bert-chinese-idioms / trainer_state.json
mmdjiji's picture
Update to final model
82c520a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 691863,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.9963865678609785e-05,
"loss": 1.3431,
"step": 500
},
{
"epoch": 0.0,
"learning_rate": 4.992773135721956e-05,
"loss": 1.3269,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 4.989159703582935e-05,
"loss": 1.2917,
"step": 1500
},
{
"epoch": 0.01,
"learning_rate": 4.9855462714439135e-05,
"loss": 1.3282,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 4.981932839304891e-05,
"loss": 1.2857,
"step": 2500
},
{
"epoch": 0.01,
"learning_rate": 4.9783194071658694e-05,
"loss": 1.2541,
"step": 3000
},
{
"epoch": 0.02,
"learning_rate": 4.9747059750268484e-05,
"loss": 1.2157,
"step": 3500
},
{
"epoch": 0.02,
"learning_rate": 4.971092542887826e-05,
"loss": 1.2527,
"step": 4000
},
{
"epoch": 0.02,
"learning_rate": 4.9674791107488043e-05,
"loss": 1.2246,
"step": 4500
},
{
"epoch": 0.02,
"learning_rate": 4.9638656786097827e-05,
"loss": 1.2072,
"step": 5000
},
{
"epoch": 0.02,
"learning_rate": 4.960252246470761e-05,
"loss": 1.2246,
"step": 5500
},
{
"epoch": 0.03,
"learning_rate": 4.956638814331739e-05,
"loss": 1.1926,
"step": 6000
},
{
"epoch": 0.03,
"learning_rate": 4.9530253821927176e-05,
"loss": 1.193,
"step": 6500
},
{
"epoch": 0.03,
"learning_rate": 4.949411950053696e-05,
"loss": 1.2025,
"step": 7000
},
{
"epoch": 0.03,
"learning_rate": 4.945798517914674e-05,
"loss": 1.1941,
"step": 7500
},
{
"epoch": 0.03,
"learning_rate": 4.9421850857756525e-05,
"loss": 1.1898,
"step": 8000
},
{
"epoch": 0.04,
"learning_rate": 4.938571653636631e-05,
"loss": 1.2054,
"step": 8500
},
{
"epoch": 0.04,
"learning_rate": 4.9349582214976085e-05,
"loss": 1.1774,
"step": 9000
},
{
"epoch": 0.04,
"learning_rate": 4.9313447893585874e-05,
"loss": 1.1779,
"step": 9500
},
{
"epoch": 0.04,
"learning_rate": 4.927731357219566e-05,
"loss": 1.1934,
"step": 10000
},
{
"epoch": 0.05,
"learning_rate": 4.9241179250805434e-05,
"loss": 1.148,
"step": 10500
},
{
"epoch": 0.05,
"learning_rate": 4.920504492941522e-05,
"loss": 1.167,
"step": 11000
},
{
"epoch": 0.05,
"learning_rate": 4.916891060802501e-05,
"loss": 1.4072,
"step": 11500
},
{
"epoch": 0.05,
"learning_rate": 4.913277628663478e-05,
"loss": 1.3979,
"step": 12000
},
{
"epoch": 0.05,
"learning_rate": 4.9096641965244566e-05,
"loss": 1.3993,
"step": 12500
},
{
"epoch": 0.06,
"learning_rate": 4.906050764385435e-05,
"loss": 1.3653,
"step": 13000
},
{
"epoch": 0.06,
"learning_rate": 4.902437332246413e-05,
"loss": 1.4102,
"step": 13500
},
{
"epoch": 0.06,
"learning_rate": 4.8988239001073915e-05,
"loss": 1.4023,
"step": 14000
},
{
"epoch": 0.06,
"learning_rate": 4.89521046796837e-05,
"loss": 1.4086,
"step": 14500
},
{
"epoch": 0.07,
"learning_rate": 4.8915970358293475e-05,
"loss": 1.3681,
"step": 15000
},
{
"epoch": 0.07,
"learning_rate": 4.8879836036903265e-05,
"loss": 1.3737,
"step": 15500
},
{
"epoch": 0.07,
"learning_rate": 4.884370171551305e-05,
"loss": 1.3768,
"step": 16000
},
{
"epoch": 0.07,
"learning_rate": 4.8807567394122824e-05,
"loss": 1.3738,
"step": 16500
},
{
"epoch": 0.07,
"learning_rate": 4.877143307273261e-05,
"loss": 1.4024,
"step": 17000
},
{
"epoch": 0.08,
"learning_rate": 4.873529875134239e-05,
"loss": 1.4007,
"step": 17500
},
{
"epoch": 0.08,
"learning_rate": 4.8699164429952173e-05,
"loss": 1.3797,
"step": 18000
},
{
"epoch": 0.08,
"learning_rate": 4.8663030108561957e-05,
"loss": 1.3598,
"step": 18500
},
{
"epoch": 0.08,
"learning_rate": 4.862689578717174e-05,
"loss": 1.3512,
"step": 19000
},
{
"epoch": 0.08,
"learning_rate": 4.859076146578152e-05,
"loss": 1.3744,
"step": 19500
},
{
"epoch": 0.09,
"learning_rate": 4.8554627144391306e-05,
"loss": 1.3753,
"step": 20000
},
{
"epoch": 0.09,
"learning_rate": 4.851849282300109e-05,
"loss": 1.3847,
"step": 20500
},
{
"epoch": 0.09,
"learning_rate": 4.848235850161087e-05,
"loss": 1.3828,
"step": 21000
},
{
"epoch": 0.09,
"learning_rate": 4.844622418022065e-05,
"loss": 1.3557,
"step": 21500
},
{
"epoch": 0.1,
"learning_rate": 4.841008985883044e-05,
"loss": 1.3499,
"step": 22000
},
{
"epoch": 0.1,
"learning_rate": 4.837395553744022e-05,
"loss": 1.3798,
"step": 22500
},
{
"epoch": 0.1,
"learning_rate": 4.833782121605e-05,
"loss": 1.3863,
"step": 23000
},
{
"epoch": 0.1,
"learning_rate": 4.830168689465978e-05,
"loss": 1.3792,
"step": 23500
},
{
"epoch": 0.1,
"learning_rate": 4.826555257326957e-05,
"loss": 1.3949,
"step": 24000
},
{
"epoch": 0.11,
"learning_rate": 4.822941825187935e-05,
"loss": 1.3579,
"step": 24500
},
{
"epoch": 0.11,
"learning_rate": 4.819328393048913e-05,
"loss": 1.3807,
"step": 25000
},
{
"epoch": 0.11,
"learning_rate": 4.815714960909891e-05,
"loss": 1.3331,
"step": 25500
},
{
"epoch": 0.11,
"learning_rate": 4.8121015287708696e-05,
"loss": 1.3689,
"step": 26000
},
{
"epoch": 0.11,
"learning_rate": 4.808488096631848e-05,
"loss": 1.3732,
"step": 26500
},
{
"epoch": 0.12,
"learning_rate": 4.804874664492826e-05,
"loss": 1.3432,
"step": 27000
},
{
"epoch": 0.12,
"learning_rate": 4.801261232353804e-05,
"loss": 1.3691,
"step": 27500
},
{
"epoch": 0.12,
"learning_rate": 4.797647800214783e-05,
"loss": 1.3541,
"step": 28000
},
{
"epoch": 0.12,
"learning_rate": 4.794034368075761e-05,
"loss": 1.344,
"step": 28500
},
{
"epoch": 0.13,
"learning_rate": 4.790420935936739e-05,
"loss": 1.3537,
"step": 29000
},
{
"epoch": 0.13,
"learning_rate": 4.786807503797717e-05,
"loss": 1.3744,
"step": 29500
},
{
"epoch": 0.13,
"learning_rate": 4.783194071658696e-05,
"loss": 1.3431,
"step": 30000
},
{
"epoch": 0.13,
"learning_rate": 4.779580639519674e-05,
"loss": 1.3639,
"step": 30500
},
{
"epoch": 0.13,
"learning_rate": 4.775967207380652e-05,
"loss": 1.3355,
"step": 31000
},
{
"epoch": 0.14,
"learning_rate": 4.7723537752416303e-05,
"loss": 1.3797,
"step": 31500
},
{
"epoch": 0.14,
"learning_rate": 4.7687403431026087e-05,
"loss": 1.3973,
"step": 32000
},
{
"epoch": 0.14,
"learning_rate": 4.765126910963587e-05,
"loss": 1.3768,
"step": 32500
},
{
"epoch": 0.14,
"learning_rate": 4.761513478824565e-05,
"loss": 1.3922,
"step": 33000
},
{
"epoch": 0.15,
"learning_rate": 4.7579000466855436e-05,
"loss": 1.4186,
"step": 33500
},
{
"epoch": 0.15,
"learning_rate": 4.754286614546521e-05,
"loss": 1.3648,
"step": 34000
},
{
"epoch": 0.15,
"learning_rate": 4.7506731824075e-05,
"loss": 1.3846,
"step": 34500
},
{
"epoch": 0.15,
"learning_rate": 4.7470597502684785e-05,
"loss": 1.3769,
"step": 35000
},
{
"epoch": 0.15,
"learning_rate": 4.743446318129456e-05,
"loss": 1.3466,
"step": 35500
},
{
"epoch": 0.16,
"learning_rate": 4.7398328859904344e-05,
"loss": 1.3716,
"step": 36000
},
{
"epoch": 0.16,
"learning_rate": 4.7362194538514134e-05,
"loss": 1.3673,
"step": 36500
},
{
"epoch": 0.16,
"learning_rate": 4.732606021712391e-05,
"loss": 1.3525,
"step": 37000
},
{
"epoch": 0.16,
"learning_rate": 4.7289925895733694e-05,
"loss": 1.3532,
"step": 37500
},
{
"epoch": 0.16,
"learning_rate": 4.725379157434348e-05,
"loss": 1.3844,
"step": 38000
},
{
"epoch": 0.17,
"learning_rate": 4.721765725295326e-05,
"loss": 1.3835,
"step": 38500
},
{
"epoch": 0.17,
"learning_rate": 4.718152293156304e-05,
"loss": 1.3957,
"step": 39000
},
{
"epoch": 0.17,
"learning_rate": 4.7145388610172826e-05,
"loss": 1.384,
"step": 39500
},
{
"epoch": 0.17,
"learning_rate": 4.710925428878261e-05,
"loss": 1.3367,
"step": 40000
},
{
"epoch": 0.18,
"learning_rate": 4.707311996739239e-05,
"loss": 1.3654,
"step": 40500
},
{
"epoch": 0.18,
"learning_rate": 4.7036985646002175e-05,
"loss": 1.3806,
"step": 41000
},
{
"epoch": 0.18,
"learning_rate": 4.700085132461196e-05,
"loss": 1.3837,
"step": 41500
},
{
"epoch": 0.18,
"learning_rate": 4.6964717003221735e-05,
"loss": 1.3801,
"step": 42000
},
{
"epoch": 0.18,
"learning_rate": 4.6928582681831525e-05,
"loss": 1.3544,
"step": 42500
},
{
"epoch": 0.19,
"learning_rate": 4.689244836044131e-05,
"loss": 1.3714,
"step": 43000
},
{
"epoch": 0.19,
"learning_rate": 4.6856314039051084e-05,
"loss": 1.3575,
"step": 43500
},
{
"epoch": 0.19,
"learning_rate": 4.682017971766087e-05,
"loss": 1.412,
"step": 44000
},
{
"epoch": 0.19,
"learning_rate": 4.678404539627066e-05,
"loss": 1.3921,
"step": 44500
},
{
"epoch": 0.2,
"learning_rate": 4.6747911074880433e-05,
"loss": 1.3363,
"step": 45000
},
{
"epoch": 0.2,
"learning_rate": 4.6711776753490217e-05,
"loss": 1.373,
"step": 45500
},
{
"epoch": 0.2,
"learning_rate": 4.66756424321e-05,
"loss": 1.393,
"step": 46000
},
{
"epoch": 0.2,
"learning_rate": 4.663950811070978e-05,
"loss": 1.413,
"step": 46500
},
{
"epoch": 0.2,
"learning_rate": 4.6603373789319566e-05,
"loss": 1.3882,
"step": 47000
},
{
"epoch": 0.21,
"learning_rate": 4.656723946792935e-05,
"loss": 1.3895,
"step": 47500
},
{
"epoch": 0.21,
"learning_rate": 4.6531105146539125e-05,
"loss": 1.4272,
"step": 48000
},
{
"epoch": 0.21,
"learning_rate": 4.649497082514891e-05,
"loss": 1.3834,
"step": 48500
},
{
"epoch": 0.21,
"learning_rate": 4.64588365037587e-05,
"loss": 1.3531,
"step": 49000
},
{
"epoch": 0.21,
"learning_rate": 4.6422702182368474e-05,
"loss": 1.3659,
"step": 49500
},
{
"epoch": 0.22,
"learning_rate": 4.638656786097826e-05,
"loss": 1.3751,
"step": 50000
},
{
"epoch": 0.22,
"learning_rate": 4.635043353958804e-05,
"loss": 1.3636,
"step": 50500
},
{
"epoch": 0.22,
"learning_rate": 4.6314299218197824e-05,
"loss": 1.4128,
"step": 51000
},
{
"epoch": 0.22,
"learning_rate": 4.627816489680761e-05,
"loss": 1.424,
"step": 51500
},
{
"epoch": 0.23,
"learning_rate": 4.624203057541739e-05,
"loss": 1.3846,
"step": 52000
},
{
"epoch": 0.23,
"learning_rate": 4.620589625402717e-05,
"loss": 1.3917,
"step": 52500
},
{
"epoch": 0.23,
"learning_rate": 4.6169761932636956e-05,
"loss": 1.4395,
"step": 53000
},
{
"epoch": 0.23,
"learning_rate": 4.613362761124674e-05,
"loss": 1.3742,
"step": 53500
},
{
"epoch": 0.23,
"learning_rate": 4.609749328985652e-05,
"loss": 1.4219,
"step": 54000
},
{
"epoch": 0.24,
"learning_rate": 4.60613589684663e-05,
"loss": 1.4127,
"step": 54500
},
{
"epoch": 0.24,
"learning_rate": 4.602522464707609e-05,
"loss": 1.3724,
"step": 55000
},
{
"epoch": 0.24,
"learning_rate": 4.598909032568587e-05,
"loss": 1.4132,
"step": 55500
},
{
"epoch": 0.24,
"learning_rate": 4.595295600429565e-05,
"loss": 1.4003,
"step": 56000
},
{
"epoch": 0.24,
"learning_rate": 4.591682168290543e-05,
"loss": 1.4179,
"step": 56500
},
{
"epoch": 0.25,
"learning_rate": 4.588068736151522e-05,
"loss": 1.418,
"step": 57000
},
{
"epoch": 0.25,
"learning_rate": 4.5844553040125e-05,
"loss": 1.4335,
"step": 57500
},
{
"epoch": 0.25,
"learning_rate": 4.580841871873478e-05,
"loss": 1.3935,
"step": 58000
},
{
"epoch": 0.25,
"learning_rate": 4.5772284397344563e-05,
"loss": 1.4047,
"step": 58500
},
{
"epoch": 0.26,
"learning_rate": 4.5736150075954346e-05,
"loss": 1.9087,
"step": 59000
},
{
"epoch": 0.26,
"learning_rate": 4.570001575456413e-05,
"loss": 1.9257,
"step": 59500
},
{
"epoch": 0.26,
"learning_rate": 4.566388143317391e-05,
"loss": 1.9329,
"step": 60000
},
{
"epoch": 0.26,
"learning_rate": 4.562774711178369e-05,
"loss": 1.9298,
"step": 60500
},
{
"epoch": 0.26,
"learning_rate": 4.559161279039348e-05,
"loss": 1.8722,
"step": 61000
},
{
"epoch": 0.27,
"learning_rate": 4.555547846900326e-05,
"loss": 1.8772,
"step": 61500
},
{
"epoch": 0.27,
"learning_rate": 4.551934414761304e-05,
"loss": 1.9697,
"step": 62000
},
{
"epoch": 0.27,
"learning_rate": 4.548320982622282e-05,
"loss": 1.8944,
"step": 62500
},
{
"epoch": 0.27,
"learning_rate": 4.5447075504832604e-05,
"loss": 1.9086,
"step": 63000
},
{
"epoch": 0.28,
"learning_rate": 4.541094118344239e-05,
"loss": 1.9308,
"step": 63500
},
{
"epoch": 0.28,
"learning_rate": 4.537480686205217e-05,
"loss": 1.8723,
"step": 64000
},
{
"epoch": 0.28,
"learning_rate": 4.5338672540661954e-05,
"loss": 1.901,
"step": 64500
},
{
"epoch": 0.28,
"learning_rate": 4.530253821927174e-05,
"loss": 1.9717,
"step": 65000
},
{
"epoch": 0.28,
"learning_rate": 4.526640389788152e-05,
"loss": 1.9005,
"step": 65500
},
{
"epoch": 0.29,
"learning_rate": 4.52302695764913e-05,
"loss": 1.9028,
"step": 66000
},
{
"epoch": 0.29,
"learning_rate": 4.5194135255101086e-05,
"loss": 1.89,
"step": 66500
},
{
"epoch": 0.29,
"learning_rate": 4.515800093371086e-05,
"loss": 1.8995,
"step": 67000
},
{
"epoch": 0.29,
"learning_rate": 4.512186661232065e-05,
"loss": 1.9324,
"step": 67500
},
{
"epoch": 0.29,
"learning_rate": 4.5085732290930435e-05,
"loss": 1.8813,
"step": 68000
},
{
"epoch": 0.3,
"learning_rate": 4.504959796954021e-05,
"loss": 1.8654,
"step": 68500
},
{
"epoch": 0.3,
"learning_rate": 4.5013463648149995e-05,
"loss": 1.9212,
"step": 69000
},
{
"epoch": 0.3,
"learning_rate": 4.4977329326759785e-05,
"loss": 1.9145,
"step": 69500
},
{
"epoch": 0.3,
"learning_rate": 4.494119500536956e-05,
"loss": 1.9058,
"step": 70000
},
{
"epoch": 0.31,
"learning_rate": 4.4905060683979344e-05,
"loss": 1.8856,
"step": 70500
},
{
"epoch": 0.31,
"learning_rate": 4.486892636258913e-05,
"loss": 1.8698,
"step": 71000
},
{
"epoch": 0.31,
"learning_rate": 4.483279204119891e-05,
"loss": 1.8785,
"step": 71500
},
{
"epoch": 0.31,
"learning_rate": 4.479665771980869e-05,
"loss": 1.908,
"step": 72000
},
{
"epoch": 0.31,
"learning_rate": 4.4760523398418476e-05,
"loss": 1.8441,
"step": 72500
},
{
"epoch": 0.32,
"learning_rate": 4.472438907702825e-05,
"loss": 1.9034,
"step": 73000
},
{
"epoch": 0.32,
"learning_rate": 4.468825475563804e-05,
"loss": 1.9122,
"step": 73500
},
{
"epoch": 0.32,
"learning_rate": 4.4652120434247826e-05,
"loss": 1.8821,
"step": 74000
},
{
"epoch": 0.32,
"learning_rate": 4.46159861128576e-05,
"loss": 1.8932,
"step": 74500
},
{
"epoch": 0.33,
"learning_rate": 4.4579851791467385e-05,
"loss": 1.8587,
"step": 75000
},
{
"epoch": 0.33,
"learning_rate": 4.4543717470077175e-05,
"loss": 1.8753,
"step": 75500
},
{
"epoch": 0.33,
"learning_rate": 4.450758314868695e-05,
"loss": 1.9215,
"step": 76000
},
{
"epoch": 0.33,
"learning_rate": 4.4471448827296734e-05,
"loss": 1.8413,
"step": 76500
},
{
"epoch": 0.33,
"learning_rate": 4.443531450590652e-05,
"loss": 1.9191,
"step": 77000
},
{
"epoch": 0.34,
"learning_rate": 4.43991801845163e-05,
"loss": 1.9044,
"step": 77500
},
{
"epoch": 0.34,
"learning_rate": 4.4363045863126084e-05,
"loss": 1.9227,
"step": 78000
},
{
"epoch": 0.34,
"learning_rate": 4.432691154173587e-05,
"loss": 1.9072,
"step": 78500
},
{
"epoch": 0.34,
"learning_rate": 4.429077722034565e-05,
"loss": 1.9007,
"step": 79000
},
{
"epoch": 0.34,
"learning_rate": 4.4254642898955426e-05,
"loss": 1.9341,
"step": 79500
},
{
"epoch": 0.35,
"learning_rate": 4.4218508577565216e-05,
"loss": 1.9075,
"step": 80000
},
{
"epoch": 0.35,
"learning_rate": 4.4182374256175e-05,
"loss": 1.9345,
"step": 80500
},
{
"epoch": 0.35,
"learning_rate": 4.4146239934784776e-05,
"loss": 1.8817,
"step": 81000
},
{
"epoch": 0.35,
"learning_rate": 4.411010561339456e-05,
"loss": 1.8741,
"step": 81500
},
{
"epoch": 0.36,
"learning_rate": 4.407397129200435e-05,
"loss": 1.859,
"step": 82000
},
{
"epoch": 0.36,
"learning_rate": 4.4037836970614125e-05,
"loss": 1.8709,
"step": 82500
},
{
"epoch": 0.36,
"learning_rate": 4.400170264922391e-05,
"loss": 1.9188,
"step": 83000
},
{
"epoch": 0.36,
"learning_rate": 4.396556832783369e-05,
"loss": 1.8965,
"step": 83500
},
{
"epoch": 0.36,
"learning_rate": 4.3929434006443474e-05,
"loss": 1.8495,
"step": 84000
},
{
"epoch": 0.37,
"learning_rate": 4.389329968505326e-05,
"loss": 1.9022,
"step": 84500
},
{
"epoch": 0.37,
"learning_rate": 4.385716536366304e-05,
"loss": 1.8732,
"step": 85000
},
{
"epoch": 0.37,
"learning_rate": 4.3821031042272817e-05,
"loss": 1.8634,
"step": 85500
},
{
"epoch": 0.37,
"learning_rate": 4.3784896720882606e-05,
"loss": 1.8772,
"step": 86000
},
{
"epoch": 0.38,
"learning_rate": 4.374876239949239e-05,
"loss": 1.8867,
"step": 86500
},
{
"epoch": 0.38,
"learning_rate": 4.3712628078102166e-05,
"loss": 1.8709,
"step": 87000
},
{
"epoch": 0.38,
"learning_rate": 4.367649375671195e-05,
"loss": 1.9255,
"step": 87500
},
{
"epoch": 0.38,
"learning_rate": 4.364035943532174e-05,
"loss": 1.8821,
"step": 88000
},
{
"epoch": 0.38,
"learning_rate": 4.3604225113931515e-05,
"loss": 1.9044,
"step": 88500
},
{
"epoch": 0.39,
"learning_rate": 4.35680907925413e-05,
"loss": 1.8816,
"step": 89000
},
{
"epoch": 0.39,
"learning_rate": 4.353195647115108e-05,
"loss": 1.8611,
"step": 89500
},
{
"epoch": 0.39,
"learning_rate": 4.3495822149760864e-05,
"loss": 1.8714,
"step": 90000
},
{
"epoch": 0.39,
"learning_rate": 4.345968782837065e-05,
"loss": 1.8591,
"step": 90500
},
{
"epoch": 0.39,
"learning_rate": 4.342355350698043e-05,
"loss": 1.8372,
"step": 91000
},
{
"epoch": 0.4,
"learning_rate": 4.3387419185590214e-05,
"loss": 1.8636,
"step": 91500
},
{
"epoch": 0.4,
"learning_rate": 4.33512848642e-05,
"loss": 1.8268,
"step": 92000
},
{
"epoch": 0.4,
"learning_rate": 4.331515054280978e-05,
"loss": 1.8421,
"step": 92500
},
{
"epoch": 0.4,
"learning_rate": 4.327901622141956e-05,
"loss": 1.8577,
"step": 93000
},
{
"epoch": 0.41,
"learning_rate": 4.324288190002934e-05,
"loss": 1.8364,
"step": 93500
},
{
"epoch": 0.41,
"learning_rate": 4.320674757863913e-05,
"loss": 1.8905,
"step": 94000
},
{
"epoch": 0.41,
"learning_rate": 4.317061325724891e-05,
"loss": 1.8942,
"step": 94500
},
{
"epoch": 0.41,
"learning_rate": 4.313447893585869e-05,
"loss": 1.8807,
"step": 95000
},
{
"epoch": 0.41,
"learning_rate": 4.309834461446847e-05,
"loss": 1.8551,
"step": 95500
},
{
"epoch": 0.42,
"learning_rate": 4.3062210293078255e-05,
"loss": 1.8697,
"step": 96000
},
{
"epoch": 0.42,
"learning_rate": 4.302607597168804e-05,
"loss": 1.8565,
"step": 96500
},
{
"epoch": 0.42,
"learning_rate": 4.298994165029782e-05,
"loss": 1.9006,
"step": 97000
},
{
"epoch": 0.42,
"learning_rate": 4.2953807328907604e-05,
"loss": 1.8626,
"step": 97500
},
{
"epoch": 0.42,
"learning_rate": 4.291767300751739e-05,
"loss": 1.8432,
"step": 98000
},
{
"epoch": 0.43,
"learning_rate": 4.288153868612717e-05,
"loss": 1.8767,
"step": 98500
},
{
"epoch": 0.43,
"learning_rate": 4.284540436473695e-05,
"loss": 1.8409,
"step": 99000
},
{
"epoch": 0.43,
"learning_rate": 4.2809270043346736e-05,
"loss": 1.8729,
"step": 99500
},
{
"epoch": 0.43,
"learning_rate": 4.277313572195651e-05,
"loss": 1.8438,
"step": 100000
},
{
"epoch": 0.44,
"learning_rate": 4.27370014005663e-05,
"loss": 1.8518,
"step": 100500
},
{
"epoch": 0.44,
"learning_rate": 4.270086707917608e-05,
"loss": 1.8619,
"step": 101000
},
{
"epoch": 0.44,
"learning_rate": 4.266473275778586e-05,
"loss": 1.847,
"step": 101500
},
{
"epoch": 0.44,
"learning_rate": 4.2628598436395645e-05,
"loss": 1.8798,
"step": 102000
},
{
"epoch": 0.44,
"learning_rate": 4.259246411500543e-05,
"loss": 1.844,
"step": 102500
},
{
"epoch": 0.45,
"learning_rate": 4.255632979361521e-05,
"loss": 1.819,
"step": 103000
},
{
"epoch": 0.45,
"learning_rate": 4.2520195472224994e-05,
"loss": 1.8694,
"step": 103500
},
{
"epoch": 0.45,
"learning_rate": 4.248406115083478e-05,
"loss": 1.8922,
"step": 104000
},
{
"epoch": 0.45,
"learning_rate": 4.244792682944456e-05,
"loss": 1.8731,
"step": 104500
},
{
"epoch": 0.46,
"learning_rate": 4.2411792508054344e-05,
"loss": 1.8815,
"step": 105000
},
{
"epoch": 0.46,
"learning_rate": 4.237565818666413e-05,
"loss": 1.8295,
"step": 105500
},
{
"epoch": 0.46,
"learning_rate": 4.23395238652739e-05,
"loss": 1.8538,
"step": 106000
},
{
"epoch": 0.46,
"learning_rate": 4.230338954388369e-05,
"loss": 1.8435,
"step": 106500
},
{
"epoch": 0.46,
"learning_rate": 4.2267255222493476e-05,
"loss": 1.8359,
"step": 107000
},
{
"epoch": 0.47,
"learning_rate": 4.223112090110325e-05,
"loss": 1.8161,
"step": 107500
},
{
"epoch": 0.47,
"learning_rate": 4.2194986579713035e-05,
"loss": 1.8572,
"step": 108000
},
{
"epoch": 0.47,
"learning_rate": 4.2158852258322825e-05,
"loss": 1.8377,
"step": 108500
},
{
"epoch": 0.47,
"learning_rate": 4.21227179369326e-05,
"loss": 1.8226,
"step": 109000
},
{
"epoch": 0.47,
"learning_rate": 4.2086583615542385e-05,
"loss": 1.8561,
"step": 109500
},
{
"epoch": 0.48,
"learning_rate": 4.205044929415217e-05,
"loss": 1.8836,
"step": 110000
},
{
"epoch": 0.48,
"learning_rate": 4.201431497276195e-05,
"loss": 1.8286,
"step": 110500
},
{
"epoch": 0.48,
"learning_rate": 4.1978180651371734e-05,
"loss": 1.8368,
"step": 111000
},
{
"epoch": 0.48,
"learning_rate": 4.194204632998152e-05,
"loss": 1.8743,
"step": 111500
},
{
"epoch": 0.49,
"learning_rate": 4.19059120085913e-05,
"loss": 1.8616,
"step": 112000
},
{
"epoch": 0.49,
"learning_rate": 4.1869777687201077e-05,
"loss": 1.8742,
"step": 112500
},
{
"epoch": 0.49,
"learning_rate": 4.1833643365810866e-05,
"loss": 1.87,
"step": 113000
},
{
"epoch": 0.49,
"learning_rate": 4.179750904442065e-05,
"loss": 1.8586,
"step": 113500
},
{
"epoch": 0.49,
"learning_rate": 4.1761374723030426e-05,
"loss": 1.8793,
"step": 114000
},
{
"epoch": 0.5,
"learning_rate": 4.172524040164021e-05,
"loss": 1.8552,
"step": 114500
},
{
"epoch": 0.5,
"learning_rate": 4.168910608025e-05,
"loss": 1.8162,
"step": 115000
},
{
"epoch": 0.5,
"learning_rate": 4.1652971758859775e-05,
"loss": 1.8504,
"step": 115500
},
{
"epoch": 0.5,
"learning_rate": 4.161683743746956e-05,
"loss": 1.862,
"step": 116000
},
{
"epoch": 0.51,
"learning_rate": 4.158070311607934e-05,
"loss": 1.8428,
"step": 116500
},
{
"epoch": 0.51,
"learning_rate": 4.1544568794689124e-05,
"loss": 1.8437,
"step": 117000
},
{
"epoch": 0.51,
"learning_rate": 4.150843447329891e-05,
"loss": 1.8408,
"step": 117500
},
{
"epoch": 0.51,
"learning_rate": 4.147230015190869e-05,
"loss": 1.8228,
"step": 118000
},
{
"epoch": 0.51,
"learning_rate": 4.143616583051847e-05,
"loss": 1.8366,
"step": 118500
},
{
"epoch": 0.52,
"learning_rate": 4.140003150912826e-05,
"loss": 1.83,
"step": 119000
},
{
"epoch": 0.52,
"learning_rate": 4.136389718773804e-05,
"loss": 1.8401,
"step": 119500
},
{
"epoch": 0.52,
"learning_rate": 4.1327762866347816e-05,
"loss": 1.8325,
"step": 120000
},
{
"epoch": 0.52,
"learning_rate": 4.12916285449576e-05,
"loss": 1.8386,
"step": 120500
},
{
"epoch": 0.52,
"learning_rate": 4.125549422356739e-05,
"loss": 1.828,
"step": 121000
},
{
"epoch": 0.53,
"learning_rate": 4.1219359902177165e-05,
"loss": 1.8971,
"step": 121500
},
{
"epoch": 0.53,
"learning_rate": 4.118322558078695e-05,
"loss": 1.8281,
"step": 122000
},
{
"epoch": 0.53,
"learning_rate": 4.114709125939673e-05,
"loss": 1.8447,
"step": 122500
},
{
"epoch": 0.53,
"learning_rate": 4.1110956938006515e-05,
"loss": 1.8189,
"step": 123000
},
{
"epoch": 0.54,
"learning_rate": 4.10748226166163e-05,
"loss": 1.7937,
"step": 123500
},
{
"epoch": 0.54,
"learning_rate": 4.103868829522608e-05,
"loss": 1.8249,
"step": 124000
},
{
"epoch": 0.54,
"learning_rate": 4.1002553973835864e-05,
"loss": 1.8378,
"step": 124500
},
{
"epoch": 0.54,
"learning_rate": 4.096641965244565e-05,
"loss": 1.8259,
"step": 125000
},
{
"epoch": 0.54,
"learning_rate": 4.093028533105543e-05,
"loss": 1.817,
"step": 125500
},
{
"epoch": 0.55,
"learning_rate": 4.089415100966521e-05,
"loss": 1.7849,
"step": 126000
},
{
"epoch": 0.55,
"learning_rate": 4.085801668827499e-05,
"loss": 1.8223,
"step": 126500
},
{
"epoch": 0.55,
"learning_rate": 4.082188236688477e-05,
"loss": 1.8344,
"step": 127000
},
{
"epoch": 0.55,
"learning_rate": 4.078574804549456e-05,
"loss": 1.7857,
"step": 127500
},
{
"epoch": 0.56,
"learning_rate": 4.074961372410434e-05,
"loss": 1.8327,
"step": 128000
},
{
"epoch": 0.56,
"learning_rate": 4.071347940271412e-05,
"loss": 1.8541,
"step": 128500
},
{
"epoch": 0.56,
"learning_rate": 4.0677345081323905e-05,
"loss": 1.784,
"step": 129000
},
{
"epoch": 0.56,
"learning_rate": 4.064121075993369e-05,
"loss": 1.803,
"step": 129500
},
{
"epoch": 0.56,
"learning_rate": 4.060507643854347e-05,
"loss": 1.8191,
"step": 130000
},
{
"epoch": 0.57,
"learning_rate": 4.0568942117153254e-05,
"loss": 1.8365,
"step": 130500
},
{
"epoch": 0.57,
"learning_rate": 4.053280779576303e-05,
"loss": 1.7944,
"step": 131000
},
{
"epoch": 0.57,
"learning_rate": 4.049667347437282e-05,
"loss": 1.8336,
"step": 131500
},
{
"epoch": 0.57,
"learning_rate": 4.0460539152982604e-05,
"loss": 1.798,
"step": 132000
},
{
"epoch": 0.57,
"learning_rate": 4.042440483159238e-05,
"loss": 1.8192,
"step": 132500
},
{
"epoch": 0.58,
"learning_rate": 4.038827051020216e-05,
"loss": 1.8244,
"step": 133000
},
{
"epoch": 0.58,
"learning_rate": 4.035213618881195e-05,
"loss": 1.8317,
"step": 133500
},
{
"epoch": 0.58,
"learning_rate": 4.031600186742173e-05,
"loss": 1.8386,
"step": 134000
},
{
"epoch": 0.58,
"learning_rate": 4.027986754603151e-05,
"loss": 1.8237,
"step": 134500
},
{
"epoch": 0.59,
"learning_rate": 4.0243733224641295e-05,
"loss": 1.8035,
"step": 135000
},
{
"epoch": 0.59,
"learning_rate": 4.020759890325108e-05,
"loss": 1.806,
"step": 135500
},
{
"epoch": 0.59,
"learning_rate": 4.017146458186086e-05,
"loss": 1.8432,
"step": 136000
},
{
"epoch": 0.59,
"learning_rate": 4.0135330260470645e-05,
"loss": 1.8079,
"step": 136500
},
{
"epoch": 0.59,
"learning_rate": 4.009919593908043e-05,
"loss": 1.819,
"step": 137000
},
{
"epoch": 0.6,
"learning_rate": 4.006306161769021e-05,
"loss": 1.8346,
"step": 137500
},
{
"epoch": 0.6,
"learning_rate": 4.0026927296299994e-05,
"loss": 1.8166,
"step": 138000
},
{
"epoch": 0.6,
"learning_rate": 3.999079297490978e-05,
"loss": 1.8071,
"step": 138500
},
{
"epoch": 0.6,
"learning_rate": 3.9954658653519553e-05,
"loss": 1.7835,
"step": 139000
},
{
"epoch": 0.6,
"learning_rate": 3.991852433212934e-05,
"loss": 1.801,
"step": 139500
},
{
"epoch": 0.61,
"learning_rate": 3.9882390010739126e-05,
"loss": 1.7885,
"step": 140000
},
{
"epoch": 0.61,
"learning_rate": 3.98462556893489e-05,
"loss": 1.7929,
"step": 140500
},
{
"epoch": 0.61,
"learning_rate": 3.9810121367958686e-05,
"loss": 1.7948,
"step": 141000
},
{
"epoch": 0.61,
"learning_rate": 3.977398704656847e-05,
"loss": 1.8254,
"step": 141500
},
{
"epoch": 0.62,
"learning_rate": 3.973785272517825e-05,
"loss": 1.7981,
"step": 142000
},
{
"epoch": 0.62,
"learning_rate": 3.9701718403788035e-05,
"loss": 1.8212,
"step": 142500
},
{
"epoch": 0.62,
"learning_rate": 3.966558408239782e-05,
"loss": 1.8422,
"step": 143000
},
{
"epoch": 0.62,
"learning_rate": 3.9629449761007594e-05,
"loss": 1.8325,
"step": 143500
},
{
"epoch": 0.62,
"learning_rate": 3.9593315439617384e-05,
"loss": 1.7791,
"step": 144000
},
{
"epoch": 0.63,
"learning_rate": 3.955718111822717e-05,
"loss": 1.8171,
"step": 144500
},
{
"epoch": 0.63,
"learning_rate": 3.9521046796836944e-05,
"loss": 1.8308,
"step": 145000
},
{
"epoch": 0.63,
"learning_rate": 3.948491247544673e-05,
"loss": 1.7797,
"step": 145500
},
{
"epoch": 0.63,
"learning_rate": 3.944877815405652e-05,
"loss": 1.8158,
"step": 146000
},
{
"epoch": 0.64,
"learning_rate": 3.941264383266629e-05,
"loss": 1.7879,
"step": 146500
},
{
"epoch": 0.64,
"learning_rate": 3.9376509511276076e-05,
"loss": 1.845,
"step": 147000
},
{
"epoch": 0.64,
"learning_rate": 3.934037518988586e-05,
"loss": 1.8268,
"step": 147500
},
{
"epoch": 0.64,
"learning_rate": 3.930424086849564e-05,
"loss": 1.8198,
"step": 148000
},
{
"epoch": 0.64,
"learning_rate": 3.9268106547105425e-05,
"loss": 1.7762,
"step": 148500
},
{
"epoch": 0.65,
"learning_rate": 3.923197222571521e-05,
"loss": 1.8328,
"step": 149000
},
{
"epoch": 0.65,
"learning_rate": 3.919583790432499e-05,
"loss": 1.8194,
"step": 149500
},
{
"epoch": 0.65,
"learning_rate": 3.9159703582934775e-05,
"loss": 1.8121,
"step": 150000
},
{
"epoch": 0.65,
"learning_rate": 3.912356926154456e-05,
"loss": 1.7601,
"step": 150500
},
{
"epoch": 0.65,
"learning_rate": 3.908743494015434e-05,
"loss": 1.7828,
"step": 151000
},
{
"epoch": 0.66,
"learning_rate": 3.905130061876412e-05,
"loss": 1.7874,
"step": 151500
},
{
"epoch": 0.66,
"learning_rate": 3.901516629737391e-05,
"loss": 1.8258,
"step": 152000
},
{
"epoch": 0.66,
"learning_rate": 3.897903197598369e-05,
"loss": 1.7744,
"step": 152500
},
{
"epoch": 0.66,
"learning_rate": 3.8942897654593466e-05,
"loss": 1.8018,
"step": 153000
},
{
"epoch": 0.67,
"learning_rate": 3.890676333320325e-05,
"loss": 1.7807,
"step": 153500
},
{
"epoch": 0.67,
"learning_rate": 3.887062901181304e-05,
"loss": 1.8158,
"step": 154000
},
{
"epoch": 0.67,
"learning_rate": 3.8834494690422816e-05,
"loss": 1.77,
"step": 154500
},
{
"epoch": 0.67,
"learning_rate": 3.87983603690326e-05,
"loss": 1.8032,
"step": 155000
},
{
"epoch": 0.67,
"learning_rate": 3.876222604764238e-05,
"loss": 1.784,
"step": 155500
},
{
"epoch": 0.68,
"learning_rate": 3.8726091726252165e-05,
"loss": 1.7757,
"step": 156000
},
{
"epoch": 0.68,
"learning_rate": 3.868995740486195e-05,
"loss": 1.7735,
"step": 156500
},
{
"epoch": 0.68,
"learning_rate": 3.865382308347173e-05,
"loss": 1.8015,
"step": 157000
},
{
"epoch": 0.68,
"learning_rate": 3.861768876208151e-05,
"loss": 1.7752,
"step": 157500
},
{
"epoch": 0.69,
"learning_rate": 3.858155444069129e-05,
"loss": 1.7906,
"step": 158000
},
{
"epoch": 0.69,
"learning_rate": 3.854542011930108e-05,
"loss": 1.7963,
"step": 158500
},
{
"epoch": 0.69,
"learning_rate": 3.850928579791086e-05,
"loss": 1.7865,
"step": 159000
},
{
"epoch": 0.69,
"learning_rate": 3.847315147652064e-05,
"loss": 1.7982,
"step": 159500
},
{
"epoch": 0.69,
"learning_rate": 3.843701715513042e-05,
"loss": 1.7739,
"step": 160000
},
{
"epoch": 0.7,
"learning_rate": 3.8400882833740206e-05,
"loss": 1.7949,
"step": 160500
},
{
"epoch": 0.7,
"learning_rate": 3.836474851234999e-05,
"loss": 1.8232,
"step": 161000
},
{
"epoch": 0.7,
"learning_rate": 3.832861419095977e-05,
"loss": 1.7773,
"step": 161500
},
{
"epoch": 0.7,
"learning_rate": 3.8292479869569555e-05,
"loss": 1.8039,
"step": 162000
},
{
"epoch": 0.7,
"learning_rate": 3.825634554817934e-05,
"loss": 1.8135,
"step": 162500
},
{
"epoch": 0.71,
"learning_rate": 3.822021122678912e-05,
"loss": 1.7746,
"step": 163000
},
{
"epoch": 0.71,
"learning_rate": 3.8184076905398905e-05,
"loss": 1.7715,
"step": 163500
},
{
"epoch": 0.71,
"learning_rate": 3.814794258400868e-05,
"loss": 1.7867,
"step": 164000
},
{
"epoch": 0.71,
"learning_rate": 3.811180826261847e-05,
"loss": 1.7638,
"step": 164500
},
{
"epoch": 0.72,
"learning_rate": 3.8075673941228254e-05,
"loss": 1.829,
"step": 165000
},
{
"epoch": 0.72,
"learning_rate": 3.803953961983803e-05,
"loss": 1.7995,
"step": 165500
},
{
"epoch": 0.72,
"learning_rate": 3.800340529844781e-05,
"loss": 1.7798,
"step": 166000
},
{
"epoch": 0.72,
"learning_rate": 3.79672709770576e-05,
"loss": 1.7758,
"step": 166500
},
{
"epoch": 0.72,
"learning_rate": 3.793113665566738e-05,
"loss": 1.797,
"step": 167000
},
{
"epoch": 0.73,
"learning_rate": 3.789500233427716e-05,
"loss": 1.816,
"step": 167500
},
{
"epoch": 0.73,
"learning_rate": 3.7858868012886946e-05,
"loss": 1.8258,
"step": 168000
},
{
"epoch": 0.73,
"learning_rate": 3.782273369149673e-05,
"loss": 1.7756,
"step": 168500
},
{
"epoch": 0.73,
"learning_rate": 3.778659937010651e-05,
"loss": 1.7822,
"step": 169000
},
{
"epoch": 0.73,
"learning_rate": 3.7750465048716295e-05,
"loss": 1.8328,
"step": 169500
},
{
"epoch": 0.74,
"learning_rate": 3.771433072732608e-05,
"loss": 1.7982,
"step": 170000
},
{
"epoch": 0.74,
"learning_rate": 3.767819640593586e-05,
"loss": 1.7811,
"step": 170500
},
{
"epoch": 0.74,
"learning_rate": 3.7642062084545644e-05,
"loss": 1.7518,
"step": 171000
},
{
"epoch": 0.74,
"learning_rate": 3.760592776315543e-05,
"loss": 1.7621,
"step": 171500
},
{
"epoch": 0.75,
"learning_rate": 3.7569793441765204e-05,
"loss": 1.783,
"step": 172000
},
{
"epoch": 0.75,
"learning_rate": 3.7533659120374994e-05,
"loss": 1.7684,
"step": 172500
},
{
"epoch": 0.75,
"learning_rate": 3.749752479898478e-05,
"loss": 1.756,
"step": 173000
},
{
"epoch": 0.75,
"learning_rate": 3.746139047759455e-05,
"loss": 1.7809,
"step": 173500
},
{
"epoch": 0.75,
"learning_rate": 3.7425256156204336e-05,
"loss": 1.8065,
"step": 174000
},
{
"epoch": 0.76,
"learning_rate": 3.738912183481412e-05,
"loss": 1.7403,
"step": 174500
},
{
"epoch": 0.76,
"learning_rate": 3.73529875134239e-05,
"loss": 1.7967,
"step": 175000
},
{
"epoch": 0.76,
"learning_rate": 3.7316853192033685e-05,
"loss": 1.7648,
"step": 175500
},
{
"epoch": 0.76,
"learning_rate": 3.728071887064347e-05,
"loss": 1.7702,
"step": 176000
},
{
"epoch": 0.77,
"learning_rate": 3.7244584549253245e-05,
"loss": 1.7684,
"step": 176500
},
{
"epoch": 0.77,
"learning_rate": 3.7208450227863035e-05,
"loss": 1.7673,
"step": 177000
},
{
"epoch": 0.77,
"learning_rate": 3.717231590647282e-05,
"loss": 1.7564,
"step": 177500
},
{
"epoch": 0.77,
"learning_rate": 3.7136181585082594e-05,
"loss": 1.7873,
"step": 178000
},
{
"epoch": 0.77,
"learning_rate": 3.710004726369238e-05,
"loss": 1.8206,
"step": 178500
},
{
"epoch": 0.78,
"learning_rate": 3.706391294230217e-05,
"loss": 1.7829,
"step": 179000
},
{
"epoch": 0.78,
"learning_rate": 3.702777862091194e-05,
"loss": 1.7859,
"step": 179500
},
{
"epoch": 0.78,
"learning_rate": 3.6991644299521726e-05,
"loss": 1.7869,
"step": 180000
},
{
"epoch": 0.78,
"learning_rate": 3.695550997813151e-05,
"loss": 1.7888,
"step": 180500
},
{
"epoch": 0.78,
"learning_rate": 3.691937565674129e-05,
"loss": 1.7676,
"step": 181000
},
{
"epoch": 0.79,
"learning_rate": 3.6883241335351076e-05,
"loss": 1.8067,
"step": 181500
},
{
"epoch": 0.79,
"learning_rate": 3.684710701396086e-05,
"loss": 1.7511,
"step": 182000
},
{
"epoch": 0.79,
"learning_rate": 3.681097269257064e-05,
"loss": 1.7919,
"step": 182500
},
{
"epoch": 0.79,
"learning_rate": 3.6774838371180425e-05,
"loss": 1.7617,
"step": 183000
},
{
"epoch": 0.8,
"learning_rate": 3.673870404979021e-05,
"loss": 1.7238,
"step": 183500
},
{
"epoch": 0.8,
"learning_rate": 3.670256972839999e-05,
"loss": 1.743,
"step": 184000
},
{
"epoch": 0.8,
"learning_rate": 3.666643540700977e-05,
"loss": 1.7632,
"step": 184500
},
{
"epoch": 0.8,
"learning_rate": 3.663030108561956e-05,
"loss": 1.7561,
"step": 185000
},
{
"epoch": 0.8,
"learning_rate": 3.659416676422934e-05,
"loss": 1.7868,
"step": 185500
},
{
"epoch": 0.81,
"learning_rate": 3.655803244283912e-05,
"loss": 1.7396,
"step": 186000
},
{
"epoch": 0.81,
"learning_rate": 3.65218981214489e-05,
"loss": 1.7736,
"step": 186500
},
{
"epoch": 0.81,
"learning_rate": 3.648576380005869e-05,
"loss": 1.8023,
"step": 187000
},
{
"epoch": 0.81,
"learning_rate": 3.6449629478668466e-05,
"loss": 1.7625,
"step": 187500
},
{
"epoch": 0.82,
"learning_rate": 3.641349515727825e-05,
"loss": 1.7317,
"step": 188000
},
{
"epoch": 0.82,
"learning_rate": 3.637736083588803e-05,
"loss": 1.7512,
"step": 188500
},
{
"epoch": 0.82,
"learning_rate": 3.634122651449781e-05,
"loss": 1.7677,
"step": 189000
},
{
"epoch": 0.82,
"learning_rate": 3.63050921931076e-05,
"loss": 1.7639,
"step": 189500
},
{
"epoch": 0.82,
"learning_rate": 3.626895787171738e-05,
"loss": 1.8208,
"step": 190000
},
{
"epoch": 0.83,
"learning_rate": 3.623282355032716e-05,
"loss": 1.7535,
"step": 190500
},
{
"epoch": 0.83,
"learning_rate": 3.619668922893694e-05,
"loss": 1.7741,
"step": 191000
},
{
"epoch": 0.83,
"learning_rate": 3.616055490754673e-05,
"loss": 1.7561,
"step": 191500
},
{
"epoch": 0.83,
"learning_rate": 3.612442058615651e-05,
"loss": 1.7307,
"step": 192000
},
{
"epoch": 0.83,
"learning_rate": 3.608828626476629e-05,
"loss": 1.7865,
"step": 192500
},
{
"epoch": 0.84,
"learning_rate": 3.605215194337607e-05,
"loss": 1.7833,
"step": 193000
},
{
"epoch": 0.84,
"learning_rate": 3.6016017621985856e-05,
"loss": 1.749,
"step": 193500
},
{
"epoch": 0.84,
"learning_rate": 3.597988330059564e-05,
"loss": 1.7587,
"step": 194000
},
{
"epoch": 0.84,
"learning_rate": 3.594374897920542e-05,
"loss": 1.7879,
"step": 194500
},
{
"epoch": 0.85,
"learning_rate": 3.5907614657815206e-05,
"loss": 1.7174,
"step": 195000
},
{
"epoch": 0.85,
"learning_rate": 3.587148033642499e-05,
"loss": 1.7353,
"step": 195500
},
{
"epoch": 0.85,
"learning_rate": 3.583534601503477e-05,
"loss": 1.7987,
"step": 196000
},
{
"epoch": 0.85,
"learning_rate": 3.5799211693644555e-05,
"loss": 1.7563,
"step": 196500
},
{
"epoch": 0.85,
"learning_rate": 3.576307737225433e-05,
"loss": 1.7937,
"step": 197000
},
{
"epoch": 0.86,
"learning_rate": 3.572694305086412e-05,
"loss": 1.7921,
"step": 197500
},
{
"epoch": 0.86,
"learning_rate": 3.5690808729473904e-05,
"loss": 1.7799,
"step": 198000
},
{
"epoch": 0.86,
"learning_rate": 3.565467440808368e-05,
"loss": 1.7276,
"step": 198500
},
{
"epoch": 0.86,
"learning_rate": 3.5618540086693464e-05,
"loss": 1.7753,
"step": 199000
},
{
"epoch": 0.87,
"learning_rate": 3.5582405765303254e-05,
"loss": 1.7645,
"step": 199500
},
{
"epoch": 0.87,
"learning_rate": 3.554627144391303e-05,
"loss": 1.7554,
"step": 200000
},
{
"epoch": 0.87,
"learning_rate": 3.551013712252281e-05,
"loss": 1.7891,
"step": 200500
},
{
"epoch": 0.87,
"learning_rate": 3.5474002801132596e-05,
"loss": 1.7417,
"step": 201000
},
{
"epoch": 0.87,
"learning_rate": 3.543786847974238e-05,
"loss": 1.7883,
"step": 201500
},
{
"epoch": 0.88,
"learning_rate": 3.540173415835216e-05,
"loss": 1.7517,
"step": 202000
},
{
"epoch": 0.88,
"learning_rate": 3.5365599836961945e-05,
"loss": 1.7404,
"step": 202500
},
{
"epoch": 0.88,
"learning_rate": 3.532946551557172e-05,
"loss": 1.7348,
"step": 203000
},
{
"epoch": 0.88,
"learning_rate": 3.529333119418151e-05,
"loss": 1.7215,
"step": 203500
},
{
"epoch": 0.88,
"learning_rate": 3.5257196872791295e-05,
"loss": 1.7298,
"step": 204000
},
{
"epoch": 0.89,
"learning_rate": 3.522106255140107e-05,
"loss": 1.7522,
"step": 204500
},
{
"epoch": 0.89,
"learning_rate": 3.5184928230010854e-05,
"loss": 1.7715,
"step": 205000
},
{
"epoch": 0.89,
"learning_rate": 3.514879390862064e-05,
"loss": 1.7939,
"step": 205500
},
{
"epoch": 0.89,
"learning_rate": 3.511265958723042e-05,
"loss": 1.7658,
"step": 206000
},
{
"epoch": 0.9,
"learning_rate": 3.50765252658402e-05,
"loss": 1.7893,
"step": 206500
},
{
"epoch": 0.9,
"learning_rate": 3.5040390944449986e-05,
"loss": 1.7972,
"step": 207000
},
{
"epoch": 0.9,
"learning_rate": 3.500425662305977e-05,
"loss": 1.7513,
"step": 207500
},
{
"epoch": 0.9,
"learning_rate": 3.496812230166955e-05,
"loss": 1.7363,
"step": 208000
},
{
"epoch": 0.9,
"learning_rate": 3.4931987980279336e-05,
"loss": 1.7488,
"step": 208500
},
{
"epoch": 0.91,
"learning_rate": 3.489585365888912e-05,
"loss": 1.7684,
"step": 209000
},
{
"epoch": 0.91,
"learning_rate": 3.4859719337498895e-05,
"loss": 1.7595,
"step": 209500
},
{
"epoch": 0.91,
"learning_rate": 3.4823585016108685e-05,
"loss": 1.7139,
"step": 210000
},
{
"epoch": 0.91,
"learning_rate": 3.478745069471847e-05,
"loss": 1.7581,
"step": 210500
},
{
"epoch": 0.91,
"learning_rate": 3.4751316373328244e-05,
"loss": 1.7617,
"step": 211000
},
{
"epoch": 0.92,
"learning_rate": 3.471518205193803e-05,
"loss": 1.7671,
"step": 211500
},
{
"epoch": 0.92,
"learning_rate": 3.467904773054782e-05,
"loss": 1.7444,
"step": 212000
},
{
"epoch": 0.92,
"learning_rate": 3.4642913409157594e-05,
"loss": 1.7269,
"step": 212500
},
{
"epoch": 0.92,
"learning_rate": 3.460677908776738e-05,
"loss": 1.7386,
"step": 213000
},
{
"epoch": 0.93,
"learning_rate": 3.457064476637716e-05,
"loss": 1.7411,
"step": 213500
},
{
"epoch": 0.93,
"learning_rate": 3.453451044498694e-05,
"loss": 1.7478,
"step": 214000
},
{
"epoch": 0.93,
"learning_rate": 3.4498376123596726e-05,
"loss": 1.7114,
"step": 214500
},
{
"epoch": 0.93,
"learning_rate": 3.446224180220651e-05,
"loss": 1.7268,
"step": 215000
},
{
"epoch": 0.93,
"learning_rate": 3.4426107480816285e-05,
"loss": 1.7231,
"step": 215500
},
{
"epoch": 0.94,
"learning_rate": 3.4389973159426075e-05,
"loss": 1.7137,
"step": 216000
},
{
"epoch": 0.94,
"learning_rate": 3.435383883803586e-05,
"loss": 1.7475,
"step": 216500
},
{
"epoch": 0.94,
"learning_rate": 3.4317704516645635e-05,
"loss": 1.7628,
"step": 217000
},
{
"epoch": 0.94,
"learning_rate": 3.428157019525542e-05,
"loss": 1.7537,
"step": 217500
},
{
"epoch": 0.95,
"learning_rate": 3.424543587386521e-05,
"loss": 1.7167,
"step": 218000
},
{
"epoch": 0.95,
"learning_rate": 3.4209301552474984e-05,
"loss": 1.7015,
"step": 218500
},
{
"epoch": 0.95,
"learning_rate": 3.417316723108477e-05,
"loss": 1.705,
"step": 219000
},
{
"epoch": 0.95,
"learning_rate": 3.413703290969455e-05,
"loss": 1.7548,
"step": 219500
},
{
"epoch": 0.95,
"learning_rate": 3.410089858830433e-05,
"loss": 1.7744,
"step": 220000
},
{
"epoch": 0.96,
"learning_rate": 3.4064764266914116e-05,
"loss": 1.7481,
"step": 220500
},
{
"epoch": 0.96,
"learning_rate": 3.40286299455239e-05,
"loss": 1.7105,
"step": 221000
},
{
"epoch": 0.96,
"learning_rate": 3.399249562413368e-05,
"loss": 1.7394,
"step": 221500
},
{
"epoch": 0.96,
"learning_rate": 3.395636130274346e-05,
"loss": 1.7356,
"step": 222000
},
{
"epoch": 0.96,
"learning_rate": 3.392022698135325e-05,
"loss": 1.7341,
"step": 222500
},
{
"epoch": 0.97,
"learning_rate": 3.388409265996303e-05,
"loss": 1.7628,
"step": 223000
},
{
"epoch": 0.97,
"learning_rate": 3.384795833857281e-05,
"loss": 1.7174,
"step": 223500
},
{
"epoch": 0.97,
"learning_rate": 3.381182401718259e-05,
"loss": 1.7154,
"step": 224000
},
{
"epoch": 0.97,
"learning_rate": 3.377568969579238e-05,
"loss": 1.713,
"step": 224500
},
{
"epoch": 0.98,
"learning_rate": 3.373955537440216e-05,
"loss": 1.6835,
"step": 225000
},
{
"epoch": 0.98,
"learning_rate": 3.370342105301194e-05,
"loss": 1.7391,
"step": 225500
},
{
"epoch": 0.98,
"learning_rate": 3.3667286731621724e-05,
"loss": 1.7753,
"step": 226000
},
{
"epoch": 0.98,
"learning_rate": 3.363115241023151e-05,
"loss": 1.7212,
"step": 226500
},
{
"epoch": 0.98,
"learning_rate": 3.359501808884129e-05,
"loss": 1.7298,
"step": 227000
},
{
"epoch": 0.99,
"learning_rate": 3.355888376745107e-05,
"loss": 1.739,
"step": 227500
},
{
"epoch": 0.99,
"learning_rate": 3.3522749446060856e-05,
"loss": 1.723,
"step": 228000
},
{
"epoch": 0.99,
"learning_rate": 3.348661512467064e-05,
"loss": 1.7261,
"step": 228500
},
{
"epoch": 0.99,
"learning_rate": 3.345048080328042e-05,
"loss": 1.7304,
"step": 229000
},
{
"epoch": 1.0,
"learning_rate": 3.34143464818902e-05,
"loss": 1.6555,
"step": 229500
},
{
"epoch": 1.0,
"learning_rate": 3.337821216049998e-05,
"loss": 1.7105,
"step": 230000
},
{
"epoch": 1.0,
"learning_rate": 3.334207783910977e-05,
"loss": 1.7542,
"step": 230500
},
{
"epoch": 1.0,
"learning_rate": 3.330594351771955e-05,
"loss": 1.6979,
"step": 231000
},
{
"epoch": 1.0,
"learning_rate": 3.326980919632933e-05,
"loss": 1.7105,
"step": 231500
},
{
"epoch": 1.01,
"learning_rate": 3.3233674874939114e-05,
"loss": 1.6445,
"step": 232000
},
{
"epoch": 1.01,
"learning_rate": 3.31975405535489e-05,
"loss": 1.6999,
"step": 232500
},
{
"epoch": 1.01,
"learning_rate": 3.316140623215868e-05,
"loss": 1.6993,
"step": 233000
},
{
"epoch": 1.01,
"learning_rate": 3.312527191076846e-05,
"loss": 1.6856,
"step": 233500
},
{
"epoch": 1.01,
"learning_rate": 3.3089137589378246e-05,
"loss": 1.6921,
"step": 234000
},
{
"epoch": 1.02,
"learning_rate": 3.305300326798803e-05,
"loss": 1.7265,
"step": 234500
},
{
"epoch": 1.02,
"learning_rate": 3.301686894659781e-05,
"loss": 1.6544,
"step": 235000
},
{
"epoch": 1.02,
"learning_rate": 3.2980734625207596e-05,
"loss": 1.7304,
"step": 235500
},
{
"epoch": 1.02,
"learning_rate": 3.294460030381737e-05,
"loss": 1.683,
"step": 236000
},
{
"epoch": 1.03,
"learning_rate": 3.2908465982427155e-05,
"loss": 1.7204,
"step": 236500
},
{
"epoch": 1.03,
"learning_rate": 3.2872331661036945e-05,
"loss": 1.7507,
"step": 237000
},
{
"epoch": 1.03,
"learning_rate": 3.283619733964672e-05,
"loss": 1.6769,
"step": 237500
},
{
"epoch": 1.03,
"learning_rate": 3.2800063018256504e-05,
"loss": 1.7191,
"step": 238000
},
{
"epoch": 1.03,
"learning_rate": 3.276392869686629e-05,
"loss": 1.6975,
"step": 238500
},
{
"epoch": 1.04,
"learning_rate": 3.272779437547607e-05,
"loss": 1.6835,
"step": 239000
},
{
"epoch": 1.04,
"learning_rate": 3.2691660054085854e-05,
"loss": 1.6927,
"step": 239500
},
{
"epoch": 1.04,
"learning_rate": 3.265552573269564e-05,
"loss": 1.6967,
"step": 240000
},
{
"epoch": 1.04,
"learning_rate": 3.261939141130542e-05,
"loss": 1.7397,
"step": 240500
},
{
"epoch": 1.05,
"learning_rate": 3.25832570899152e-05,
"loss": 1.74,
"step": 241000
},
{
"epoch": 1.05,
"learning_rate": 3.2547122768524986e-05,
"loss": 1.6969,
"step": 241500
},
{
"epoch": 1.05,
"learning_rate": 3.251098844713477e-05,
"loss": 1.6809,
"step": 242000
},
{
"epoch": 1.05,
"learning_rate": 3.2474854125744545e-05,
"loss": 1.674,
"step": 242500
},
{
"epoch": 1.05,
"learning_rate": 3.2438719804354335e-05,
"loss": 1.672,
"step": 243000
},
{
"epoch": 1.06,
"learning_rate": 3.240258548296412e-05,
"loss": 1.7377,
"step": 243500
},
{
"epoch": 1.06,
"learning_rate": 3.2366451161573895e-05,
"loss": 1.7237,
"step": 244000
},
{
"epoch": 1.06,
"learning_rate": 3.233031684018368e-05,
"loss": 1.6982,
"step": 244500
},
{
"epoch": 1.06,
"learning_rate": 3.229418251879347e-05,
"loss": 1.6938,
"step": 245000
},
{
"epoch": 1.06,
"learning_rate": 3.2258048197403244e-05,
"loss": 1.665,
"step": 245500
},
{
"epoch": 1.07,
"learning_rate": 3.222191387601303e-05,
"loss": 1.7151,
"step": 246000
},
{
"epoch": 1.07,
"learning_rate": 3.218577955462281e-05,
"loss": 1.7028,
"step": 246500
},
{
"epoch": 1.07,
"learning_rate": 3.214964523323259e-05,
"loss": 1.7277,
"step": 247000
},
{
"epoch": 1.07,
"learning_rate": 3.2113510911842376e-05,
"loss": 1.7078,
"step": 247500
},
{
"epoch": 1.08,
"learning_rate": 3.207737659045216e-05,
"loss": 1.7049,
"step": 248000
},
{
"epoch": 1.08,
"learning_rate": 3.2041242269061936e-05,
"loss": 1.6905,
"step": 248500
},
{
"epoch": 1.08,
"learning_rate": 3.2005107947671726e-05,
"loss": 1.6697,
"step": 249000
},
{
"epoch": 1.08,
"learning_rate": 3.196897362628151e-05,
"loss": 1.6782,
"step": 249500
},
{
"epoch": 1.08,
"learning_rate": 3.1932839304891285e-05,
"loss": 1.7029,
"step": 250000
},
{
"epoch": 1.09,
"learning_rate": 3.189670498350107e-05,
"loss": 1.6552,
"step": 250500
},
{
"epoch": 1.09,
"learning_rate": 3.186057066211086e-05,
"loss": 1.7048,
"step": 251000
},
{
"epoch": 1.09,
"learning_rate": 3.1824436340720634e-05,
"loss": 1.6952,
"step": 251500
},
{
"epoch": 1.09,
"learning_rate": 3.178830201933042e-05,
"loss": 1.6739,
"step": 252000
},
{
"epoch": 1.09,
"learning_rate": 3.17521676979402e-05,
"loss": 1.684,
"step": 252500
},
{
"epoch": 1.1,
"learning_rate": 3.1716033376549984e-05,
"loss": 1.68,
"step": 253000
},
{
"epoch": 1.1,
"learning_rate": 3.167989905515977e-05,
"loss": 1.6553,
"step": 253500
},
{
"epoch": 1.1,
"learning_rate": 3.164376473376955e-05,
"loss": 1.6784,
"step": 254000
},
{
"epoch": 1.1,
"learning_rate": 3.160763041237933e-05,
"loss": 1.7055,
"step": 254500
},
{
"epoch": 1.11,
"learning_rate": 3.157149609098911e-05,
"loss": 1.6762,
"step": 255000
},
{
"epoch": 1.11,
"learning_rate": 3.15353617695989e-05,
"loss": 1.7085,
"step": 255500
},
{
"epoch": 1.11,
"learning_rate": 3.149922744820868e-05,
"loss": 1.6958,
"step": 256000
},
{
"epoch": 1.11,
"learning_rate": 3.146309312681846e-05,
"loss": 1.6795,
"step": 256500
},
{
"epoch": 1.11,
"learning_rate": 3.142695880542824e-05,
"loss": 1.6779,
"step": 257000
},
{
"epoch": 1.12,
"learning_rate": 3.139082448403803e-05,
"loss": 1.6951,
"step": 257500
},
{
"epoch": 1.12,
"learning_rate": 3.135469016264781e-05,
"loss": 1.6731,
"step": 258000
},
{
"epoch": 1.12,
"learning_rate": 3.131855584125759e-05,
"loss": 1.704,
"step": 258500
},
{
"epoch": 1.12,
"learning_rate": 3.1282421519867374e-05,
"loss": 1.6642,
"step": 259000
},
{
"epoch": 1.13,
"learning_rate": 3.124628719847716e-05,
"loss": 1.6902,
"step": 259500
},
{
"epoch": 1.13,
"learning_rate": 3.121015287708694e-05,
"loss": 1.6541,
"step": 260000
},
{
"epoch": 1.13,
"learning_rate": 3.117401855569672e-05,
"loss": 1.712,
"step": 260500
},
{
"epoch": 1.13,
"learning_rate": 3.11378842343065e-05,
"loss": 1.702,
"step": 261000
},
{
"epoch": 1.13,
"learning_rate": 3.110174991291629e-05,
"loss": 1.6944,
"step": 261500
},
{
"epoch": 1.14,
"learning_rate": 3.106561559152607e-05,
"loss": 1.701,
"step": 262000
},
{
"epoch": 1.14,
"learning_rate": 3.102948127013585e-05,
"loss": 1.7197,
"step": 262500
},
{
"epoch": 1.14,
"learning_rate": 3.099334694874563e-05,
"loss": 1.6948,
"step": 263000
},
{
"epoch": 1.14,
"learning_rate": 3.095721262735542e-05,
"loss": 1.6968,
"step": 263500
},
{
"epoch": 1.14,
"learning_rate": 3.09210783059652e-05,
"loss": 1.7315,
"step": 264000
},
{
"epoch": 1.15,
"learning_rate": 3.088494398457498e-05,
"loss": 1.7067,
"step": 264500
},
{
"epoch": 1.15,
"learning_rate": 3.0848809663184764e-05,
"loss": 1.7057,
"step": 265000
},
{
"epoch": 1.15,
"learning_rate": 3.081267534179455e-05,
"loss": 1.7043,
"step": 265500
},
{
"epoch": 1.15,
"learning_rate": 3.077654102040433e-05,
"loss": 1.6902,
"step": 266000
},
{
"epoch": 1.16,
"learning_rate": 3.0740406699014114e-05,
"loss": 1.7088,
"step": 266500
},
{
"epoch": 1.16,
"learning_rate": 3.07042723776239e-05,
"loss": 1.6449,
"step": 267000
},
{
"epoch": 1.16,
"learning_rate": 3.066813805623367e-05,
"loss": 1.674,
"step": 267500
},
{
"epoch": 1.16,
"learning_rate": 3.063200373484346e-05,
"loss": 1.6666,
"step": 268000
},
{
"epoch": 1.16,
"learning_rate": 3.0595869413453246e-05,
"loss": 1.671,
"step": 268500
},
{
"epoch": 1.17,
"learning_rate": 3.055973509206302e-05,
"loss": 1.669,
"step": 269000
},
{
"epoch": 1.17,
"learning_rate": 3.0523600770672805e-05,
"loss": 1.682,
"step": 269500
},
{
"epoch": 1.17,
"learning_rate": 3.0487466449282592e-05,
"loss": 1.6672,
"step": 270000
},
{
"epoch": 1.17,
"learning_rate": 3.0451332127892375e-05,
"loss": 1.6511,
"step": 270500
},
{
"epoch": 1.18,
"learning_rate": 3.0415197806502155e-05,
"loss": 1.6438,
"step": 271000
},
{
"epoch": 1.18,
"learning_rate": 3.0379063485111934e-05,
"loss": 1.6543,
"step": 271500
},
{
"epoch": 1.18,
"learning_rate": 3.0342929163721724e-05,
"loss": 1.6192,
"step": 272000
},
{
"epoch": 1.18,
"learning_rate": 3.0306794842331504e-05,
"loss": 1.6534,
"step": 272500
},
{
"epoch": 1.18,
"learning_rate": 3.0270660520941284e-05,
"loss": 1.6818,
"step": 273000
},
{
"epoch": 1.19,
"learning_rate": 3.0234526199551067e-05,
"loss": 1.6893,
"step": 273500
},
{
"epoch": 1.19,
"learning_rate": 3.0198391878160853e-05,
"loss": 1.6608,
"step": 274000
},
{
"epoch": 1.19,
"learning_rate": 3.0162257556770633e-05,
"loss": 1.6699,
"step": 274500
},
{
"epoch": 1.19,
"learning_rate": 3.0126123235380416e-05,
"loss": 1.6474,
"step": 275000
},
{
"epoch": 1.19,
"learning_rate": 3.0089988913990196e-05,
"loss": 1.6208,
"step": 275500
},
{
"epoch": 1.2,
"learning_rate": 3.0053854592599982e-05,
"loss": 1.6208,
"step": 276000
},
{
"epoch": 1.2,
"learning_rate": 3.0017720271209765e-05,
"loss": 1.6492,
"step": 276500
},
{
"epoch": 1.2,
"learning_rate": 2.9981585949819545e-05,
"loss": 1.692,
"step": 277000
},
{
"epoch": 1.2,
"learning_rate": 2.9945451628429328e-05,
"loss": 1.6518,
"step": 277500
},
{
"epoch": 1.21,
"learning_rate": 2.9909317307039115e-05,
"loss": 1.6715,
"step": 278000
},
{
"epoch": 1.21,
"learning_rate": 2.9873182985648894e-05,
"loss": 1.6603,
"step": 278500
},
{
"epoch": 1.21,
"learning_rate": 2.9837048664258677e-05,
"loss": 1.6928,
"step": 279000
},
{
"epoch": 1.21,
"learning_rate": 2.9800914342868457e-05,
"loss": 1.662,
"step": 279500
},
{
"epoch": 1.21,
"learning_rate": 2.9764780021478244e-05,
"loss": 1.6472,
"step": 280000
},
{
"epoch": 1.22,
"learning_rate": 2.9728645700088027e-05,
"loss": 1.684,
"step": 280500
},
{
"epoch": 1.22,
"learning_rate": 2.9692511378697806e-05,
"loss": 1.6837,
"step": 281000
},
{
"epoch": 1.22,
"learning_rate": 2.965637705730759e-05,
"loss": 1.6324,
"step": 281500
},
{
"epoch": 1.22,
"learning_rate": 2.9620242735917376e-05,
"loss": 1.7038,
"step": 282000
},
{
"epoch": 1.22,
"learning_rate": 2.9584108414527156e-05,
"loss": 1.6556,
"step": 282500
},
{
"epoch": 1.23,
"learning_rate": 2.954797409313694e-05,
"loss": 1.6356,
"step": 283000
},
{
"epoch": 1.23,
"learning_rate": 2.951183977174672e-05,
"loss": 1.6846,
"step": 283500
},
{
"epoch": 1.23,
"learning_rate": 2.94757054503565e-05,
"loss": 1.6672,
"step": 284000
},
{
"epoch": 1.23,
"learning_rate": 2.9439571128966288e-05,
"loss": 1.6782,
"step": 284500
},
{
"epoch": 1.24,
"learning_rate": 2.9403436807576068e-05,
"loss": 1.6251,
"step": 285000
},
{
"epoch": 1.24,
"learning_rate": 2.936730248618585e-05,
"loss": 1.627,
"step": 285500
},
{
"epoch": 1.24,
"learning_rate": 2.933116816479563e-05,
"loss": 1.642,
"step": 286000
},
{
"epoch": 1.24,
"learning_rate": 2.9295033843405417e-05,
"loss": 1.6834,
"step": 286500
},
{
"epoch": 1.24,
"learning_rate": 2.92588995220152e-05,
"loss": 1.635,
"step": 287000
},
{
"epoch": 1.25,
"learning_rate": 2.922276520062498e-05,
"loss": 1.6538,
"step": 287500
},
{
"epoch": 1.25,
"learning_rate": 2.918663087923476e-05,
"loss": 1.657,
"step": 288000
},
{
"epoch": 1.25,
"learning_rate": 2.915049655784455e-05,
"loss": 1.6776,
"step": 288500
},
{
"epoch": 1.25,
"learning_rate": 2.911436223645433e-05,
"loss": 1.6439,
"step": 289000
},
{
"epoch": 1.26,
"learning_rate": 2.907822791506411e-05,
"loss": 1.6726,
"step": 289500
},
{
"epoch": 1.26,
"learning_rate": 2.9042093593673892e-05,
"loss": 1.6613,
"step": 290000
},
{
"epoch": 1.26,
"learning_rate": 2.900595927228368e-05,
"loss": 1.6745,
"step": 290500
},
{
"epoch": 1.26,
"learning_rate": 2.8969824950893458e-05,
"loss": 1.6323,
"step": 291000
},
{
"epoch": 1.26,
"learning_rate": 2.893369062950324e-05,
"loss": 1.6773,
"step": 291500
},
{
"epoch": 1.27,
"learning_rate": 2.889755630811302e-05,
"loss": 1.6605,
"step": 292000
},
{
"epoch": 1.27,
"learning_rate": 2.8861421986722807e-05,
"loss": 1.623,
"step": 292500
},
{
"epoch": 1.27,
"learning_rate": 2.882528766533259e-05,
"loss": 1.6681,
"step": 293000
},
{
"epoch": 1.27,
"learning_rate": 2.878915334394237e-05,
"loss": 1.6331,
"step": 293500
},
{
"epoch": 1.27,
"learning_rate": 2.8753019022552153e-05,
"loss": 1.6713,
"step": 294000
},
{
"epoch": 1.28,
"learning_rate": 2.871688470116194e-05,
"loss": 1.66,
"step": 294500
},
{
"epoch": 1.28,
"learning_rate": 2.868075037977172e-05,
"loss": 1.6349,
"step": 295000
},
{
"epoch": 1.28,
"learning_rate": 2.8644616058381503e-05,
"loss": 1.6145,
"step": 295500
},
{
"epoch": 1.28,
"learning_rate": 2.8608481736991282e-05,
"loss": 1.6918,
"step": 296000
},
{
"epoch": 1.29,
"learning_rate": 2.857234741560107e-05,
"loss": 1.6269,
"step": 296500
},
{
"epoch": 1.29,
"learning_rate": 2.8536213094210852e-05,
"loss": 1.6511,
"step": 297000
},
{
"epoch": 1.29,
"learning_rate": 2.850007877282063e-05,
"loss": 1.6606,
"step": 297500
},
{
"epoch": 1.29,
"learning_rate": 2.8463944451430415e-05,
"loss": 1.6842,
"step": 298000
},
{
"epoch": 1.29,
"learning_rate": 2.8427810130040194e-05,
"loss": 1.6416,
"step": 298500
},
{
"epoch": 1.3,
"learning_rate": 2.839167580864998e-05,
"loss": 1.6985,
"step": 299000
},
{
"epoch": 1.3,
"learning_rate": 2.8355541487259764e-05,
"loss": 1.656,
"step": 299500
},
{
"epoch": 1.3,
"learning_rate": 2.8319407165869544e-05,
"loss": 1.6255,
"step": 300000
},
{
"epoch": 1.3,
"learning_rate": 2.8283272844479323e-05,
"loss": 1.6282,
"step": 300500
},
{
"epoch": 1.31,
"learning_rate": 2.8247138523089113e-05,
"loss": 1.6374,
"step": 301000
},
{
"epoch": 1.31,
"learning_rate": 2.8211004201698893e-05,
"loss": 1.6097,
"step": 301500
},
{
"epoch": 1.31,
"learning_rate": 2.8174869880308673e-05,
"loss": 1.6067,
"step": 302000
},
{
"epoch": 1.31,
"learning_rate": 2.8138735558918456e-05,
"loss": 1.6417,
"step": 302500
},
{
"epoch": 1.31,
"learning_rate": 2.8102601237528242e-05,
"loss": 1.6705,
"step": 303000
},
{
"epoch": 1.32,
"learning_rate": 2.8066466916138022e-05,
"loss": 1.6531,
"step": 303500
},
{
"epoch": 1.32,
"learning_rate": 2.8030332594747805e-05,
"loss": 1.6282,
"step": 304000
},
{
"epoch": 1.32,
"learning_rate": 2.7994198273357585e-05,
"loss": 1.6361,
"step": 304500
},
{
"epoch": 1.32,
"learning_rate": 2.795806395196737e-05,
"loss": 1.6682,
"step": 305000
},
{
"epoch": 1.32,
"learning_rate": 2.7921929630577154e-05,
"loss": 1.5798,
"step": 305500
},
{
"epoch": 1.33,
"learning_rate": 2.7885795309186934e-05,
"loss": 1.6414,
"step": 306000
},
{
"epoch": 1.33,
"learning_rate": 2.7849660987796717e-05,
"loss": 1.6428,
"step": 306500
},
{
"epoch": 1.33,
"learning_rate": 2.7813526666406504e-05,
"loss": 1.6403,
"step": 307000
},
{
"epoch": 1.33,
"learning_rate": 2.7777392345016283e-05,
"loss": 1.6357,
"step": 307500
},
{
"epoch": 1.34,
"learning_rate": 2.7741258023626066e-05,
"loss": 1.6039,
"step": 308000
},
{
"epoch": 1.34,
"learning_rate": 2.7705123702235846e-05,
"loss": 1.619,
"step": 308500
},
{
"epoch": 1.34,
"learning_rate": 2.7668989380845633e-05,
"loss": 1.6513,
"step": 309000
},
{
"epoch": 1.34,
"learning_rate": 2.7632855059455416e-05,
"loss": 1.6732,
"step": 309500
},
{
"epoch": 1.34,
"learning_rate": 2.7596720738065195e-05,
"loss": 1.674,
"step": 310000
},
{
"epoch": 1.35,
"learning_rate": 2.756058641667498e-05,
"loss": 1.6321,
"step": 310500
},
{
"epoch": 1.35,
"learning_rate": 2.7524452095284765e-05,
"loss": 1.6681,
"step": 311000
},
{
"epoch": 1.35,
"learning_rate": 2.7488317773894545e-05,
"loss": 1.6434,
"step": 311500
},
{
"epoch": 1.35,
"learning_rate": 2.7452183452504328e-05,
"loss": 1.6551,
"step": 312000
},
{
"epoch": 1.36,
"learning_rate": 2.7416049131114107e-05,
"loss": 1.6468,
"step": 312500
},
{
"epoch": 1.36,
"learning_rate": 2.7379914809723894e-05,
"loss": 1.6349,
"step": 313000
},
{
"epoch": 1.36,
"learning_rate": 2.7343780488333677e-05,
"loss": 1.6371,
"step": 313500
},
{
"epoch": 1.36,
"learning_rate": 2.7307646166943457e-05,
"loss": 1.5933,
"step": 314000
},
{
"epoch": 1.36,
"learning_rate": 2.727151184555324e-05,
"loss": 1.6186,
"step": 314500
},
{
"epoch": 1.37,
"learning_rate": 2.723537752416302e-05,
"loss": 1.6484,
"step": 315000
},
{
"epoch": 1.37,
"learning_rate": 2.7199243202772806e-05,
"loss": 1.6024,
"step": 315500
},
{
"epoch": 1.37,
"learning_rate": 2.7163108881382586e-05,
"loss": 1.6102,
"step": 316000
},
{
"epoch": 1.37,
"learning_rate": 2.712697455999237e-05,
"loss": 1.6002,
"step": 316500
},
{
"epoch": 1.37,
"learning_rate": 2.709084023860215e-05,
"loss": 1.6381,
"step": 317000
},
{
"epoch": 1.38,
"learning_rate": 2.7054705917211935e-05,
"loss": 1.6088,
"step": 317500
},
{
"epoch": 1.38,
"learning_rate": 2.7018571595821718e-05,
"loss": 1.6108,
"step": 318000
},
{
"epoch": 1.38,
"learning_rate": 2.6982437274431498e-05,
"loss": 1.6222,
"step": 318500
},
{
"epoch": 1.38,
"learning_rate": 2.694630295304128e-05,
"loss": 1.6422,
"step": 319000
},
{
"epoch": 1.39,
"learning_rate": 2.6910168631651067e-05,
"loss": 1.6483,
"step": 319500
},
{
"epoch": 1.39,
"learning_rate": 2.6874034310260847e-05,
"loss": 1.5779,
"step": 320000
},
{
"epoch": 1.39,
"learning_rate": 2.683789998887063e-05,
"loss": 1.6302,
"step": 320500
},
{
"epoch": 1.39,
"learning_rate": 2.680176566748041e-05,
"loss": 1.6199,
"step": 321000
},
{
"epoch": 1.39,
"learning_rate": 2.6765631346090196e-05,
"loss": 1.6147,
"step": 321500
},
{
"epoch": 1.4,
"learning_rate": 2.672949702469998e-05,
"loss": 1.6335,
"step": 322000
},
{
"epoch": 1.4,
"learning_rate": 2.669336270330976e-05,
"loss": 1.6021,
"step": 322500
},
{
"epoch": 1.4,
"learning_rate": 2.6657228381919542e-05,
"loss": 1.6145,
"step": 323000
},
{
"epoch": 1.4,
"learning_rate": 2.662109406052933e-05,
"loss": 1.6376,
"step": 323500
},
{
"epoch": 1.4,
"learning_rate": 2.658495973913911e-05,
"loss": 1.5844,
"step": 324000
},
{
"epoch": 1.41,
"learning_rate": 2.654882541774889e-05,
"loss": 1.6192,
"step": 324500
},
{
"epoch": 1.41,
"learning_rate": 2.651269109635867e-05,
"loss": 1.621,
"step": 325000
},
{
"epoch": 1.41,
"learning_rate": 2.6476556774968458e-05,
"loss": 1.5913,
"step": 325500
},
{
"epoch": 1.41,
"learning_rate": 2.644042245357824e-05,
"loss": 1.5939,
"step": 326000
},
{
"epoch": 1.42,
"learning_rate": 2.640428813218802e-05,
"loss": 1.6107,
"step": 326500
},
{
"epoch": 1.42,
"learning_rate": 2.6368153810797804e-05,
"loss": 1.6015,
"step": 327000
},
{
"epoch": 1.42,
"learning_rate": 2.633201948940759e-05,
"loss": 1.6209,
"step": 327500
},
{
"epoch": 1.42,
"learning_rate": 2.629588516801737e-05,
"loss": 1.6385,
"step": 328000
},
{
"epoch": 1.42,
"learning_rate": 2.6259750846627153e-05,
"loss": 1.624,
"step": 328500
},
{
"epoch": 1.43,
"learning_rate": 2.6223616525236933e-05,
"loss": 1.6466,
"step": 329000
},
{
"epoch": 1.43,
"learning_rate": 2.6187482203846712e-05,
"loss": 1.6577,
"step": 329500
},
{
"epoch": 1.43,
"learning_rate": 2.6151347882456502e-05,
"loss": 1.6463,
"step": 330000
},
{
"epoch": 1.43,
"learning_rate": 2.6115213561066282e-05,
"loss": 1.5799,
"step": 330500
},
{
"epoch": 1.44,
"learning_rate": 2.607907923967606e-05,
"loss": 1.6057,
"step": 331000
},
{
"epoch": 1.44,
"learning_rate": 2.6042944918285845e-05,
"loss": 1.5531,
"step": 331500
},
{
"epoch": 1.44,
"learning_rate": 2.600681059689563e-05,
"loss": 1.6361,
"step": 332000
},
{
"epoch": 1.44,
"learning_rate": 2.597067627550541e-05,
"loss": 1.565,
"step": 332500
},
{
"epoch": 1.44,
"learning_rate": 2.5934541954115194e-05,
"loss": 1.5786,
"step": 333000
},
{
"epoch": 1.45,
"learning_rate": 2.5898407632724974e-05,
"loss": 1.6438,
"step": 333500
},
{
"epoch": 1.45,
"learning_rate": 2.586227331133476e-05,
"loss": 1.5995,
"step": 334000
},
{
"epoch": 1.45,
"learning_rate": 2.5826138989944543e-05,
"loss": 1.5987,
"step": 334500
},
{
"epoch": 1.45,
"learning_rate": 2.5790004668554323e-05,
"loss": 1.6033,
"step": 335000
},
{
"epoch": 1.45,
"learning_rate": 2.5753870347164106e-05,
"loss": 1.6203,
"step": 335500
},
{
"epoch": 1.46,
"learning_rate": 2.5717736025773892e-05,
"loss": 1.5875,
"step": 336000
},
{
"epoch": 1.46,
"learning_rate": 2.5681601704383672e-05,
"loss": 1.5942,
"step": 336500
},
{
"epoch": 1.46,
"learning_rate": 2.5645467382993455e-05,
"loss": 1.6057,
"step": 337000
},
{
"epoch": 1.46,
"learning_rate": 2.5609333061603235e-05,
"loss": 1.6015,
"step": 337500
},
{
"epoch": 1.47,
"learning_rate": 2.557319874021302e-05,
"loss": 1.632,
"step": 338000
},
{
"epoch": 1.47,
"learning_rate": 2.5537064418822805e-05,
"loss": 1.6149,
"step": 338500
},
{
"epoch": 1.47,
"learning_rate": 2.5500930097432584e-05,
"loss": 1.5971,
"step": 339000
},
{
"epoch": 1.47,
"learning_rate": 2.5464795776042367e-05,
"loss": 1.5524,
"step": 339500
},
{
"epoch": 1.47,
"learning_rate": 2.5428661454652154e-05,
"loss": 1.6095,
"step": 340000
},
{
"epoch": 1.48,
"learning_rate": 2.5392527133261934e-05,
"loss": 1.5737,
"step": 340500
},
{
"epoch": 1.48,
"learning_rate": 2.5356392811871717e-05,
"loss": 1.5917,
"step": 341000
},
{
"epoch": 1.48,
"learning_rate": 2.5320258490481496e-05,
"loss": 1.6022,
"step": 341500
},
{
"epoch": 1.48,
"learning_rate": 2.5284124169091283e-05,
"loss": 1.6097,
"step": 342000
},
{
"epoch": 1.49,
"learning_rate": 2.5247989847701066e-05,
"loss": 1.5965,
"step": 342500
},
{
"epoch": 1.49,
"learning_rate": 2.5211855526310846e-05,
"loss": 1.6415,
"step": 343000
},
{
"epoch": 1.49,
"learning_rate": 2.5175721204920625e-05,
"loss": 1.5745,
"step": 343500
},
{
"epoch": 1.49,
"learning_rate": 2.5139586883530415e-05,
"loss": 1.5646,
"step": 344000
},
{
"epoch": 1.49,
"learning_rate": 2.5103452562140195e-05,
"loss": 1.5929,
"step": 344500
},
{
"epoch": 1.5,
"learning_rate": 2.5067318240749975e-05,
"loss": 1.609,
"step": 345000
},
{
"epoch": 1.5,
"learning_rate": 2.5031183919359758e-05,
"loss": 1.574,
"step": 345500
},
{
"epoch": 1.5,
"learning_rate": 2.499504959796954e-05,
"loss": 1.575,
"step": 346000
},
{
"epoch": 1.5,
"learning_rate": 2.4958915276579324e-05,
"loss": 1.5967,
"step": 346500
},
{
"epoch": 1.5,
"learning_rate": 2.4922780955189107e-05,
"loss": 1.5799,
"step": 347000
},
{
"epoch": 1.51,
"learning_rate": 2.4886646633798887e-05,
"loss": 1.5616,
"step": 347500
},
{
"epoch": 1.51,
"learning_rate": 2.4850512312408673e-05,
"loss": 1.5752,
"step": 348000
},
{
"epoch": 1.51,
"learning_rate": 2.4814377991018453e-05,
"loss": 1.6246,
"step": 348500
},
{
"epoch": 1.51,
"learning_rate": 2.4778243669628236e-05,
"loss": 1.592,
"step": 349000
},
{
"epoch": 1.52,
"learning_rate": 2.474210934823802e-05,
"loss": 1.5794,
"step": 349500
},
{
"epoch": 1.52,
"learning_rate": 2.4705975026847802e-05,
"loss": 1.5979,
"step": 350000
},
{
"epoch": 1.52,
"learning_rate": 2.4669840705457585e-05,
"loss": 1.6168,
"step": 350500
},
{
"epoch": 1.52,
"learning_rate": 2.463370638406737e-05,
"loss": 1.6053,
"step": 351000
},
{
"epoch": 1.52,
"learning_rate": 2.4597572062677148e-05,
"loss": 1.5586,
"step": 351500
},
{
"epoch": 1.53,
"learning_rate": 2.4561437741286935e-05,
"loss": 1.5682,
"step": 352000
},
{
"epoch": 1.53,
"learning_rate": 2.4525303419896714e-05,
"loss": 1.5928,
"step": 352500
},
{
"epoch": 1.53,
"learning_rate": 2.4489169098506497e-05,
"loss": 1.5969,
"step": 353000
},
{
"epoch": 1.53,
"learning_rate": 2.445303477711628e-05,
"loss": 1.6073,
"step": 353500
},
{
"epoch": 1.53,
"learning_rate": 2.4416900455726064e-05,
"loss": 1.5718,
"step": 354000
},
{
"epoch": 1.54,
"learning_rate": 2.4380766134335843e-05,
"loss": 1.5827,
"step": 354500
},
{
"epoch": 1.54,
"learning_rate": 2.434463181294563e-05,
"loss": 1.5744,
"step": 355000
},
{
"epoch": 1.54,
"learning_rate": 2.430849749155541e-05,
"loss": 1.5752,
"step": 355500
},
{
"epoch": 1.54,
"learning_rate": 2.4272363170165193e-05,
"loss": 1.6167,
"step": 356000
},
{
"epoch": 1.55,
"learning_rate": 2.4236228848774976e-05,
"loss": 1.6042,
"step": 356500
},
{
"epoch": 1.55,
"learning_rate": 2.420009452738476e-05,
"loss": 1.5933,
"step": 357000
},
{
"epoch": 1.55,
"learning_rate": 2.4163960205994542e-05,
"loss": 1.5544,
"step": 357500
},
{
"epoch": 1.55,
"learning_rate": 2.4127825884604325e-05,
"loss": 1.5629,
"step": 358000
},
{
"epoch": 1.55,
"learning_rate": 2.4091691563214105e-05,
"loss": 1.584,
"step": 358500
},
{
"epoch": 1.56,
"learning_rate": 2.405555724182389e-05,
"loss": 1.6006,
"step": 359000
},
{
"epoch": 1.56,
"learning_rate": 2.401942292043367e-05,
"loss": 1.5669,
"step": 359500
},
{
"epoch": 1.56,
"learning_rate": 2.3983288599043454e-05,
"loss": 1.5901,
"step": 360000
},
{
"epoch": 1.56,
"learning_rate": 2.3947154277653237e-05,
"loss": 1.5573,
"step": 360500
},
{
"epoch": 1.57,
"learning_rate": 2.3911019956263017e-05,
"loss": 1.6311,
"step": 361000
},
{
"epoch": 1.57,
"learning_rate": 2.38748856348728e-05,
"loss": 1.5877,
"step": 361500
},
{
"epoch": 1.57,
"learning_rate": 2.3838751313482583e-05,
"loss": 1.5926,
"step": 362000
},
{
"epoch": 1.57,
"learning_rate": 2.3802616992092366e-05,
"loss": 1.5801,
"step": 362500
},
{
"epoch": 1.57,
"learning_rate": 2.376648267070215e-05,
"loss": 1.5608,
"step": 363000
},
{
"epoch": 1.58,
"learning_rate": 2.3730348349311932e-05,
"loss": 1.5751,
"step": 363500
},
{
"epoch": 1.58,
"learning_rate": 2.3694214027921712e-05,
"loss": 1.5665,
"step": 364000
},
{
"epoch": 1.58,
"learning_rate": 2.36580797065315e-05,
"loss": 1.5489,
"step": 364500
},
{
"epoch": 1.58,
"learning_rate": 2.3621945385141278e-05,
"loss": 1.594,
"step": 365000
},
{
"epoch": 1.58,
"learning_rate": 2.358581106375106e-05,
"loss": 1.6077,
"step": 365500
},
{
"epoch": 1.59,
"learning_rate": 2.3549676742360844e-05,
"loss": 1.6038,
"step": 366000
},
{
"epoch": 1.59,
"learning_rate": 2.3513542420970627e-05,
"loss": 1.5906,
"step": 366500
},
{
"epoch": 1.59,
"learning_rate": 2.3477408099580407e-05,
"loss": 1.5739,
"step": 367000
},
{
"epoch": 1.59,
"learning_rate": 2.3441273778190194e-05,
"loss": 1.5923,
"step": 367500
},
{
"epoch": 1.6,
"learning_rate": 2.3405139456799973e-05,
"loss": 1.5309,
"step": 368000
},
{
"epoch": 1.6,
"learning_rate": 2.3369005135409756e-05,
"loss": 1.555,
"step": 368500
},
{
"epoch": 1.6,
"learning_rate": 2.333287081401954e-05,
"loss": 1.573,
"step": 369000
},
{
"epoch": 1.6,
"learning_rate": 2.3296736492629322e-05,
"loss": 1.5887,
"step": 369500
},
{
"epoch": 1.6,
"learning_rate": 2.3260602171239106e-05,
"loss": 1.5559,
"step": 370000
},
{
"epoch": 1.61,
"learning_rate": 2.322446784984889e-05,
"loss": 1.5287,
"step": 370500
},
{
"epoch": 1.61,
"learning_rate": 2.318833352845867e-05,
"loss": 1.6143,
"step": 371000
},
{
"epoch": 1.61,
"learning_rate": 2.3152199207068455e-05,
"loss": 1.6023,
"step": 371500
},
{
"epoch": 1.61,
"learning_rate": 2.3116064885678235e-05,
"loss": 1.5846,
"step": 372000
},
{
"epoch": 1.62,
"learning_rate": 2.3079930564288018e-05,
"loss": 1.6275,
"step": 372500
},
{
"epoch": 1.62,
"learning_rate": 2.30437962428978e-05,
"loss": 1.589,
"step": 373000
},
{
"epoch": 1.62,
"learning_rate": 2.3007661921507584e-05,
"loss": 1.582,
"step": 373500
},
{
"epoch": 1.62,
"learning_rate": 2.2971527600117364e-05,
"loss": 1.5769,
"step": 374000
},
{
"epoch": 1.62,
"learning_rate": 2.293539327872715e-05,
"loss": 1.5649,
"step": 374500
},
{
"epoch": 1.63,
"learning_rate": 2.289925895733693e-05,
"loss": 1.5886,
"step": 375000
},
{
"epoch": 1.63,
"learning_rate": 2.2863124635946713e-05,
"loss": 1.5533,
"step": 375500
},
{
"epoch": 1.63,
"learning_rate": 2.2826990314556496e-05,
"loss": 1.5223,
"step": 376000
},
{
"epoch": 1.63,
"learning_rate": 2.279085599316628e-05,
"loss": 1.5494,
"step": 376500
},
{
"epoch": 1.63,
"learning_rate": 2.2754721671776062e-05,
"loss": 1.5931,
"step": 377000
},
{
"epoch": 1.64,
"learning_rate": 2.2718587350385842e-05,
"loss": 1.5693,
"step": 377500
},
{
"epoch": 1.64,
"learning_rate": 2.2682453028995625e-05,
"loss": 1.5519,
"step": 378000
},
{
"epoch": 1.64,
"learning_rate": 2.2646318707605408e-05,
"loss": 1.582,
"step": 378500
},
{
"epoch": 1.64,
"learning_rate": 2.261018438621519e-05,
"loss": 1.5588,
"step": 379000
},
{
"epoch": 1.65,
"learning_rate": 2.2574050064824974e-05,
"loss": 1.5856,
"step": 379500
},
{
"epoch": 1.65,
"learning_rate": 2.2537915743434757e-05,
"loss": 1.5546,
"step": 380000
},
{
"epoch": 1.65,
"learning_rate": 2.2501781422044537e-05,
"loss": 1.5627,
"step": 380500
},
{
"epoch": 1.65,
"learning_rate": 2.246564710065432e-05,
"loss": 1.5559,
"step": 381000
},
{
"epoch": 1.65,
"learning_rate": 2.2429512779264103e-05,
"loss": 1.5878,
"step": 381500
},
{
"epoch": 1.66,
"learning_rate": 2.2393378457873886e-05,
"loss": 1.5342,
"step": 382000
},
{
"epoch": 1.66,
"learning_rate": 2.235724413648367e-05,
"loss": 1.5444,
"step": 382500
},
{
"epoch": 1.66,
"learning_rate": 2.2321109815093452e-05,
"loss": 1.5817,
"step": 383000
},
{
"epoch": 1.66,
"learning_rate": 2.2284975493703232e-05,
"loss": 1.5019,
"step": 383500
},
{
"epoch": 1.67,
"learning_rate": 2.224884117231302e-05,
"loss": 1.5444,
"step": 384000
},
{
"epoch": 1.67,
"learning_rate": 2.22127068509228e-05,
"loss": 1.5389,
"step": 384500
},
{
"epoch": 1.67,
"learning_rate": 2.217657252953258e-05,
"loss": 1.5955,
"step": 385000
},
{
"epoch": 1.67,
"learning_rate": 2.2140438208142365e-05,
"loss": 1.5355,
"step": 385500
},
{
"epoch": 1.67,
"learning_rate": 2.2104303886752148e-05,
"loss": 1.5472,
"step": 386000
},
{
"epoch": 1.68,
"learning_rate": 2.206816956536193e-05,
"loss": 1.5501,
"step": 386500
},
{
"epoch": 1.68,
"learning_rate": 2.2032035243971714e-05,
"loss": 1.5939,
"step": 387000
},
{
"epoch": 1.68,
"learning_rate": 2.1995900922581494e-05,
"loss": 1.5782,
"step": 387500
},
{
"epoch": 1.68,
"learning_rate": 2.195976660119128e-05,
"loss": 1.5557,
"step": 388000
},
{
"epoch": 1.68,
"learning_rate": 2.192363227980106e-05,
"loss": 1.5296,
"step": 388500
},
{
"epoch": 1.69,
"learning_rate": 2.1887497958410843e-05,
"loss": 1.5602,
"step": 389000
},
{
"epoch": 1.69,
"learning_rate": 2.1851363637020626e-05,
"loss": 1.577,
"step": 389500
},
{
"epoch": 1.69,
"learning_rate": 2.181522931563041e-05,
"loss": 1.5835,
"step": 390000
},
{
"epoch": 1.69,
"learning_rate": 2.177909499424019e-05,
"loss": 1.5543,
"step": 390500
},
{
"epoch": 1.7,
"learning_rate": 2.1742960672849975e-05,
"loss": 1.5327,
"step": 391000
},
{
"epoch": 1.7,
"learning_rate": 2.1706826351459755e-05,
"loss": 1.5545,
"step": 391500
},
{
"epoch": 1.7,
"learning_rate": 2.1670692030069538e-05,
"loss": 1.5505,
"step": 392000
},
{
"epoch": 1.7,
"learning_rate": 2.163455770867932e-05,
"loss": 1.5299,
"step": 392500
},
{
"epoch": 1.7,
"learning_rate": 2.15984233872891e-05,
"loss": 1.5943,
"step": 393000
},
{
"epoch": 1.71,
"learning_rate": 2.1562289065898887e-05,
"loss": 1.5031,
"step": 393500
},
{
"epoch": 1.71,
"learning_rate": 2.1526154744508667e-05,
"loss": 1.5635,
"step": 394000
},
{
"epoch": 1.71,
"learning_rate": 2.149002042311845e-05,
"loss": 1.556,
"step": 394500
},
{
"epoch": 1.71,
"learning_rate": 2.1453886101728233e-05,
"loss": 1.5528,
"step": 395000
},
{
"epoch": 1.71,
"learning_rate": 2.1417751780338016e-05,
"loss": 1.5574,
"step": 395500
},
{
"epoch": 1.72,
"learning_rate": 2.1381617458947796e-05,
"loss": 1.5438,
"step": 396000
},
{
"epoch": 1.72,
"learning_rate": 2.1345483137557582e-05,
"loss": 1.5584,
"step": 396500
},
{
"epoch": 1.72,
"learning_rate": 2.1309348816167362e-05,
"loss": 1.5397,
"step": 397000
},
{
"epoch": 1.72,
"learning_rate": 2.1273214494777145e-05,
"loss": 1.5572,
"step": 397500
},
{
"epoch": 1.73,
"learning_rate": 2.123708017338693e-05,
"loss": 1.5245,
"step": 398000
},
{
"epoch": 1.73,
"learning_rate": 2.120094585199671e-05,
"loss": 1.5418,
"step": 398500
},
{
"epoch": 1.73,
"learning_rate": 2.1164811530606495e-05,
"loss": 1.4851,
"step": 399000
},
{
"epoch": 1.73,
"learning_rate": 2.1128677209216278e-05,
"loss": 1.5774,
"step": 399500
},
{
"epoch": 1.73,
"learning_rate": 2.1092542887826057e-05,
"loss": 1.5815,
"step": 400000
},
{
"epoch": 1.74,
"learning_rate": 2.1056408566435844e-05,
"loss": 1.5491,
"step": 400500
},
{
"epoch": 1.74,
"learning_rate": 2.1020274245045624e-05,
"loss": 1.5462,
"step": 401000
},
{
"epoch": 1.74,
"learning_rate": 2.0984139923655407e-05,
"loss": 1.5607,
"step": 401500
},
{
"epoch": 1.74,
"learning_rate": 2.094800560226519e-05,
"loss": 1.5391,
"step": 402000
},
{
"epoch": 1.75,
"learning_rate": 2.0911871280874973e-05,
"loss": 1.5052,
"step": 402500
},
{
"epoch": 1.75,
"learning_rate": 2.0875736959484753e-05,
"loss": 1.5585,
"step": 403000
},
{
"epoch": 1.75,
"learning_rate": 2.083960263809454e-05,
"loss": 1.5343,
"step": 403500
},
{
"epoch": 1.75,
"learning_rate": 2.080346831670432e-05,
"loss": 1.543,
"step": 404000
},
{
"epoch": 1.75,
"learning_rate": 2.0767333995314102e-05,
"loss": 1.5462,
"step": 404500
},
{
"epoch": 1.76,
"learning_rate": 2.0731199673923885e-05,
"loss": 1.5329,
"step": 405000
},
{
"epoch": 1.76,
"learning_rate": 2.0695065352533668e-05,
"loss": 1.5626,
"step": 405500
},
{
"epoch": 1.76,
"learning_rate": 2.065893103114345e-05,
"loss": 1.5306,
"step": 406000
},
{
"epoch": 1.76,
"learning_rate": 2.0622796709753234e-05,
"loss": 1.5386,
"step": 406500
},
{
"epoch": 1.76,
"learning_rate": 2.0586662388363014e-05,
"loss": 1.5137,
"step": 407000
},
{
"epoch": 1.77,
"learning_rate": 2.05505280669728e-05,
"loss": 1.5113,
"step": 407500
},
{
"epoch": 1.77,
"learning_rate": 2.051439374558258e-05,
"loss": 1.534,
"step": 408000
},
{
"epoch": 1.77,
"learning_rate": 2.047825942419236e-05,
"loss": 1.517,
"step": 408500
},
{
"epoch": 1.77,
"learning_rate": 2.0442125102802146e-05,
"loss": 1.5512,
"step": 409000
},
{
"epoch": 1.78,
"learning_rate": 2.0405990781411926e-05,
"loss": 1.5329,
"step": 409500
},
{
"epoch": 1.78,
"learning_rate": 2.036985646002171e-05,
"loss": 1.5215,
"step": 410000
},
{
"epoch": 1.78,
"learning_rate": 2.0333722138631492e-05,
"loss": 1.5314,
"step": 410500
},
{
"epoch": 1.78,
"learning_rate": 2.0297587817241275e-05,
"loss": 1.5114,
"step": 411000
},
{
"epoch": 1.78,
"learning_rate": 2.026145349585106e-05,
"loss": 1.5483,
"step": 411500
},
{
"epoch": 1.79,
"learning_rate": 2.022531917446084e-05,
"loss": 1.5469,
"step": 412000
},
{
"epoch": 1.79,
"learning_rate": 2.018918485307062e-05,
"loss": 1.5341,
"step": 412500
},
{
"epoch": 1.79,
"learning_rate": 2.0153050531680408e-05,
"loss": 1.5798,
"step": 413000
},
{
"epoch": 1.79,
"learning_rate": 2.0116916210290187e-05,
"loss": 1.5468,
"step": 413500
},
{
"epoch": 1.8,
"learning_rate": 2.008078188889997e-05,
"loss": 1.5002,
"step": 414000
},
{
"epoch": 1.8,
"learning_rate": 2.0044647567509754e-05,
"loss": 1.5829,
"step": 414500
},
{
"epoch": 1.8,
"learning_rate": 2.0008513246119537e-05,
"loss": 1.5043,
"step": 415000
},
{
"epoch": 1.8,
"learning_rate": 1.997237892472932e-05,
"loss": 1.5137,
"step": 415500
},
{
"epoch": 1.8,
"learning_rate": 1.9936244603339103e-05,
"loss": 1.567,
"step": 416000
},
{
"epoch": 1.81,
"learning_rate": 1.9900110281948882e-05,
"loss": 1.542,
"step": 416500
},
{
"epoch": 1.81,
"learning_rate": 1.9863975960558666e-05,
"loss": 1.5471,
"step": 417000
},
{
"epoch": 1.81,
"learning_rate": 1.982784163916845e-05,
"loss": 1.4926,
"step": 417500
},
{
"epoch": 1.81,
"learning_rate": 1.9791707317778232e-05,
"loss": 1.5535,
"step": 418000
},
{
"epoch": 1.81,
"learning_rate": 1.9755572996388015e-05,
"loss": 1.5139,
"step": 418500
},
{
"epoch": 1.82,
"learning_rate": 1.9719438674997798e-05,
"loss": 1.5626,
"step": 419000
},
{
"epoch": 1.82,
"learning_rate": 1.9683304353607578e-05,
"loss": 1.5086,
"step": 419500
},
{
"epoch": 1.82,
"learning_rate": 1.9647170032217364e-05,
"loss": 1.5181,
"step": 420000
},
{
"epoch": 1.82,
"learning_rate": 1.9611035710827144e-05,
"loss": 1.5033,
"step": 420500
},
{
"epoch": 1.83,
"learning_rate": 1.9574901389436927e-05,
"loss": 1.5119,
"step": 421000
},
{
"epoch": 1.83,
"learning_rate": 1.953876706804671e-05,
"loss": 1.5393,
"step": 421500
},
{
"epoch": 1.83,
"learning_rate": 1.9502632746656493e-05,
"loss": 1.5239,
"step": 422000
},
{
"epoch": 1.83,
"learning_rate": 1.9466498425266276e-05,
"loss": 1.4977,
"step": 422500
},
{
"epoch": 1.83,
"learning_rate": 1.943036410387606e-05,
"loss": 1.5371,
"step": 423000
},
{
"epoch": 1.84,
"learning_rate": 1.939422978248584e-05,
"loss": 1.4919,
"step": 423500
},
{
"epoch": 1.84,
"learning_rate": 1.9358095461095622e-05,
"loss": 1.5356,
"step": 424000
},
{
"epoch": 1.84,
"learning_rate": 1.9321961139705405e-05,
"loss": 1.5455,
"step": 424500
},
{
"epoch": 1.84,
"learning_rate": 1.9285826818315185e-05,
"loss": 1.5217,
"step": 425000
},
{
"epoch": 1.85,
"learning_rate": 1.924969249692497e-05,
"loss": 1.5092,
"step": 425500
},
{
"epoch": 1.85,
"learning_rate": 1.921355817553475e-05,
"loss": 1.5463,
"step": 426000
},
{
"epoch": 1.85,
"learning_rate": 1.9177423854144534e-05,
"loss": 1.5141,
"step": 426500
},
{
"epoch": 1.85,
"learning_rate": 1.9141289532754317e-05,
"loss": 1.5047,
"step": 427000
},
{
"epoch": 1.85,
"learning_rate": 1.91051552113641e-05,
"loss": 1.5194,
"step": 427500
},
{
"epoch": 1.86,
"learning_rate": 1.9069020889973883e-05,
"loss": 1.5249,
"step": 428000
},
{
"epoch": 1.86,
"learning_rate": 1.9032886568583667e-05,
"loss": 1.4905,
"step": 428500
},
{
"epoch": 1.86,
"learning_rate": 1.8996752247193446e-05,
"loss": 1.5426,
"step": 429000
},
{
"epoch": 1.86,
"learning_rate": 1.8960617925803233e-05,
"loss": 1.5167,
"step": 429500
},
{
"epoch": 1.86,
"learning_rate": 1.8924483604413012e-05,
"loss": 1.5211,
"step": 430000
},
{
"epoch": 1.87,
"learning_rate": 1.8888349283022796e-05,
"loss": 1.5299,
"step": 430500
},
{
"epoch": 1.87,
"learning_rate": 1.885221496163258e-05,
"loss": 1.5145,
"step": 431000
},
{
"epoch": 1.87,
"learning_rate": 1.8816080640242362e-05,
"loss": 1.5137,
"step": 431500
},
{
"epoch": 1.87,
"learning_rate": 1.877994631885214e-05,
"loss": 1.4812,
"step": 432000
},
{
"epoch": 1.88,
"learning_rate": 1.8743811997461928e-05,
"loss": 1.5136,
"step": 432500
},
{
"epoch": 1.88,
"learning_rate": 1.8707677676071708e-05,
"loss": 1.4779,
"step": 433000
},
{
"epoch": 1.88,
"learning_rate": 1.867154335468149e-05,
"loss": 1.5019,
"step": 433500
},
{
"epoch": 1.88,
"learning_rate": 1.8635409033291274e-05,
"loss": 1.5257,
"step": 434000
},
{
"epoch": 1.88,
"learning_rate": 1.8599274711901057e-05,
"loss": 1.5006,
"step": 434500
},
{
"epoch": 1.89,
"learning_rate": 1.856314039051084e-05,
"loss": 1.5235,
"step": 435000
},
{
"epoch": 1.89,
"learning_rate": 1.8527006069120623e-05,
"loss": 1.4978,
"step": 435500
},
{
"epoch": 1.89,
"learning_rate": 1.8490871747730403e-05,
"loss": 1.4991,
"step": 436000
},
{
"epoch": 1.89,
"learning_rate": 1.845473742634019e-05,
"loss": 1.5137,
"step": 436500
},
{
"epoch": 1.89,
"learning_rate": 1.841860310494997e-05,
"loss": 1.5057,
"step": 437000
},
{
"epoch": 1.9,
"learning_rate": 1.8382468783559752e-05,
"loss": 1.5032,
"step": 437500
},
{
"epoch": 1.9,
"learning_rate": 1.8346334462169535e-05,
"loss": 1.4749,
"step": 438000
},
{
"epoch": 1.9,
"learning_rate": 1.8310200140779318e-05,
"loss": 1.5456,
"step": 438500
},
{
"epoch": 1.9,
"learning_rate": 1.8274065819389098e-05,
"loss": 1.5161,
"step": 439000
},
{
"epoch": 1.91,
"learning_rate": 1.823793149799888e-05,
"loss": 1.4988,
"step": 439500
},
{
"epoch": 1.91,
"learning_rate": 1.8201797176608664e-05,
"loss": 1.4921,
"step": 440000
},
{
"epoch": 1.91,
"learning_rate": 1.8165662855218447e-05,
"loss": 1.4987,
"step": 440500
},
{
"epoch": 1.91,
"learning_rate": 1.812952853382823e-05,
"loss": 1.4942,
"step": 441000
},
{
"epoch": 1.91,
"learning_rate": 1.809339421243801e-05,
"loss": 1.5123,
"step": 441500
},
{
"epoch": 1.92,
"learning_rate": 1.8057259891047797e-05,
"loss": 1.541,
"step": 442000
},
{
"epoch": 1.92,
"learning_rate": 1.8021125569657576e-05,
"loss": 1.4926,
"step": 442500
},
{
"epoch": 1.92,
"learning_rate": 1.798499124826736e-05,
"loss": 1.5246,
"step": 443000
},
{
"epoch": 1.92,
"learning_rate": 1.7948856926877142e-05,
"loss": 1.5182,
"step": 443500
},
{
"epoch": 1.93,
"learning_rate": 1.7912722605486926e-05,
"loss": 1.4966,
"step": 444000
},
{
"epoch": 1.93,
"learning_rate": 1.7876588284096705e-05,
"loss": 1.5202,
"step": 444500
},
{
"epoch": 1.93,
"learning_rate": 1.7840453962706492e-05,
"loss": 1.5377,
"step": 445000
},
{
"epoch": 1.93,
"learning_rate": 1.780431964131627e-05,
"loss": 1.4819,
"step": 445500
},
{
"epoch": 1.93,
"learning_rate": 1.7768185319926055e-05,
"loss": 1.4955,
"step": 446000
},
{
"epoch": 1.94,
"learning_rate": 1.7732050998535838e-05,
"loss": 1.4938,
"step": 446500
},
{
"epoch": 1.94,
"learning_rate": 1.769591667714562e-05,
"loss": 1.4885,
"step": 447000
},
{
"epoch": 1.94,
"learning_rate": 1.7659782355755404e-05,
"loss": 1.4703,
"step": 447500
},
{
"epoch": 1.94,
"learning_rate": 1.7623648034365187e-05,
"loss": 1.514,
"step": 448000
},
{
"epoch": 1.94,
"learning_rate": 1.7587513712974967e-05,
"loss": 1.5895,
"step": 448500
},
{
"epoch": 1.95,
"learning_rate": 1.7551379391584753e-05,
"loss": 1.51,
"step": 449000
},
{
"epoch": 1.95,
"learning_rate": 1.7515245070194533e-05,
"loss": 1.4901,
"step": 449500
},
{
"epoch": 1.95,
"learning_rate": 1.7479110748804316e-05,
"loss": 1.5189,
"step": 450000
},
{
"epoch": 1.95,
"learning_rate": 1.74429764274141e-05,
"loss": 1.4983,
"step": 450500
},
{
"epoch": 1.96,
"learning_rate": 1.7406842106023882e-05,
"loss": 1.4805,
"step": 451000
},
{
"epoch": 1.96,
"learning_rate": 1.7370707784633665e-05,
"loss": 1.4711,
"step": 451500
},
{
"epoch": 1.96,
"learning_rate": 1.7334573463243448e-05,
"loss": 1.4868,
"step": 452000
},
{
"epoch": 1.96,
"learning_rate": 1.7298439141853228e-05,
"loss": 1.5257,
"step": 452500
},
{
"epoch": 1.96,
"learning_rate": 1.7262304820463014e-05,
"loss": 1.485,
"step": 453000
},
{
"epoch": 1.97,
"learning_rate": 1.7226170499072794e-05,
"loss": 1.4902,
"step": 453500
},
{
"epoch": 1.97,
"learning_rate": 1.7190036177682577e-05,
"loss": 1.4856,
"step": 454000
},
{
"epoch": 1.97,
"learning_rate": 1.715390185629236e-05,
"loss": 1.4745,
"step": 454500
},
{
"epoch": 1.97,
"learning_rate": 1.711776753490214e-05,
"loss": 1.549,
"step": 455000
},
{
"epoch": 1.98,
"learning_rate": 1.7081633213511923e-05,
"loss": 1.5343,
"step": 455500
},
{
"epoch": 1.98,
"learning_rate": 1.7045498892121706e-05,
"loss": 1.4615,
"step": 456000
},
{
"epoch": 1.98,
"learning_rate": 1.700936457073149e-05,
"loss": 1.4834,
"step": 456500
},
{
"epoch": 1.98,
"learning_rate": 1.6973230249341272e-05,
"loss": 1.5317,
"step": 457000
},
{
"epoch": 1.98,
"learning_rate": 1.6937095927951056e-05,
"loss": 1.4873,
"step": 457500
},
{
"epoch": 1.99,
"learning_rate": 1.6900961606560835e-05,
"loss": 1.5077,
"step": 458000
},
{
"epoch": 1.99,
"learning_rate": 1.6864827285170622e-05,
"loss": 1.4931,
"step": 458500
},
{
"epoch": 1.99,
"learning_rate": 1.68286929637804e-05,
"loss": 1.4884,
"step": 459000
},
{
"epoch": 1.99,
"learning_rate": 1.6792558642390185e-05,
"loss": 1.5085,
"step": 459500
},
{
"epoch": 1.99,
"learning_rate": 1.6756424320999968e-05,
"loss": 1.5031,
"step": 460000
},
{
"epoch": 2.0,
"learning_rate": 1.672028999960975e-05,
"loss": 1.5137,
"step": 460500
},
{
"epoch": 2.0,
"learning_rate": 1.668415567821953e-05,
"loss": 1.503,
"step": 461000
},
{
"epoch": 2.0,
"learning_rate": 1.6648021356829317e-05,
"loss": 1.5044,
"step": 461500
},
{
"epoch": 2.0,
"learning_rate": 1.6611887035439097e-05,
"loss": 1.503,
"step": 462000
},
{
"epoch": 2.01,
"learning_rate": 1.657575271404888e-05,
"loss": 1.5166,
"step": 462500
},
{
"epoch": 2.01,
"learning_rate": 1.6539618392658663e-05,
"loss": 1.4866,
"step": 463000
},
{
"epoch": 2.01,
"learning_rate": 1.6503484071268446e-05,
"loss": 1.4696,
"step": 463500
},
{
"epoch": 2.01,
"learning_rate": 1.646734974987823e-05,
"loss": 1.4641,
"step": 464000
},
{
"epoch": 2.01,
"learning_rate": 1.6431215428488012e-05,
"loss": 1.426,
"step": 464500
},
{
"epoch": 2.02,
"learning_rate": 1.6395081107097792e-05,
"loss": 1.4801,
"step": 465000
},
{
"epoch": 2.02,
"learning_rate": 1.6358946785707578e-05,
"loss": 1.4632,
"step": 465500
},
{
"epoch": 2.02,
"learning_rate": 1.6322812464317358e-05,
"loss": 1.5042,
"step": 466000
},
{
"epoch": 2.02,
"learning_rate": 1.628667814292714e-05,
"loss": 1.4887,
"step": 466500
},
{
"epoch": 2.02,
"learning_rate": 1.6250543821536924e-05,
"loss": 1.427,
"step": 467000
},
{
"epoch": 2.03,
"learning_rate": 1.6214409500146707e-05,
"loss": 1.466,
"step": 467500
},
{
"epoch": 2.03,
"learning_rate": 1.6178275178756487e-05,
"loss": 1.4376,
"step": 468000
},
{
"epoch": 2.03,
"learning_rate": 1.6142140857366273e-05,
"loss": 1.4774,
"step": 468500
},
{
"epoch": 2.03,
"learning_rate": 1.6106006535976053e-05,
"loss": 1.4783,
"step": 469000
},
{
"epoch": 2.04,
"learning_rate": 1.6069872214585836e-05,
"loss": 1.4318,
"step": 469500
},
{
"epoch": 2.04,
"learning_rate": 1.603373789319562e-05,
"loss": 1.4263,
"step": 470000
},
{
"epoch": 2.04,
"learning_rate": 1.5997603571805402e-05,
"loss": 1.4621,
"step": 470500
},
{
"epoch": 2.04,
"learning_rate": 1.5961469250415186e-05,
"loss": 1.421,
"step": 471000
},
{
"epoch": 2.04,
"learning_rate": 1.5925334929024965e-05,
"loss": 1.4621,
"step": 471500
},
{
"epoch": 2.05,
"learning_rate": 1.588920060763475e-05,
"loss": 1.4773,
"step": 472000
},
{
"epoch": 2.05,
"learning_rate": 1.585306628624453e-05,
"loss": 1.49,
"step": 472500
},
{
"epoch": 2.05,
"learning_rate": 1.5816931964854315e-05,
"loss": 1.4757,
"step": 473000
},
{
"epoch": 2.05,
"learning_rate": 1.5780797643464094e-05,
"loss": 1.4496,
"step": 473500
},
{
"epoch": 2.06,
"learning_rate": 1.574466332207388e-05,
"loss": 1.4963,
"step": 474000
},
{
"epoch": 2.06,
"learning_rate": 1.570852900068366e-05,
"loss": 1.4373,
"step": 474500
},
{
"epoch": 2.06,
"learning_rate": 1.5672394679293443e-05,
"loss": 1.4389,
"step": 475000
},
{
"epoch": 2.06,
"learning_rate": 1.5636260357903227e-05,
"loss": 1.4557,
"step": 475500
},
{
"epoch": 2.06,
"learning_rate": 1.560012603651301e-05,
"loss": 1.4192,
"step": 476000
},
{
"epoch": 2.07,
"learning_rate": 1.5563991715122793e-05,
"loss": 1.4801,
"step": 476500
},
{
"epoch": 2.07,
"learning_rate": 1.5527857393732576e-05,
"loss": 1.4757,
"step": 477000
},
{
"epoch": 2.07,
"learning_rate": 1.5491723072342356e-05,
"loss": 1.4435,
"step": 477500
},
{
"epoch": 2.07,
"learning_rate": 1.5455588750952142e-05,
"loss": 1.4611,
"step": 478000
},
{
"epoch": 2.07,
"learning_rate": 1.5419454429561922e-05,
"loss": 1.4716,
"step": 478500
},
{
"epoch": 2.08,
"learning_rate": 1.5383320108171705e-05,
"loss": 1.5053,
"step": 479000
},
{
"epoch": 2.08,
"learning_rate": 1.5347185786781488e-05,
"loss": 1.4292,
"step": 479500
},
{
"epoch": 2.08,
"learning_rate": 1.531105146539127e-05,
"loss": 1.5052,
"step": 480000
},
{
"epoch": 2.08,
"learning_rate": 1.5274917144001054e-05,
"loss": 1.453,
"step": 480500
},
{
"epoch": 2.09,
"learning_rate": 1.5238782822610837e-05,
"loss": 1.4431,
"step": 481000
},
{
"epoch": 2.09,
"learning_rate": 1.5202648501220617e-05,
"loss": 1.4807,
"step": 481500
},
{
"epoch": 2.09,
"learning_rate": 1.5166514179830402e-05,
"loss": 1.4948,
"step": 482000
},
{
"epoch": 2.09,
"learning_rate": 1.5130379858440183e-05,
"loss": 1.454,
"step": 482500
},
{
"epoch": 2.09,
"learning_rate": 1.5094245537049966e-05,
"loss": 1.4567,
"step": 483000
},
{
"epoch": 2.1,
"learning_rate": 1.5058111215659748e-05,
"loss": 1.4708,
"step": 483500
},
{
"epoch": 2.1,
"learning_rate": 1.5021976894269532e-05,
"loss": 1.462,
"step": 484000
},
{
"epoch": 2.1,
"learning_rate": 1.4985842572879314e-05,
"loss": 1.4815,
"step": 484500
},
{
"epoch": 2.1,
"learning_rate": 1.4949708251489097e-05,
"loss": 1.4871,
"step": 485000
},
{
"epoch": 2.11,
"learning_rate": 1.4913573930098878e-05,
"loss": 1.4272,
"step": 485500
},
{
"epoch": 2.11,
"learning_rate": 1.4877439608708663e-05,
"loss": 1.4824,
"step": 486000
},
{
"epoch": 2.11,
"learning_rate": 1.4841305287318444e-05,
"loss": 1.4107,
"step": 486500
},
{
"epoch": 2.11,
"learning_rate": 1.4805170965928226e-05,
"loss": 1.4344,
"step": 487000
},
{
"epoch": 2.11,
"learning_rate": 1.4769036644538009e-05,
"loss": 1.4459,
"step": 487500
},
{
"epoch": 2.12,
"learning_rate": 1.473290232314779e-05,
"loss": 1.458,
"step": 488000
},
{
"epoch": 2.12,
"learning_rate": 1.4696768001757573e-05,
"loss": 1.4314,
"step": 488500
},
{
"epoch": 2.12,
"learning_rate": 1.4660633680367355e-05,
"loss": 1.4257,
"step": 489000
},
{
"epoch": 2.12,
"learning_rate": 1.462449935897714e-05,
"loss": 1.4453,
"step": 489500
},
{
"epoch": 2.12,
"learning_rate": 1.4588365037586921e-05,
"loss": 1.4747,
"step": 490000
},
{
"epoch": 2.13,
"learning_rate": 1.4552230716196704e-05,
"loss": 1.4456,
"step": 490500
},
{
"epoch": 2.13,
"learning_rate": 1.4516096394806486e-05,
"loss": 1.4268,
"step": 491000
},
{
"epoch": 2.13,
"learning_rate": 1.447996207341627e-05,
"loss": 1.4477,
"step": 491500
},
{
"epoch": 2.13,
"learning_rate": 1.4443827752026052e-05,
"loss": 1.481,
"step": 492000
},
{
"epoch": 2.14,
"learning_rate": 1.4407693430635835e-05,
"loss": 1.5086,
"step": 492500
},
{
"epoch": 2.14,
"learning_rate": 1.4371559109245616e-05,
"loss": 1.4312,
"step": 493000
},
{
"epoch": 2.14,
"learning_rate": 1.4335424787855401e-05,
"loss": 1.4249,
"step": 493500
},
{
"epoch": 2.14,
"learning_rate": 1.4299290466465182e-05,
"loss": 1.4639,
"step": 494000
},
{
"epoch": 2.14,
"learning_rate": 1.4263156145074966e-05,
"loss": 1.457,
"step": 494500
},
{
"epoch": 2.15,
"learning_rate": 1.4227021823684747e-05,
"loss": 1.431,
"step": 495000
},
{
"epoch": 2.15,
"learning_rate": 1.4190887502294532e-05,
"loss": 1.4745,
"step": 495500
},
{
"epoch": 2.15,
"learning_rate": 1.4154753180904311e-05,
"loss": 1.4481,
"step": 496000
},
{
"epoch": 2.15,
"learning_rate": 1.4118618859514096e-05,
"loss": 1.4994,
"step": 496500
},
{
"epoch": 2.16,
"learning_rate": 1.4082484538123878e-05,
"loss": 1.4606,
"step": 497000
},
{
"epoch": 2.16,
"learning_rate": 1.404635021673366e-05,
"loss": 1.4564,
"step": 497500
},
{
"epoch": 2.16,
"learning_rate": 1.4010215895343442e-05,
"loss": 1.4314,
"step": 498000
},
{
"epoch": 2.16,
"learning_rate": 1.3974081573953227e-05,
"loss": 1.4186,
"step": 498500
},
{
"epoch": 2.16,
"learning_rate": 1.3937947252563008e-05,
"loss": 1.4544,
"step": 499000
},
{
"epoch": 2.17,
"learning_rate": 1.3901812931172791e-05,
"loss": 1.4543,
"step": 499500
},
{
"epoch": 2.17,
"learning_rate": 1.3865678609782573e-05,
"loss": 1.4342,
"step": 500000
},
{
"epoch": 2.17,
"learning_rate": 1.3829544288392358e-05,
"loss": 1.4649,
"step": 500500
},
{
"epoch": 2.17,
"learning_rate": 1.3793409967002139e-05,
"loss": 1.4296,
"step": 501000
},
{
"epoch": 2.17,
"learning_rate": 1.3757275645611922e-05,
"loss": 1.4514,
"step": 501500
},
{
"epoch": 2.18,
"learning_rate": 1.3721141324221703e-05,
"loss": 1.4256,
"step": 502000
},
{
"epoch": 2.18,
"learning_rate": 1.3685007002831485e-05,
"loss": 1.4472,
"step": 502500
},
{
"epoch": 2.18,
"learning_rate": 1.3648872681441268e-05,
"loss": 1.466,
"step": 503000
},
{
"epoch": 2.18,
"learning_rate": 1.361273836005105e-05,
"loss": 1.4633,
"step": 503500
},
{
"epoch": 2.19,
"learning_rate": 1.3576604038660834e-05,
"loss": 1.4246,
"step": 504000
},
{
"epoch": 2.19,
"learning_rate": 1.3540469717270616e-05,
"loss": 1.4055,
"step": 504500
},
{
"epoch": 2.19,
"learning_rate": 1.3504335395880399e-05,
"loss": 1.4214,
"step": 505000
},
{
"epoch": 2.19,
"learning_rate": 1.346820107449018e-05,
"loss": 1.4088,
"step": 505500
},
{
"epoch": 2.19,
"learning_rate": 1.3432066753099965e-05,
"loss": 1.4703,
"step": 506000
},
{
"epoch": 2.2,
"learning_rate": 1.3395932431709746e-05,
"loss": 1.406,
"step": 506500
},
{
"epoch": 2.2,
"learning_rate": 1.335979811031953e-05,
"loss": 1.4278,
"step": 507000
},
{
"epoch": 2.2,
"learning_rate": 1.332366378892931e-05,
"loss": 1.4846,
"step": 507500
},
{
"epoch": 2.2,
"learning_rate": 1.3287529467539095e-05,
"loss": 1.4458,
"step": 508000
},
{
"epoch": 2.2,
"learning_rate": 1.3251395146148877e-05,
"loss": 1.4072,
"step": 508500
},
{
"epoch": 2.21,
"learning_rate": 1.321526082475866e-05,
"loss": 1.444,
"step": 509000
},
{
"epoch": 2.21,
"learning_rate": 1.3179126503368441e-05,
"loss": 1.4382,
"step": 509500
},
{
"epoch": 2.21,
"learning_rate": 1.3142992181978226e-05,
"loss": 1.4198,
"step": 510000
},
{
"epoch": 2.21,
"learning_rate": 1.3106857860588006e-05,
"loss": 1.4283,
"step": 510500
},
{
"epoch": 2.22,
"learning_rate": 1.307072353919779e-05,
"loss": 1.4691,
"step": 511000
},
{
"epoch": 2.22,
"learning_rate": 1.3034589217807572e-05,
"loss": 1.4271,
"step": 511500
},
{
"epoch": 2.22,
"learning_rate": 1.2998454896417355e-05,
"loss": 1.4434,
"step": 512000
},
{
"epoch": 2.22,
"learning_rate": 1.2962320575027137e-05,
"loss": 1.4562,
"step": 512500
},
{
"epoch": 2.22,
"learning_rate": 1.2926186253636921e-05,
"loss": 1.4442,
"step": 513000
},
{
"epoch": 2.23,
"learning_rate": 1.2890051932246703e-05,
"loss": 1.474,
"step": 513500
},
{
"epoch": 2.23,
"learning_rate": 1.2853917610856486e-05,
"loss": 1.4134,
"step": 514000
},
{
"epoch": 2.23,
"learning_rate": 1.2817783289466267e-05,
"loss": 1.4054,
"step": 514500
},
{
"epoch": 2.23,
"learning_rate": 1.2781648968076052e-05,
"loss": 1.3957,
"step": 515000
},
{
"epoch": 2.24,
"learning_rate": 1.2745514646685833e-05,
"loss": 1.4274,
"step": 515500
},
{
"epoch": 2.24,
"learning_rate": 1.2709380325295617e-05,
"loss": 1.4372,
"step": 516000
},
{
"epoch": 2.24,
"learning_rate": 1.2673246003905398e-05,
"loss": 1.4332,
"step": 516500
},
{
"epoch": 2.24,
"learning_rate": 1.2637111682515183e-05,
"loss": 1.4321,
"step": 517000
},
{
"epoch": 2.24,
"learning_rate": 1.2600977361124962e-05,
"loss": 1.3978,
"step": 517500
},
{
"epoch": 2.25,
"learning_rate": 1.2564843039734744e-05,
"loss": 1.4483,
"step": 518000
},
{
"epoch": 2.25,
"learning_rate": 1.2528708718344529e-05,
"loss": 1.4294,
"step": 518500
},
{
"epoch": 2.25,
"learning_rate": 1.2492574396954312e-05,
"loss": 1.4353,
"step": 519000
},
{
"epoch": 2.25,
"learning_rate": 1.2456440075564093e-05,
"loss": 1.4237,
"step": 519500
},
{
"epoch": 2.25,
"learning_rate": 1.2420305754173876e-05,
"loss": 1.4292,
"step": 520000
},
{
"epoch": 2.26,
"learning_rate": 1.238417143278366e-05,
"loss": 1.3973,
"step": 520500
},
{
"epoch": 2.26,
"learning_rate": 1.234803711139344e-05,
"loss": 1.4142,
"step": 521000
},
{
"epoch": 2.26,
"learning_rate": 1.2311902790003224e-05,
"loss": 1.4929,
"step": 521500
},
{
"epoch": 2.26,
"learning_rate": 1.2275768468613007e-05,
"loss": 1.4267,
"step": 522000
},
{
"epoch": 2.27,
"learning_rate": 1.223963414722279e-05,
"loss": 1.4154,
"step": 522500
},
{
"epoch": 2.27,
"learning_rate": 1.2203499825832571e-05,
"loss": 1.4319,
"step": 523000
},
{
"epoch": 2.27,
"learning_rate": 1.2167365504442354e-05,
"loss": 1.4838,
"step": 523500
},
{
"epoch": 2.27,
"learning_rate": 1.2131231183052138e-05,
"loss": 1.4557,
"step": 524000
},
{
"epoch": 2.27,
"learning_rate": 1.2095096861661919e-05,
"loss": 1.4256,
"step": 524500
},
{
"epoch": 2.28,
"learning_rate": 1.2058962540271702e-05,
"loss": 1.4146,
"step": 525000
},
{
"epoch": 2.28,
"learning_rate": 1.2022828218881485e-05,
"loss": 1.449,
"step": 525500
},
{
"epoch": 2.28,
"learning_rate": 1.1986693897491267e-05,
"loss": 1.4231,
"step": 526000
},
{
"epoch": 2.28,
"learning_rate": 1.195055957610105e-05,
"loss": 1.4006,
"step": 526500
},
{
"epoch": 2.29,
"learning_rate": 1.1914425254710831e-05,
"loss": 1.4105,
"step": 527000
},
{
"epoch": 2.29,
"learning_rate": 1.1878290933320614e-05,
"loss": 1.4028,
"step": 527500
},
{
"epoch": 2.29,
"learning_rate": 1.1842156611930397e-05,
"loss": 1.4328,
"step": 528000
},
{
"epoch": 2.29,
"learning_rate": 1.1806022290540179e-05,
"loss": 1.4376,
"step": 528500
},
{
"epoch": 2.29,
"learning_rate": 1.1769887969149962e-05,
"loss": 1.4125,
"step": 529000
},
{
"epoch": 2.3,
"learning_rate": 1.1733753647759745e-05,
"loss": 1.4222,
"step": 529500
},
{
"epoch": 2.3,
"learning_rate": 1.1697619326369528e-05,
"loss": 1.4116,
"step": 530000
},
{
"epoch": 2.3,
"learning_rate": 1.166148500497931e-05,
"loss": 1.4227,
"step": 530500
},
{
"epoch": 2.3,
"learning_rate": 1.1625350683589092e-05,
"loss": 1.3947,
"step": 531000
},
{
"epoch": 2.3,
"learning_rate": 1.1589216362198875e-05,
"loss": 1.4376,
"step": 531500
},
{
"epoch": 2.31,
"learning_rate": 1.1553082040808657e-05,
"loss": 1.4212,
"step": 532000
},
{
"epoch": 2.31,
"learning_rate": 1.151694771941844e-05,
"loss": 1.4012,
"step": 532500
},
{
"epoch": 2.31,
"learning_rate": 1.1480813398028223e-05,
"loss": 1.4403,
"step": 533000
},
{
"epoch": 2.31,
"learning_rate": 1.1444679076638006e-05,
"loss": 1.4377,
"step": 533500
},
{
"epoch": 2.32,
"learning_rate": 1.1408544755247788e-05,
"loss": 1.4492,
"step": 534000
},
{
"epoch": 2.32,
"learning_rate": 1.137241043385757e-05,
"loss": 1.3854,
"step": 534500
},
{
"epoch": 2.32,
"learning_rate": 1.1336276112467354e-05,
"loss": 1.4119,
"step": 535000
},
{
"epoch": 2.32,
"learning_rate": 1.1300141791077135e-05,
"loss": 1.3798,
"step": 535500
},
{
"epoch": 2.32,
"learning_rate": 1.1264007469686918e-05,
"loss": 1.4242,
"step": 536000
},
{
"epoch": 2.33,
"learning_rate": 1.1227873148296701e-05,
"loss": 1.3758,
"step": 536500
},
{
"epoch": 2.33,
"learning_rate": 1.1191738826906484e-05,
"loss": 1.4261,
"step": 537000
},
{
"epoch": 2.33,
"learning_rate": 1.1155604505516266e-05,
"loss": 1.4007,
"step": 537500
},
{
"epoch": 2.33,
"learning_rate": 1.1119470184126049e-05,
"loss": 1.3788,
"step": 538000
},
{
"epoch": 2.33,
"learning_rate": 1.1083335862735832e-05,
"loss": 1.4018,
"step": 538500
},
{
"epoch": 2.34,
"learning_rate": 1.1047201541345613e-05,
"loss": 1.4226,
"step": 539000
},
{
"epoch": 2.34,
"learning_rate": 1.1011067219955397e-05,
"loss": 1.3565,
"step": 539500
},
{
"epoch": 2.34,
"learning_rate": 1.097493289856518e-05,
"loss": 1.3948,
"step": 540000
},
{
"epoch": 2.34,
"learning_rate": 1.0938798577174963e-05,
"loss": 1.3796,
"step": 540500
},
{
"epoch": 2.35,
"learning_rate": 1.0902664255784744e-05,
"loss": 1.3938,
"step": 541000
},
{
"epoch": 2.35,
"learning_rate": 1.0866529934394526e-05,
"loss": 1.4246,
"step": 541500
},
{
"epoch": 2.35,
"learning_rate": 1.0830395613004309e-05,
"loss": 1.4174,
"step": 542000
},
{
"epoch": 2.35,
"learning_rate": 1.0794261291614092e-05,
"loss": 1.3972,
"step": 542500
},
{
"epoch": 2.35,
"learning_rate": 1.0758126970223873e-05,
"loss": 1.4093,
"step": 543000
},
{
"epoch": 2.36,
"learning_rate": 1.0721992648833656e-05,
"loss": 1.4145,
"step": 543500
},
{
"epoch": 2.36,
"learning_rate": 1.068585832744344e-05,
"loss": 1.4571,
"step": 544000
},
{
"epoch": 2.36,
"learning_rate": 1.0649724006053222e-05,
"loss": 1.4263,
"step": 544500
},
{
"epoch": 2.36,
"learning_rate": 1.0613589684663004e-05,
"loss": 1.3886,
"step": 545000
},
{
"epoch": 2.37,
"learning_rate": 1.0577455363272787e-05,
"loss": 1.4097,
"step": 545500
},
{
"epoch": 2.37,
"learning_rate": 1.054132104188257e-05,
"loss": 1.3736,
"step": 546000
},
{
"epoch": 2.37,
"learning_rate": 1.0505186720492351e-05,
"loss": 1.4224,
"step": 546500
},
{
"epoch": 2.37,
"learning_rate": 1.0469052399102134e-05,
"loss": 1.4065,
"step": 547000
},
{
"epoch": 2.37,
"learning_rate": 1.0432918077711918e-05,
"loss": 1.4234,
"step": 547500
},
{
"epoch": 2.38,
"learning_rate": 1.03967837563217e-05,
"loss": 1.406,
"step": 548000
},
{
"epoch": 2.38,
"learning_rate": 1.0360649434931482e-05,
"loss": 1.3627,
"step": 548500
},
{
"epoch": 2.38,
"learning_rate": 1.0324515113541265e-05,
"loss": 1.4247,
"step": 549000
},
{
"epoch": 2.38,
"learning_rate": 1.0288380792151048e-05,
"loss": 1.4084,
"step": 549500
},
{
"epoch": 2.38,
"learning_rate": 1.025224647076083e-05,
"loss": 1.3685,
"step": 550000
},
{
"epoch": 2.39,
"learning_rate": 1.0216112149370613e-05,
"loss": 1.399,
"step": 550500
},
{
"epoch": 2.39,
"learning_rate": 1.0179977827980396e-05,
"loss": 1.4163,
"step": 551000
},
{
"epoch": 2.39,
"learning_rate": 1.0143843506590179e-05,
"loss": 1.4019,
"step": 551500
},
{
"epoch": 2.39,
"learning_rate": 1.010770918519996e-05,
"loss": 1.3962,
"step": 552000
},
{
"epoch": 2.4,
"learning_rate": 1.0071574863809743e-05,
"loss": 1.3893,
"step": 552500
},
{
"epoch": 2.4,
"learning_rate": 1.0035440542419527e-05,
"loss": 1.3688,
"step": 553000
},
{
"epoch": 2.4,
"learning_rate": 9.999306221029308e-06,
"loss": 1.3812,
"step": 553500
},
{
"epoch": 2.4,
"learning_rate": 9.963171899639091e-06,
"loss": 1.4005,
"step": 554000
},
{
"epoch": 2.4,
"learning_rate": 9.927037578248874e-06,
"loss": 1.3756,
"step": 554500
},
{
"epoch": 2.41,
"learning_rate": 9.890903256858657e-06,
"loss": 1.3753,
"step": 555000
},
{
"epoch": 2.41,
"learning_rate": 9.854768935468439e-06,
"loss": 1.4005,
"step": 555500
},
{
"epoch": 2.41,
"learning_rate": 9.818634614078222e-06,
"loss": 1.4143,
"step": 556000
},
{
"epoch": 2.41,
"learning_rate": 9.782500292688005e-06,
"loss": 1.3608,
"step": 556500
},
{
"epoch": 2.42,
"learning_rate": 9.746365971297786e-06,
"loss": 1.4235,
"step": 557000
},
{
"epoch": 2.42,
"learning_rate": 9.710231649907568e-06,
"loss": 1.4031,
"step": 557500
},
{
"epoch": 2.42,
"learning_rate": 9.67409732851735e-06,
"loss": 1.3783,
"step": 558000
},
{
"epoch": 2.42,
"learning_rate": 9.637963007127134e-06,
"loss": 1.4141,
"step": 558500
},
{
"epoch": 2.42,
"learning_rate": 9.601828685736917e-06,
"loss": 1.4845,
"step": 559000
},
{
"epoch": 2.43,
"learning_rate": 9.565694364346698e-06,
"loss": 1.403,
"step": 559500
},
{
"epoch": 2.43,
"learning_rate": 9.529560042956481e-06,
"loss": 1.399,
"step": 560000
},
{
"epoch": 2.43,
"learning_rate": 9.493425721566264e-06,
"loss": 1.3877,
"step": 560500
},
{
"epoch": 2.43,
"learning_rate": 9.457291400176046e-06,
"loss": 1.3755,
"step": 561000
},
{
"epoch": 2.43,
"learning_rate": 9.421157078785829e-06,
"loss": 1.4109,
"step": 561500
},
{
"epoch": 2.44,
"learning_rate": 9.385022757395612e-06,
"loss": 1.3869,
"step": 562000
},
{
"epoch": 2.44,
"learning_rate": 9.348888436005395e-06,
"loss": 1.3991,
"step": 562500
},
{
"epoch": 2.44,
"learning_rate": 9.312754114615177e-06,
"loss": 1.3921,
"step": 563000
},
{
"epoch": 2.44,
"learning_rate": 9.27661979322496e-06,
"loss": 1.4022,
"step": 563500
},
{
"epoch": 2.45,
"learning_rate": 9.240485471834743e-06,
"loss": 1.4058,
"step": 564000
},
{
"epoch": 2.45,
"learning_rate": 9.204351150444524e-06,
"loss": 1.3632,
"step": 564500
},
{
"epoch": 2.45,
"learning_rate": 9.168216829054307e-06,
"loss": 1.3922,
"step": 565000
},
{
"epoch": 2.45,
"learning_rate": 9.13208250766409e-06,
"loss": 1.3635,
"step": 565500
},
{
"epoch": 2.45,
"learning_rate": 9.095948186273873e-06,
"loss": 1.3999,
"step": 566000
},
{
"epoch": 2.46,
"learning_rate": 9.059813864883655e-06,
"loss": 1.4021,
"step": 566500
},
{
"epoch": 2.46,
"learning_rate": 9.023679543493438e-06,
"loss": 1.3668,
"step": 567000
},
{
"epoch": 2.46,
"learning_rate": 8.987545222103221e-06,
"loss": 1.3657,
"step": 567500
},
{
"epoch": 2.46,
"learning_rate": 8.951410900713002e-06,
"loss": 1.3903,
"step": 568000
},
{
"epoch": 2.47,
"learning_rate": 8.915276579322785e-06,
"loss": 1.4274,
"step": 568500
},
{
"epoch": 2.47,
"learning_rate": 8.879142257932569e-06,
"loss": 1.3791,
"step": 569000
},
{
"epoch": 2.47,
"learning_rate": 8.843007936542352e-06,
"loss": 1.3871,
"step": 569500
},
{
"epoch": 2.47,
"learning_rate": 8.806873615152133e-06,
"loss": 1.3863,
"step": 570000
},
{
"epoch": 2.47,
"learning_rate": 8.770739293761916e-06,
"loss": 1.3893,
"step": 570500
},
{
"epoch": 2.48,
"learning_rate": 8.7346049723717e-06,
"loss": 1.3815,
"step": 571000
},
{
"epoch": 2.48,
"learning_rate": 8.69847065098148e-06,
"loss": 1.4172,
"step": 571500
},
{
"epoch": 2.48,
"learning_rate": 8.662336329591264e-06,
"loss": 1.3357,
"step": 572000
},
{
"epoch": 2.48,
"learning_rate": 8.626202008201047e-06,
"loss": 1.3741,
"step": 572500
},
{
"epoch": 2.48,
"learning_rate": 8.590067686810828e-06,
"loss": 1.3942,
"step": 573000
},
{
"epoch": 2.49,
"learning_rate": 8.553933365420611e-06,
"loss": 1.3493,
"step": 573500
},
{
"epoch": 2.49,
"learning_rate": 8.517799044030393e-06,
"loss": 1.3547,
"step": 574000
},
{
"epoch": 2.49,
"learning_rate": 8.481664722640176e-06,
"loss": 1.3848,
"step": 574500
},
{
"epoch": 2.49,
"learning_rate": 8.445530401249959e-06,
"loss": 1.3652,
"step": 575000
},
{
"epoch": 2.5,
"learning_rate": 8.40939607985974e-06,
"loss": 1.398,
"step": 575500
},
{
"epoch": 2.5,
"learning_rate": 8.373261758469523e-06,
"loss": 1.3569,
"step": 576000
},
{
"epoch": 2.5,
"learning_rate": 8.337127437079307e-06,
"loss": 1.3565,
"step": 576500
},
{
"epoch": 2.5,
"learning_rate": 8.30099311568909e-06,
"loss": 1.3922,
"step": 577000
},
{
"epoch": 2.5,
"learning_rate": 8.264858794298871e-06,
"loss": 1.3579,
"step": 577500
},
{
"epoch": 2.51,
"learning_rate": 8.228724472908654e-06,
"loss": 1.3834,
"step": 578000
},
{
"epoch": 2.51,
"learning_rate": 8.192590151518437e-06,
"loss": 1.3939,
"step": 578500
},
{
"epoch": 2.51,
"learning_rate": 8.156455830128219e-06,
"loss": 1.3715,
"step": 579000
},
{
"epoch": 2.51,
"learning_rate": 8.120321508738002e-06,
"loss": 1.4274,
"step": 579500
},
{
"epoch": 2.51,
"learning_rate": 8.084187187347785e-06,
"loss": 1.3733,
"step": 580000
},
{
"epoch": 2.52,
"learning_rate": 8.048052865957568e-06,
"loss": 1.415,
"step": 580500
},
{
"epoch": 2.52,
"learning_rate": 8.01191854456735e-06,
"loss": 1.4213,
"step": 581000
},
{
"epoch": 2.52,
"learning_rate": 7.975784223177132e-06,
"loss": 1.3705,
"step": 581500
},
{
"epoch": 2.52,
"learning_rate": 7.939649901786915e-06,
"loss": 1.3978,
"step": 582000
},
{
"epoch": 2.53,
"learning_rate": 7.903515580396697e-06,
"loss": 1.3631,
"step": 582500
},
{
"epoch": 2.53,
"learning_rate": 7.86738125900648e-06,
"loss": 1.4069,
"step": 583000
},
{
"epoch": 2.53,
"learning_rate": 7.831246937616263e-06,
"loss": 1.3387,
"step": 583500
},
{
"epoch": 2.53,
"learning_rate": 7.795112616226046e-06,
"loss": 1.3661,
"step": 584000
},
{
"epoch": 2.53,
"learning_rate": 7.758978294835828e-06,
"loss": 1.4038,
"step": 584500
},
{
"epoch": 2.54,
"learning_rate": 7.72284397344561e-06,
"loss": 1.3339,
"step": 585000
},
{
"epoch": 2.54,
"learning_rate": 7.686709652055394e-06,
"loss": 1.3693,
"step": 585500
},
{
"epoch": 2.54,
"learning_rate": 7.650575330665175e-06,
"loss": 1.36,
"step": 586000
},
{
"epoch": 2.54,
"learning_rate": 7.614441009274958e-06,
"loss": 1.3207,
"step": 586500
},
{
"epoch": 2.55,
"learning_rate": 7.578306687884741e-06,
"loss": 1.3437,
"step": 587000
},
{
"epoch": 2.55,
"learning_rate": 7.5421723664945236e-06,
"loss": 1.3696,
"step": 587500
},
{
"epoch": 2.55,
"learning_rate": 7.506038045104307e-06,
"loss": 1.3895,
"step": 588000
},
{
"epoch": 2.55,
"learning_rate": 7.469903723714087e-06,
"loss": 1.3793,
"step": 588500
},
{
"epoch": 2.55,
"learning_rate": 7.43376940232387e-06,
"loss": 1.3608,
"step": 589000
},
{
"epoch": 2.56,
"learning_rate": 7.3976350809336525e-06,
"loss": 1.349,
"step": 589500
},
{
"epoch": 2.56,
"learning_rate": 7.361500759543436e-06,
"loss": 1.3252,
"step": 590000
},
{
"epoch": 2.56,
"learning_rate": 7.325366438153218e-06,
"loss": 1.3703,
"step": 590500
},
{
"epoch": 2.56,
"learning_rate": 7.289232116763001e-06,
"loss": 1.3619,
"step": 591000
},
{
"epoch": 2.56,
"learning_rate": 7.253097795372783e-06,
"loss": 1.3361,
"step": 591500
},
{
"epoch": 2.57,
"learning_rate": 7.2169634739825655e-06,
"loss": 1.3377,
"step": 592000
},
{
"epoch": 2.57,
"learning_rate": 7.1808291525923486e-06,
"loss": 1.3891,
"step": 592500
},
{
"epoch": 2.57,
"learning_rate": 7.144694831202131e-06,
"loss": 1.3632,
"step": 593000
},
{
"epoch": 2.57,
"learning_rate": 7.108560509811914e-06,
"loss": 1.3634,
"step": 593500
},
{
"epoch": 2.58,
"learning_rate": 7.072426188421696e-06,
"loss": 1.3836,
"step": 594000
},
{
"epoch": 2.58,
"learning_rate": 7.036291867031479e-06,
"loss": 1.3712,
"step": 594500
},
{
"epoch": 2.58,
"learning_rate": 7.0001575456412615e-06,
"loss": 1.3641,
"step": 595000
},
{
"epoch": 2.58,
"learning_rate": 6.964023224251045e-06,
"loss": 1.3245,
"step": 595500
},
{
"epoch": 2.58,
"learning_rate": 6.927888902860827e-06,
"loss": 1.343,
"step": 596000
},
{
"epoch": 2.59,
"learning_rate": 6.891754581470609e-06,
"loss": 1.334,
"step": 596500
},
{
"epoch": 2.59,
"learning_rate": 6.855620260080392e-06,
"loss": 1.356,
"step": 597000
},
{
"epoch": 2.59,
"learning_rate": 6.8194859386901744e-06,
"loss": 1.3779,
"step": 597500
},
{
"epoch": 2.59,
"learning_rate": 6.7833516172999575e-06,
"loss": 1.3692,
"step": 598000
},
{
"epoch": 2.6,
"learning_rate": 6.74721729590974e-06,
"loss": 1.3418,
"step": 598500
},
{
"epoch": 2.6,
"learning_rate": 6.711082974519523e-06,
"loss": 1.3658,
"step": 599000
},
{
"epoch": 2.6,
"learning_rate": 6.674948653129305e-06,
"loss": 1.3686,
"step": 599500
},
{
"epoch": 2.6,
"learning_rate": 6.638814331739087e-06,
"loss": 1.3645,
"step": 600000
},
{
"epoch": 2.6,
"learning_rate": 6.6026800103488704e-06,
"loss": 1.3355,
"step": 600500
},
{
"epoch": 2.61,
"learning_rate": 6.566545688958653e-06,
"loss": 1.3503,
"step": 601000
},
{
"epoch": 2.61,
"learning_rate": 6.530411367568436e-06,
"loss": 1.3485,
"step": 601500
},
{
"epoch": 2.61,
"learning_rate": 6.494277046178218e-06,
"loss": 1.361,
"step": 602000
},
{
"epoch": 2.61,
"learning_rate": 6.458142724788001e-06,
"loss": 1.3793,
"step": 602500
},
{
"epoch": 2.61,
"learning_rate": 6.422008403397783e-06,
"loss": 1.3741,
"step": 603000
},
{
"epoch": 2.62,
"learning_rate": 6.385874082007566e-06,
"loss": 1.3382,
"step": 603500
},
{
"epoch": 2.62,
"learning_rate": 6.349739760617347e-06,
"loss": 1.3425,
"step": 604000
},
{
"epoch": 2.62,
"learning_rate": 6.31360543922713e-06,
"loss": 1.3536,
"step": 604500
},
{
"epoch": 2.62,
"learning_rate": 6.277471117836912e-06,
"loss": 1.3434,
"step": 605000
},
{
"epoch": 2.63,
"learning_rate": 6.2413367964466955e-06,
"loss": 1.3411,
"step": 605500
},
{
"epoch": 2.63,
"learning_rate": 6.2052024750564786e-06,
"loss": 1.3767,
"step": 606000
},
{
"epoch": 2.63,
"learning_rate": 6.169068153666261e-06,
"loss": 1.37,
"step": 606500
},
{
"epoch": 2.63,
"learning_rate": 6.132933832276044e-06,
"loss": 1.4048,
"step": 607000
},
{
"epoch": 2.63,
"learning_rate": 6.096799510885826e-06,
"loss": 1.3918,
"step": 607500
},
{
"epoch": 2.64,
"learning_rate": 6.060665189495608e-06,
"loss": 1.3642,
"step": 608000
},
{
"epoch": 2.64,
"learning_rate": 6.024530868105391e-06,
"loss": 1.3937,
"step": 608500
},
{
"epoch": 2.64,
"learning_rate": 5.988396546715174e-06,
"loss": 1.3523,
"step": 609000
},
{
"epoch": 2.64,
"learning_rate": 5.952262225324956e-06,
"loss": 1.3306,
"step": 609500
},
{
"epoch": 2.65,
"learning_rate": 5.916127903934739e-06,
"loss": 1.3811,
"step": 610000
},
{
"epoch": 2.65,
"learning_rate": 5.879993582544521e-06,
"loss": 1.3033,
"step": 610500
},
{
"epoch": 2.65,
"learning_rate": 5.8438592611543036e-06,
"loss": 1.3555,
"step": 611000
},
{
"epoch": 2.65,
"learning_rate": 5.807724939764087e-06,
"loss": 1.3746,
"step": 611500
},
{
"epoch": 2.65,
"learning_rate": 5.771590618373869e-06,
"loss": 1.3293,
"step": 612000
},
{
"epoch": 2.66,
"learning_rate": 5.735456296983652e-06,
"loss": 1.3661,
"step": 612500
},
{
"epoch": 2.66,
"learning_rate": 5.699321975593434e-06,
"loss": 1.3856,
"step": 613000
},
{
"epoch": 2.66,
"learning_rate": 5.663187654203217e-06,
"loss": 1.334,
"step": 613500
},
{
"epoch": 2.66,
"learning_rate": 5.627053332813e-06,
"loss": 1.3603,
"step": 614000
},
{
"epoch": 2.66,
"learning_rate": 5.590919011422782e-06,
"loss": 1.3682,
"step": 614500
},
{
"epoch": 2.67,
"learning_rate": 5.554784690032565e-06,
"loss": 1.3803,
"step": 615000
},
{
"epoch": 2.67,
"learning_rate": 5.518650368642347e-06,
"loss": 1.3569,
"step": 615500
},
{
"epoch": 2.67,
"learning_rate": 5.482516047252129e-06,
"loss": 1.3854,
"step": 616000
},
{
"epoch": 2.67,
"learning_rate": 5.446381725861912e-06,
"loss": 1.3391,
"step": 616500
},
{
"epoch": 2.68,
"learning_rate": 5.410247404471695e-06,
"loss": 1.3513,
"step": 617000
},
{
"epoch": 2.68,
"learning_rate": 5.374113083081477e-06,
"loss": 1.3653,
"step": 617500
},
{
"epoch": 2.68,
"learning_rate": 5.33797876169126e-06,
"loss": 1.3811,
"step": 618000
},
{
"epoch": 2.68,
"learning_rate": 5.301844440301042e-06,
"loss": 1.3527,
"step": 618500
},
{
"epoch": 2.68,
"learning_rate": 5.2657101189108254e-06,
"loss": 1.3779,
"step": 619000
},
{
"epoch": 2.69,
"learning_rate": 5.229575797520608e-06,
"loss": 1.3391,
"step": 619500
},
{
"epoch": 2.69,
"learning_rate": 5.19344147613039e-06,
"loss": 1.3906,
"step": 620000
},
{
"epoch": 2.69,
"learning_rate": 5.157307154740173e-06,
"loss": 1.3632,
"step": 620500
},
{
"epoch": 2.69,
"learning_rate": 5.121172833349955e-06,
"loss": 1.3865,
"step": 621000
},
{
"epoch": 2.69,
"learning_rate": 5.085038511959738e-06,
"loss": 1.3753,
"step": 621500
},
{
"epoch": 2.7,
"learning_rate": 5.048904190569521e-06,
"loss": 1.3558,
"step": 622000
},
{
"epoch": 2.7,
"learning_rate": 5.012769869179304e-06,
"loss": 1.371,
"step": 622500
},
{
"epoch": 2.7,
"learning_rate": 4.976635547789086e-06,
"loss": 1.3011,
"step": 623000
},
{
"epoch": 2.7,
"learning_rate": 4.940501226398868e-06,
"loss": 1.3495,
"step": 623500
},
{
"epoch": 2.71,
"learning_rate": 4.9043669050086504e-06,
"loss": 1.33,
"step": 624000
},
{
"epoch": 2.71,
"learning_rate": 4.868232583618433e-06,
"loss": 1.3437,
"step": 624500
},
{
"epoch": 2.71,
"learning_rate": 4.832098262228216e-06,
"loss": 1.3375,
"step": 625000
},
{
"epoch": 2.71,
"learning_rate": 4.795963940837998e-06,
"loss": 1.3019,
"step": 625500
},
{
"epoch": 2.71,
"learning_rate": 4.759829619447781e-06,
"loss": 1.3496,
"step": 626000
},
{
"epoch": 2.72,
"learning_rate": 4.723695298057563e-06,
"loss": 1.3469,
"step": 626500
},
{
"epoch": 2.72,
"learning_rate": 4.6875609766673465e-06,
"loss": 1.3284,
"step": 627000
},
{
"epoch": 2.72,
"learning_rate": 4.651426655277129e-06,
"loss": 1.3144,
"step": 627500
},
{
"epoch": 2.72,
"learning_rate": 4.615292333886912e-06,
"loss": 1.345,
"step": 628000
},
{
"epoch": 2.73,
"learning_rate": 4.579158012496694e-06,
"loss": 1.3552,
"step": 628500
},
{
"epoch": 2.73,
"learning_rate": 4.543023691106476e-06,
"loss": 1.3143,
"step": 629000
},
{
"epoch": 2.73,
"learning_rate": 4.506889369716259e-06,
"loss": 1.36,
"step": 629500
},
{
"epoch": 2.73,
"learning_rate": 4.470755048326042e-06,
"loss": 1.3315,
"step": 630000
},
{
"epoch": 2.73,
"learning_rate": 4.434620726935825e-06,
"loss": 1.3772,
"step": 630500
},
{
"epoch": 2.74,
"learning_rate": 4.398486405545607e-06,
"loss": 1.3508,
"step": 631000
},
{
"epoch": 2.74,
"learning_rate": 4.362352084155389e-06,
"loss": 1.3375,
"step": 631500
},
{
"epoch": 2.74,
"learning_rate": 4.3262177627651715e-06,
"loss": 1.3561,
"step": 632000
},
{
"epoch": 2.74,
"learning_rate": 4.2900834413749546e-06,
"loss": 1.3272,
"step": 632500
},
{
"epoch": 2.74,
"learning_rate": 4.253949119984737e-06,
"loss": 1.3409,
"step": 633000
},
{
"epoch": 2.75,
"learning_rate": 4.217814798594519e-06,
"loss": 1.3422,
"step": 633500
},
{
"epoch": 2.75,
"learning_rate": 4.181680477204302e-06,
"loss": 1.32,
"step": 634000
},
{
"epoch": 2.75,
"learning_rate": 4.145546155814084e-06,
"loss": 1.325,
"step": 634500
},
{
"epoch": 2.75,
"learning_rate": 4.1094118344238675e-06,
"loss": 1.372,
"step": 635000
},
{
"epoch": 2.76,
"learning_rate": 4.07327751303365e-06,
"loss": 1.3224,
"step": 635500
},
{
"epoch": 2.76,
"learning_rate": 4.037143191643433e-06,
"loss": 1.3448,
"step": 636000
},
{
"epoch": 2.76,
"learning_rate": 4.001008870253215e-06,
"loss": 1.3475,
"step": 636500
},
{
"epoch": 2.76,
"learning_rate": 3.964874548862998e-06,
"loss": 1.347,
"step": 637000
},
{
"epoch": 2.76,
"learning_rate": 3.9287402274727804e-06,
"loss": 1.3446,
"step": 637500
},
{
"epoch": 2.77,
"learning_rate": 3.892605906082563e-06,
"loss": 1.3413,
"step": 638000
},
{
"epoch": 2.77,
"learning_rate": 3.856471584692346e-06,
"loss": 1.3541,
"step": 638500
},
{
"epoch": 2.77,
"learning_rate": 3.820337263302128e-06,
"loss": 1.3282,
"step": 639000
},
{
"epoch": 2.77,
"learning_rate": 3.7842029419119103e-06,
"loss": 1.2956,
"step": 639500
},
{
"epoch": 2.78,
"learning_rate": 3.748068620521693e-06,
"loss": 1.3368,
"step": 640000
},
{
"epoch": 2.78,
"learning_rate": 3.711934299131475e-06,
"loss": 1.322,
"step": 640500
},
{
"epoch": 2.78,
"learning_rate": 3.675799977741258e-06,
"loss": 1.3089,
"step": 641000
},
{
"epoch": 2.78,
"learning_rate": 3.6396656563510405e-06,
"loss": 1.2995,
"step": 641500
},
{
"epoch": 2.78,
"learning_rate": 3.603531334960823e-06,
"loss": 1.3611,
"step": 642000
},
{
"epoch": 2.79,
"learning_rate": 3.567397013570606e-06,
"loss": 1.3749,
"step": 642500
},
{
"epoch": 2.79,
"learning_rate": 3.5312626921803885e-06,
"loss": 1.3495,
"step": 643000
},
{
"epoch": 2.79,
"learning_rate": 3.495128370790171e-06,
"loss": 1.3715,
"step": 643500
},
{
"epoch": 2.79,
"learning_rate": 3.458994049399954e-06,
"loss": 1.3345,
"step": 644000
},
{
"epoch": 2.79,
"learning_rate": 3.422859728009736e-06,
"loss": 1.3122,
"step": 644500
},
{
"epoch": 2.8,
"learning_rate": 3.386725406619519e-06,
"loss": 1.3306,
"step": 645000
},
{
"epoch": 2.8,
"learning_rate": 3.3505910852293015e-06,
"loss": 1.3305,
"step": 645500
},
{
"epoch": 2.8,
"learning_rate": 3.314456763839084e-06,
"loss": 1.3662,
"step": 646000
},
{
"epoch": 2.8,
"learning_rate": 3.278322442448867e-06,
"loss": 1.341,
"step": 646500
},
{
"epoch": 2.81,
"learning_rate": 3.2421881210586495e-06,
"loss": 1.3767,
"step": 647000
},
{
"epoch": 2.81,
"learning_rate": 3.2060537996684313e-06,
"loss": 1.3321,
"step": 647500
},
{
"epoch": 2.81,
"learning_rate": 3.169919478278214e-06,
"loss": 1.3631,
"step": 648000
},
{
"epoch": 2.81,
"learning_rate": 3.1337851568879966e-06,
"loss": 1.3548,
"step": 648500
},
{
"epoch": 2.81,
"learning_rate": 3.0976508354977793e-06,
"loss": 1.3302,
"step": 649000
},
{
"epoch": 2.82,
"learning_rate": 3.061516514107562e-06,
"loss": 1.3043,
"step": 649500
},
{
"epoch": 2.82,
"learning_rate": 3.0253821927173442e-06,
"loss": 1.3838,
"step": 650000
},
{
"epoch": 2.82,
"learning_rate": 2.989247871327127e-06,
"loss": 1.3528,
"step": 650500
},
{
"epoch": 2.82,
"learning_rate": 2.9531135499369096e-06,
"loss": 1.2877,
"step": 651000
},
{
"epoch": 2.82,
"learning_rate": 2.9169792285466922e-06,
"loss": 1.331,
"step": 651500
},
{
"epoch": 2.83,
"learning_rate": 2.880844907156475e-06,
"loss": 1.3573,
"step": 652000
},
{
"epoch": 2.83,
"learning_rate": 2.8447105857662576e-06,
"loss": 1.3574,
"step": 652500
},
{
"epoch": 2.83,
"learning_rate": 2.8085762643760402e-06,
"loss": 1.3271,
"step": 653000
},
{
"epoch": 2.83,
"learning_rate": 2.7724419429858225e-06,
"loss": 1.3175,
"step": 653500
},
{
"epoch": 2.84,
"learning_rate": 2.736307621595605e-06,
"loss": 1.3847,
"step": 654000
},
{
"epoch": 2.84,
"learning_rate": 2.7001733002053874e-06,
"loss": 1.3711,
"step": 654500
},
{
"epoch": 2.84,
"learning_rate": 2.66403897881517e-06,
"loss": 1.3588,
"step": 655000
},
{
"epoch": 2.84,
"learning_rate": 2.6279046574249527e-06,
"loss": 1.3004,
"step": 655500
},
{
"epoch": 2.84,
"learning_rate": 2.5917703360347354e-06,
"loss": 1.3099,
"step": 656000
},
{
"epoch": 2.85,
"learning_rate": 2.555636014644518e-06,
"loss": 1.3345,
"step": 656500
},
{
"epoch": 2.85,
"learning_rate": 2.5195016932543003e-06,
"loss": 1.3437,
"step": 657000
},
{
"epoch": 2.85,
"learning_rate": 2.483367371864083e-06,
"loss": 1.278,
"step": 657500
},
{
"epoch": 2.85,
"learning_rate": 2.4472330504738657e-06,
"loss": 1.3061,
"step": 658000
},
{
"epoch": 2.86,
"learning_rate": 2.4110987290836483e-06,
"loss": 1.3336,
"step": 658500
},
{
"epoch": 2.86,
"learning_rate": 2.3749644076934306e-06,
"loss": 1.3328,
"step": 659000
},
{
"epoch": 2.86,
"learning_rate": 2.3388300863032133e-06,
"loss": 1.3399,
"step": 659500
},
{
"epoch": 2.86,
"learning_rate": 2.302695764912996e-06,
"loss": 1.3307,
"step": 660000
},
{
"epoch": 2.86,
"learning_rate": 2.2665614435227786e-06,
"loss": 1.332,
"step": 660500
},
{
"epoch": 2.87,
"learning_rate": 2.230427122132561e-06,
"loss": 1.3241,
"step": 661000
},
{
"epoch": 2.87,
"learning_rate": 2.1942928007423435e-06,
"loss": 1.3303,
"step": 661500
},
{
"epoch": 2.87,
"learning_rate": 2.158158479352126e-06,
"loss": 1.3192,
"step": 662000
},
{
"epoch": 2.87,
"learning_rate": 2.122024157961909e-06,
"loss": 1.3447,
"step": 662500
},
{
"epoch": 2.87,
"learning_rate": 2.0858898365716915e-06,
"loss": 1.3289,
"step": 663000
},
{
"epoch": 2.88,
"learning_rate": 2.0497555151814738e-06,
"loss": 1.3171,
"step": 663500
},
{
"epoch": 2.88,
"learning_rate": 2.0136211937912565e-06,
"loss": 1.3244,
"step": 664000
},
{
"epoch": 2.88,
"learning_rate": 1.977486872401039e-06,
"loss": 1.3333,
"step": 664500
},
{
"epoch": 2.88,
"learning_rate": 1.9413525510108214e-06,
"loss": 1.3438,
"step": 665000
},
{
"epoch": 2.89,
"learning_rate": 1.905218229620604e-06,
"loss": 1.3007,
"step": 665500
},
{
"epoch": 2.89,
"learning_rate": 1.8690839082303867e-06,
"loss": 1.325,
"step": 666000
},
{
"epoch": 2.89,
"learning_rate": 1.8329495868401694e-06,
"loss": 1.3181,
"step": 666500
},
{
"epoch": 2.89,
"learning_rate": 1.7968152654499518e-06,
"loss": 1.2825,
"step": 667000
},
{
"epoch": 2.89,
"learning_rate": 1.7606809440597345e-06,
"loss": 1.2894,
"step": 667500
},
{
"epoch": 2.9,
"learning_rate": 1.7245466226695172e-06,
"loss": 1.3206,
"step": 668000
},
{
"epoch": 2.9,
"learning_rate": 1.6884123012792998e-06,
"loss": 1.3114,
"step": 668500
},
{
"epoch": 2.9,
"learning_rate": 1.652277979889082e-06,
"loss": 1.3253,
"step": 669000
},
{
"epoch": 2.9,
"learning_rate": 1.6161436584988646e-06,
"loss": 1.371,
"step": 669500
},
{
"epoch": 2.91,
"learning_rate": 1.5800093371086472e-06,
"loss": 1.3003,
"step": 670000
},
{
"epoch": 2.91,
"learning_rate": 1.54387501571843e-06,
"loss": 1.2888,
"step": 670500
},
{
"epoch": 2.91,
"learning_rate": 1.5077406943282126e-06,
"loss": 1.3108,
"step": 671000
},
{
"epoch": 2.91,
"learning_rate": 1.471606372937995e-06,
"loss": 1.3098,
"step": 671500
},
{
"epoch": 2.91,
"learning_rate": 1.4354720515477775e-06,
"loss": 1.3063,
"step": 672000
},
{
"epoch": 2.92,
"learning_rate": 1.3993377301575602e-06,
"loss": 1.3471,
"step": 672500
},
{
"epoch": 2.92,
"learning_rate": 1.3632034087673428e-06,
"loss": 1.3224,
"step": 673000
},
{
"epoch": 2.92,
"learning_rate": 1.3270690873771253e-06,
"loss": 1.3253,
"step": 673500
},
{
"epoch": 2.92,
"learning_rate": 1.2909347659869077e-06,
"loss": 1.3317,
"step": 674000
},
{
"epoch": 2.92,
"learning_rate": 1.2548004445966904e-06,
"loss": 1.3157,
"step": 674500
},
{
"epoch": 2.93,
"learning_rate": 1.218666123206473e-06,
"loss": 1.3168,
"step": 675000
},
{
"epoch": 2.93,
"learning_rate": 1.1825318018162558e-06,
"loss": 1.3336,
"step": 675500
},
{
"epoch": 2.93,
"learning_rate": 1.1463974804260382e-06,
"loss": 1.2913,
"step": 676000
},
{
"epoch": 2.93,
"learning_rate": 1.1102631590358207e-06,
"loss": 1.2924,
"step": 676500
},
{
"epoch": 2.94,
"learning_rate": 1.0741288376456033e-06,
"loss": 1.2916,
"step": 677000
},
{
"epoch": 2.94,
"learning_rate": 1.037994516255386e-06,
"loss": 1.3312,
"step": 677500
},
{
"epoch": 2.94,
"learning_rate": 1.0018601948651685e-06,
"loss": 1.3616,
"step": 678000
},
{
"epoch": 2.94,
"learning_rate": 9.65725873474951e-07,
"loss": 1.3382,
"step": 678500
},
{
"epoch": 2.94,
"learning_rate": 9.295915520847336e-07,
"loss": 1.3094,
"step": 679000
},
{
"epoch": 2.95,
"learning_rate": 8.934572306945161e-07,
"loss": 1.2849,
"step": 679500
},
{
"epoch": 2.95,
"learning_rate": 8.573229093042987e-07,
"loss": 1.3214,
"step": 680000
},
{
"epoch": 2.95,
"learning_rate": 8.211885879140813e-07,
"loss": 1.346,
"step": 680500
},
{
"epoch": 2.95,
"learning_rate": 7.85054266523864e-07,
"loss": 1.3084,
"step": 681000
},
{
"epoch": 2.96,
"learning_rate": 7.489199451336464e-07,
"loss": 1.3189,
"step": 681500
},
{
"epoch": 2.96,
"learning_rate": 7.12785623743429e-07,
"loss": 1.3384,
"step": 682000
},
{
"epoch": 2.96,
"learning_rate": 6.766513023532115e-07,
"loss": 1.3081,
"step": 682500
},
{
"epoch": 2.96,
"learning_rate": 6.405169809629941e-07,
"loss": 1.3347,
"step": 683000
},
{
"epoch": 2.96,
"learning_rate": 6.043826595727768e-07,
"loss": 1.2949,
"step": 683500
},
{
"epoch": 2.97,
"learning_rate": 5.682483381825592e-07,
"loss": 1.3019,
"step": 684000
},
{
"epoch": 2.97,
"learning_rate": 5.321140167923419e-07,
"loss": 1.318,
"step": 684500
},
{
"epoch": 2.97,
"learning_rate": 4.959796954021244e-07,
"loss": 1.3188,
"step": 685000
},
{
"epoch": 2.97,
"learning_rate": 4.5984537401190704e-07,
"loss": 1.3237,
"step": 685500
},
{
"epoch": 2.97,
"learning_rate": 4.2371105262168955e-07,
"loss": 1.3194,
"step": 686000
},
{
"epoch": 2.98,
"learning_rate": 3.8757673123147217e-07,
"loss": 1.2914,
"step": 686500
},
{
"epoch": 2.98,
"learning_rate": 3.5144240984125473e-07,
"loss": 1.2938,
"step": 687000
},
{
"epoch": 2.98,
"learning_rate": 3.153080884510373e-07,
"loss": 1.324,
"step": 687500
},
{
"epoch": 2.98,
"learning_rate": 2.7917376706081986e-07,
"loss": 1.3568,
"step": 688000
},
{
"epoch": 2.99,
"learning_rate": 2.430394456706024e-07,
"loss": 1.2937,
"step": 688500
},
{
"epoch": 2.99,
"learning_rate": 2.0690512428038502e-07,
"loss": 1.3336,
"step": 689000
},
{
"epoch": 2.99,
"learning_rate": 1.7077080289016755e-07,
"loss": 1.3009,
"step": 689500
},
{
"epoch": 2.99,
"learning_rate": 1.3463648149995015e-07,
"loss": 1.3006,
"step": 690000
},
{
"epoch": 2.99,
"learning_rate": 9.850216010973271e-08,
"loss": 1.319,
"step": 690500
},
{
"epoch": 3.0,
"learning_rate": 6.236783871951529e-08,
"loss": 1.3137,
"step": 691000
},
{
"epoch": 3.0,
"learning_rate": 2.6233517329297856e-08,
"loss": 1.3008,
"step": 691500
},
{
"epoch": 3.0,
"step": 691863,
"total_flos": 1.4060904033953434e+17,
"train_loss": 1.5596977327828456,
"train_runtime": 96781.0119,
"train_samples_per_second": 14.297,
"train_steps_per_second": 7.149
}
],
"max_steps": 691863,
"num_train_epochs": 3,
"total_flos": 1.4060904033953434e+17,
"trial_name": null,
"trial_params": null
}