790
},
{
"epoch": 1.81,
"learning_rate": 1.1303123885558874e-06,
"loss": 0.6592,
"step": 7800
},
{
"epoch": 1.81,
"learning_rate": 1.1034087511690188e-06,
"loss": 0.6792,
"step": 7810
},
{
"epoch": 1.81,
"learning_rate": 1.0768219355024035e-06,
"loss": 0.6476,
"step": 7820
},
{
"epoch": 1.82,
"learning_rate": 1.0505522940448348e-06,
"loss": 0.6669,
"step": 7830
},
{
"epoch": 1.82,
"learning_rate": 1.0246001750800037e-06,
"loss": 0.6702,
"step": 7840
},
{
"epoch": 1.82,
"learning_rate": 9.989659226818771e-07,
"loss": 0.6782,
"step": 7850
},
{
"epoch": 1.82,
"learning_rate": 9.73649876710142e-07,
"loss": 0.6471,
"step": 7860
},
{
"epoch": 1.82,
"learning_rate": 9.486523728056945e-07,
"loss": 0.6706,
"step": 7870
},
{
"epoch": 1.83,
"learning_rate": 9.239737423861778e-07,
"loss": 0.6739,
"step": 7880
},
{
"epoch": 1.83,
"learning_rate": 8.99614312641614e-07,
"loss": 0.6649,
"step": 7890
},
{
"epoch": 1.83,
"learning_rate": 8.755744065300553e-07,
"loss": 0.6407,
"step": 7900
},
{
"epoch": 1.83,
"learning_rate": 8.51854342773295e-07,
"loss": 0.6688,
"step": 7910
},
{
"epoch": 1.84,
"learning_rate": 8.284544358526381e-07,
"loss": 0.6662,
"step": 7920
},
{
"epoch": 1.84,
"learning_rate": 8.053749960047568e-07,
"loss": 0.6668,
"step": 7930
},
{
"epoch": 1.84,
"learning_rate": 7.826163292175503e-07,
"loss": 0.6617,
"step": 7940
},
{
"epoch": 1.84,
"learning_rate": 7.601787372261026e-07,
"loss": 0.6778,
"step": 7950
},
{
"epoch": 1.85,
"learning_rate": 7.380625175086808e-07,
"loss": 0.6618,
"step": 7960
},
{
"epoch": 1.85,
"learning_rate": 7.162679632827823e-07,
"loss": 0.6585,
"step": 7970
},
{
"epoch": 1.85,
"learning_rate": 6.947953635012606e-07,
"loss": 0.6694,
"step": 7980
},
{
"epoch": 1.85,
"learning_rate": 6.73645002848483e-07,
"loss": 0.6875,
"step": 7990
},
{
"epoch": 1.85,
"learning_rate": 6.52817161736563e-07,
"loss": 0.6585,
"step": 8000
},
{
"epoch": 1.86,
"learning_rate": 6.323121163016393e-07,
"loss": 0.6702,
"step": 8010
},
{
"epoch": 1.86,
"learning_rate": 6.121301384002215e-07,
"loss": 0.6785,
"step": 8020
},
{
"epoch": 1.86,
"learning_rate": 5.922714956055703e-07,
"loss": 0.6723,
"step": 8030
},
{
"epoch": 1.86,
"learning_rate": 5.727364512041616e-07,
"loss": 0.6764,
"step": 8040
},
{
"epoch": 1.87,
"learning_rate": 5.535252641922062e-07,
"loss": 0.6761,
"step": 8050
},
{
"epoch": 1.87,
"learning_rate": 5.346381892721852e-07,
"loss": 0.6624,
"step": 8060
},
{
"epoch": 1.87,
"learning_rate": 5.16075476849509e-07,
"loss": 0.6639,
"step": 8070
},
{
"epoch": 1.87,
"learning_rate": 4.978373730291724e-07,
"loss": 0.6774,
"step": 8080
},
{
"epoch": 1.88,
"learning_rate": 4.799241196124987e-07,
"loss": 0.6611,
"step": 8090
},
{
"epoch": 1.88,
"learning_rate": 4.6233595409393705e-07,
"loss": 0.6818,
"step": 8100
},
{
"epoch": 1.88,
"learning_rate": 4.450731096579064e-07,
"loss": 0.6724,
"step": 8110
},
{
"epoch": 1.88,
"learning_rate": 4.281358151757203e-07,
"loss": 0.6727,
"step": 8120
},
{
"epoch": 1.88,
"learning_rate": 4.115242952025367e-07,
"loss": 0.666,
"step": 8130
},
{
"epoch": 1.89,
"learning_rate": 3.952387699743737e-07,
"loss": 0.6682,
"step": 8140
},
{
"epoch": 1.89,
"learning_rate": 3.7927945540521815e-07,
"loss": 0.6593,
"step": 8150
},
{
"epoch": 1.89,
"learning_rate": 3.6364656308413846e-07,
"loss": 0.6772,
"step": 8160
},
{
"epoch": 1.89,
"learning_rate": 3.4834030027248445e-07,
"loss": 0.6693,
"step": 8170
},
{
"epoch": 1.9,
"learning_rate": 3.3336086990114754e-07,
"loss": 0.6701,
"step": 8180
},
{
"epoch": 1.9,
"learning_rate": 3.1870847056786336e-07,
"loss": 0.663,
"step": 8190
},
{
"epoch": 1.9,
"learning_rate": 3.0438329653458e-07,
"loss": 0.6618,
"step": 8200
},
{
"epoch": 1.9,
"learning_rate": 2.903855377248854e-07,
"loss": 0.6635,
"step": 8210
},
{
"epoch": 1.91,
"learning_rate": 2.767153797214733e-07,
"loss": 0.6536,
"step": 8220
},
{
"epoch": 1.91,
"learning_rate": 2.633730037637172e-07,
"loss": 0.6658,
"step": 8230
},
{
"epoch": 1.91,
"learning_rate": 2.5035858674523074e-07,
"loss": 0.6681,
"step": 8240
},
{
"epoch": 1.91,
"learning_rate": 2.3767230121154727e-07,
"loss": 0.6749,
"step": 8250
},
{
"epoch": 1.91,
"learning_rate": 2.2531431535781634e-07,
"loss": 0.6709,
"step": 8260
},
{
"epoch": 1.92,
"learning_rate": 2.13284793026583e-07,
"loss": 0.664,
"step": 8270
},
{
"epoch": 1.92,
"learning_rate": 2.015838937056147e-07,
"loss": 0.6591,
"step": 8280
},
{
"epoch": 1.92,
"learning_rate": 1.902117725257807e-07,
"loss": 0.6521,
"step": 8290
},
{
"epoch": 1.92,
"learning_rate": 1.791685802590093e-07,
"loss": 0.6733,
"step": 8300
},
{
"epoch": 1.93,
"learning_rate": 1.684544633162699e-07,
"loss": 0.667,
"step": 8310
},
{
"epoch": 1.93,
"learning_rate": 1.5806956374564142e-07,
"loss": 0.6694,
"step": 8320
},
{
"epoch": 1.93,
"learning_rate": 1.4801401923043855e-07,
"loss": 0.6554,
"step": 8330
},
{
"epoch": 1.93,
"learning_rate": 1.38287963087369e-07,
"loss": 0.651,
"step": 8340
},
{
"epoch": 1.94,
"learning_rate": 1.288915242647737e-07,
"loss": 0.6554,
"step": 8350
},
{
"epoch": 1.94,
"learning_rate": 1.198248273409197e-07,
"loss": 0.6856,
"step": 8360
},
{
"epoch": 1.94,
"learning_rate": 1.1108799252234625e-07,
"loss": 0.6678,
"step": 8370
},
{
"epoch": 1.94,
"learning_rate": 1.0268113564226856e-07,
"loss": 0.6546,
"step": 8380
},
{
"epoch": 1.94,
"learning_rate": 9.460436815904583e-08,
"loss": 0.685,
"step": 8390
},
{
"epoch": 1.95,
"learning_rate": 8.685779715470743e-08,
"loss": 0.6695,
"step": 8400
},
{
"epoch": 1.95,
"learning_rate": 7.94415253335179e-08,
"loss": 0.6657,
"step": 8410
},
{
"epoch": 1.95,
"learning_rate": 7.235565102063357e-08,
"loss": 0.6461,
"step": 8420
},
{
"epoch": 1.95,
"learning_rate": 6.560026816078424e-08,
"loss": 0.6671,
"step": 8430
},
{
"epoch": 1.96,
"learning_rate": 5.917546631704074e-08,
"loss": 0.6614,
"step": 8440
},
{
"epoch": 1.96,
"learning_rate": 5.308133066961596e-08,
"loss": 0.6817,
"step": 8450
},
{
"epoch": 1.96,
"learning_rate": 4.731794201474349e-08,
"loss": 0.6655,
"step": 8460
},
{
"epoch": 1.96,
"learning_rate": 4.188537676360071e-08,
"loss": 0.6612,
"step": 8470
},
{
"epoch": 1.97,
"learning_rate": 3.678370694130129e-08,
"loss": 0.6913,
"step": 8480
},
{
"epoch": 1.97,
"learning_rate": 3.201300018593478e-08,
"loss": 0.6849,
"step": 8490
},
{
"epoch": 1.97,
"learning_rate": 2.757331974767574e-08,
"loss": 0.661,
"step": 8500
},
{
"epoch": 1.97,
"learning_rate": 2.3464724487937128e-08,
"loss": 0.6754,
"step": 8510
},
{
"epoch": 1.97,
"learning_rate": 1.9687268878601507e-08,
"loss": 0.6689,
"step": 8520
},
{
"epoch": 1.98,
"learning_rate": 1.624100300128273e-08,
"loss": 0.6801,
"step": 8530
},
{
"epoch": 1.98,
"learning_rate": 1.312597254668202e-08,
"loss": 0.6558,
"step": 8540
},
{
"epoch": 1.98,
"learning_rate": 1.0342218813963467e-08,
"loss": 0.6736,
"step": 8550
},
{
"epoch": 1.98,
"learning_rate": 7.889778710218343e-09,
"loss": 0.6818,
"step": 8560
},
{
"epoch": 1.99,
"learning_rate": 5.768684749968278e-09,
"loss": 0.6682,
"step": 8570
},
{
"epoch": 1.99,
"learning_rate": 3.978965054743378e-09,
"loss": 0.6762,
"step": 8580
},
{
"epoch": 1.99,
"learning_rate": 2.5206433526991924e-09,
"loss": 0.6602,
"step": 8590
},
{
"epoch": 1.99,
"learning_rate": 1.393738978308634e-09,
"loss": 0.6754,
"step": 8600
},
{
"epoch": 2.0,
"learning_rate": 5.982668721038476e-10,
"loss": 0.6718,
"step": 8610
},
{
"epoch": 2.0,
"learning_rate": 1.3423758047914625e-10,
"loss": 0.6708,
"step": 8620
},
{
"epoch": 2.0,
"step": 8628,
"total_flos": 2.724860482467922e+18,
"train_loss": 0.7045552698505881,
"train_runtime": 69586.6665,
"train_samples_per_second": 1.984,
"train_steps_per_second": 0.124
}
],
"max_steps": 8628,
"num_train_epochs": 2,
"total_flos": 2.724860482467922e+18,
"trial_name": null,
"trial_params": null
}