yesidcanoc's picture
Upload 7 files
123d7a4
{
"best_metric": 2.2859742641448975,
"best_model_checkpoint": "../models/swin_NO_F_GPT_image_captioning\\checkpoint-59176",
"epoch": 1.0,
"global_step": 59176,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.0000000000000004e-08,
"loss": 1.9115,
"step": 100
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.8638,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 1.5000000000000002e-07,
"loss": 1.8939,
"step": 300
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.94,
"step": 400
},
{
"epoch": 0.01,
"learning_rate": 2.5000000000000004e-07,
"loss": 1.8921,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.8659,
"step": 600
},
{
"epoch": 0.01,
"learning_rate": 3.5000000000000004e-07,
"loss": 1.8387,
"step": 700
},
{
"epoch": 0.01,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.8242,
"step": 800
},
{
"epoch": 0.02,
"learning_rate": 4.5000000000000003e-07,
"loss": 1.813,
"step": 900
},
{
"epoch": 0.02,
"learning_rate": 5.000000000000001e-07,
"loss": 1.8073,
"step": 1000
},
{
"epoch": 0.02,
"learning_rate": 5.5e-07,
"loss": 1.7857,
"step": 1100
},
{
"epoch": 0.02,
"learning_rate": 6.000000000000001e-07,
"loss": 1.81,
"step": 1200
},
{
"epoch": 0.02,
"learning_rate": 6.5e-07,
"loss": 1.721,
"step": 1300
},
{
"epoch": 0.02,
"learning_rate": 7.000000000000001e-07,
"loss": 1.7273,
"step": 1400
},
{
"epoch": 0.03,
"learning_rate": 7.5e-07,
"loss": 1.7144,
"step": 1500
},
{
"epoch": 0.03,
"learning_rate": 8.000000000000001e-07,
"loss": 1.737,
"step": 1600
},
{
"epoch": 0.03,
"learning_rate": 8.500000000000001e-07,
"loss": 1.68,
"step": 1700
},
{
"epoch": 0.03,
"learning_rate": 9.000000000000001e-07,
"loss": 1.6471,
"step": 1800
},
{
"epoch": 0.03,
"learning_rate": 9.500000000000001e-07,
"loss": 1.7123,
"step": 1900
},
{
"epoch": 0.03,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.6329,
"step": 2000
},
{
"epoch": 0.04,
"learning_rate": 1.0500000000000001e-06,
"loss": 1.6601,
"step": 2100
},
{
"epoch": 0.04,
"learning_rate": 1.1e-06,
"loss": 1.6305,
"step": 2200
},
{
"epoch": 0.04,
"learning_rate": 1.1500000000000002e-06,
"loss": 1.6655,
"step": 2300
},
{
"epoch": 0.04,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.6398,
"step": 2400
},
{
"epoch": 0.04,
"learning_rate": 1.25e-06,
"loss": 1.6253,
"step": 2500
},
{
"epoch": 0.04,
"learning_rate": 1.3e-06,
"loss": 1.6158,
"step": 2600
},
{
"epoch": 0.05,
"learning_rate": 1.3500000000000002e-06,
"loss": 1.5647,
"step": 2700
},
{
"epoch": 0.05,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.5577,
"step": 2800
},
{
"epoch": 0.05,
"learning_rate": 1.45e-06,
"loss": 1.5262,
"step": 2900
},
{
"epoch": 0.05,
"learning_rate": 1.5e-06,
"loss": 1.5114,
"step": 3000
},
{
"epoch": 0.05,
"learning_rate": 1.5500000000000002e-06,
"loss": 1.4956,
"step": 3100
},
{
"epoch": 0.05,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.5055,
"step": 3200
},
{
"epoch": 0.06,
"learning_rate": 1.6500000000000003e-06,
"loss": 1.4823,
"step": 3300
},
{
"epoch": 0.06,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.4824,
"step": 3400
},
{
"epoch": 0.06,
"learning_rate": 1.75e-06,
"loss": 1.4526,
"step": 3500
},
{
"epoch": 0.06,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.445,
"step": 3600
},
{
"epoch": 0.06,
"learning_rate": 1.85e-06,
"loss": 1.4739,
"step": 3700
},
{
"epoch": 0.06,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.3971,
"step": 3800
},
{
"epoch": 0.07,
"learning_rate": 1.9500000000000004e-06,
"loss": 1.4285,
"step": 3900
},
{
"epoch": 0.07,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.3709,
"step": 4000
},
{
"epoch": 0.07,
"learning_rate": 2.05e-06,
"loss": 1.4105,
"step": 4100
},
{
"epoch": 0.07,
"learning_rate": 2.1000000000000002e-06,
"loss": 1.3386,
"step": 4200
},
{
"epoch": 0.07,
"learning_rate": 2.15e-06,
"loss": 1.3688,
"step": 4300
},
{
"epoch": 0.07,
"learning_rate": 2.2e-06,
"loss": 1.3148,
"step": 4400
},
{
"epoch": 0.08,
"learning_rate": 2.25e-06,
"loss": 1.3506,
"step": 4500
},
{
"epoch": 0.08,
"learning_rate": 2.3000000000000004e-06,
"loss": 1.3414,
"step": 4600
},
{
"epoch": 0.08,
"learning_rate": 2.35e-06,
"loss": 1.2912,
"step": 4700
},
{
"epoch": 0.08,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.2854,
"step": 4800
},
{
"epoch": 0.08,
"learning_rate": 2.4500000000000003e-06,
"loss": 1.3153,
"step": 4900
},
{
"epoch": 0.08,
"learning_rate": 2.5e-06,
"loss": 1.2519,
"step": 5000
},
{
"epoch": 0.09,
"learning_rate": 2.55e-06,
"loss": 1.2903,
"step": 5100
},
{
"epoch": 0.09,
"learning_rate": 2.6e-06,
"loss": 1.2432,
"step": 5200
},
{
"epoch": 0.09,
"learning_rate": 2.6500000000000005e-06,
"loss": 1.2559,
"step": 5300
},
{
"epoch": 0.09,
"learning_rate": 2.7000000000000004e-06,
"loss": 1.219,
"step": 5400
},
{
"epoch": 0.09,
"learning_rate": 2.7500000000000004e-06,
"loss": 1.2051,
"step": 5500
},
{
"epoch": 0.09,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.1742,
"step": 5600
},
{
"epoch": 0.1,
"learning_rate": 2.85e-06,
"loss": 1.2276,
"step": 5700
},
{
"epoch": 0.1,
"learning_rate": 2.9e-06,
"loss": 1.1489,
"step": 5800
},
{
"epoch": 0.1,
"learning_rate": 2.95e-06,
"loss": 1.114,
"step": 5900
},
{
"epoch": 0.1,
"learning_rate": 3e-06,
"loss": 1.1554,
"step": 6000
},
{
"epoch": 0.1,
"learning_rate": 3.05e-06,
"loss": 1.148,
"step": 6100
},
{
"epoch": 0.1,
"learning_rate": 3.1000000000000004e-06,
"loss": 1.1117,
"step": 6200
},
{
"epoch": 0.11,
"learning_rate": 3.1500000000000003e-06,
"loss": 1.1639,
"step": 6300
},
{
"epoch": 0.11,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.1183,
"step": 6400
},
{
"epoch": 0.11,
"learning_rate": 3.2500000000000002e-06,
"loss": 1.1068,
"step": 6500
},
{
"epoch": 0.11,
"learning_rate": 3.3000000000000006e-06,
"loss": 1.0429,
"step": 6600
},
{
"epoch": 0.11,
"learning_rate": 3.3500000000000005e-06,
"loss": 1.048,
"step": 6700
},
{
"epoch": 0.11,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.0517,
"step": 6800
},
{
"epoch": 0.12,
"learning_rate": 3.45e-06,
"loss": 1.0875,
"step": 6900
},
{
"epoch": 0.12,
"learning_rate": 3.5e-06,
"loss": 1.0267,
"step": 7000
},
{
"epoch": 0.12,
"learning_rate": 3.5500000000000003e-06,
"loss": 1.0076,
"step": 7100
},
{
"epoch": 0.12,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.0332,
"step": 7200
},
{
"epoch": 0.12,
"learning_rate": 3.65e-06,
"loss": 1.022,
"step": 7300
},
{
"epoch": 0.13,
"learning_rate": 3.7e-06,
"loss": 0.9922,
"step": 7400
},
{
"epoch": 0.13,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.9827,
"step": 7500
},
{
"epoch": 0.13,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.9964,
"step": 7600
},
{
"epoch": 0.13,
"learning_rate": 3.85e-06,
"loss": 0.9998,
"step": 7700
},
{
"epoch": 0.13,
"learning_rate": 3.900000000000001e-06,
"loss": 0.9645,
"step": 7800
},
{
"epoch": 0.13,
"learning_rate": 3.95e-06,
"loss": 0.9919,
"step": 7900
},
{
"epoch": 0.14,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9206,
"step": 8000
},
{
"epoch": 0.14,
"learning_rate": 4.05e-06,
"loss": 0.9339,
"step": 8100
},
{
"epoch": 0.14,
"learning_rate": 4.1e-06,
"loss": 0.8937,
"step": 8200
},
{
"epoch": 0.14,
"learning_rate": 4.15e-06,
"loss": 0.8807,
"step": 8300
},
{
"epoch": 0.14,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.902,
"step": 8400
},
{
"epoch": 0.14,
"learning_rate": 4.25e-06,
"loss": 0.9295,
"step": 8500
},
{
"epoch": 0.15,
"learning_rate": 4.3e-06,
"loss": 0.8799,
"step": 8600
},
{
"epoch": 0.15,
"learning_rate": 4.350000000000001e-06,
"loss": 0.8545,
"step": 8700
},
{
"epoch": 0.15,
"learning_rate": 4.4e-06,
"loss": 0.8779,
"step": 8800
},
{
"epoch": 0.15,
"learning_rate": 4.450000000000001e-06,
"loss": 0.8964,
"step": 8900
},
{
"epoch": 0.15,
"learning_rate": 4.5e-06,
"loss": 0.8306,
"step": 9000
},
{
"epoch": 0.15,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.8146,
"step": 9100
},
{
"epoch": 0.16,
"learning_rate": 4.600000000000001e-06,
"loss": 0.8287,
"step": 9200
},
{
"epoch": 0.16,
"learning_rate": 4.65e-06,
"loss": 0.8235,
"step": 9300
},
{
"epoch": 0.16,
"learning_rate": 4.7e-06,
"loss": 0.8055,
"step": 9400
},
{
"epoch": 0.16,
"learning_rate": 4.75e-06,
"loss": 0.8282,
"step": 9500
},
{
"epoch": 0.16,
"learning_rate": 4.800000000000001e-06,
"loss": 0.8218,
"step": 9600
},
{
"epoch": 0.16,
"learning_rate": 4.85e-06,
"loss": 0.8294,
"step": 9700
},
{
"epoch": 0.17,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.8133,
"step": 9800
},
{
"epoch": 0.17,
"learning_rate": 4.95e-06,
"loss": 0.7674,
"step": 9900
},
{
"epoch": 0.17,
"learning_rate": 5e-06,
"loss": 0.7761,
"step": 10000
},
{
"epoch": 0.17,
"learning_rate": 4.989832438587929e-06,
"loss": 0.7799,
"step": 10100
},
{
"epoch": 0.17,
"learning_rate": 4.979664877175859e-06,
"loss": 0.8074,
"step": 10200
},
{
"epoch": 0.17,
"learning_rate": 4.9694973157637875e-06,
"loss": 0.7971,
"step": 10300
},
{
"epoch": 0.18,
"learning_rate": 4.959329754351716e-06,
"loss": 0.8144,
"step": 10400
},
{
"epoch": 0.18,
"learning_rate": 4.949162192939646e-06,
"loss": 0.7849,
"step": 10500
},
{
"epoch": 0.18,
"learning_rate": 4.938994631527575e-06,
"loss": 0.8072,
"step": 10600
},
{
"epoch": 0.18,
"learning_rate": 4.928827070115504e-06,
"loss": 0.7639,
"step": 10700
},
{
"epoch": 0.18,
"learning_rate": 4.918659508703433e-06,
"loss": 0.8055,
"step": 10800
},
{
"epoch": 0.18,
"learning_rate": 4.908491947291363e-06,
"loss": 0.8342,
"step": 10900
},
{
"epoch": 0.19,
"learning_rate": 4.898324385879291e-06,
"loss": 0.8107,
"step": 11000
},
{
"epoch": 0.19,
"learning_rate": 4.88815682446722e-06,
"loss": 0.8115,
"step": 11100
},
{
"epoch": 0.19,
"learning_rate": 4.87798926305515e-06,
"loss": 0.8227,
"step": 11200
},
{
"epoch": 0.19,
"learning_rate": 4.8678217016430785e-06,
"loss": 0.8339,
"step": 11300
},
{
"epoch": 0.19,
"learning_rate": 4.857654140231007e-06,
"loss": 0.8013,
"step": 11400
},
{
"epoch": 0.19,
"learning_rate": 4.847486578818936e-06,
"loss": 0.7854,
"step": 11500
},
{
"epoch": 0.2,
"learning_rate": 4.837319017406866e-06,
"loss": 0.8078,
"step": 11600
},
{
"epoch": 0.2,
"learning_rate": 4.827151455994794e-06,
"loss": 0.8368,
"step": 11700
},
{
"epoch": 0.2,
"learning_rate": 4.816983894582723e-06,
"loss": 0.8031,
"step": 11800
},
{
"epoch": 0.2,
"learning_rate": 4.806816333170653e-06,
"loss": 0.8054,
"step": 11900
},
{
"epoch": 0.2,
"learning_rate": 4.796648771758582e-06,
"loss": 0.8356,
"step": 12000
},
{
"epoch": 0.2,
"learning_rate": 4.786481210346511e-06,
"loss": 0.8048,
"step": 12100
},
{
"epoch": 0.21,
"learning_rate": 4.77631364893444e-06,
"loss": 0.8205,
"step": 12200
},
{
"epoch": 0.21,
"learning_rate": 4.7661460875223694e-06,
"loss": 0.8153,
"step": 12300
},
{
"epoch": 0.21,
"learning_rate": 4.755978526110298e-06,
"loss": 0.8099,
"step": 12400
},
{
"epoch": 0.21,
"learning_rate": 4.745810964698227e-06,
"loss": 0.8307,
"step": 12500
},
{
"epoch": 0.21,
"learning_rate": 4.7356434032861566e-06,
"loss": 0.8131,
"step": 12600
},
{
"epoch": 0.21,
"learning_rate": 4.725475841874085e-06,
"loss": 0.8255,
"step": 12700
},
{
"epoch": 0.22,
"learning_rate": 4.715308280462014e-06,
"loss": 0.8092,
"step": 12800
},
{
"epoch": 0.22,
"learning_rate": 4.705140719049943e-06,
"loss": 0.8543,
"step": 12900
},
{
"epoch": 0.22,
"learning_rate": 4.6949731576378724e-06,
"loss": 0.8896,
"step": 13000
},
{
"epoch": 0.22,
"learning_rate": 4.684805596225801e-06,
"loss": 0.8353,
"step": 13100
},
{
"epoch": 0.22,
"learning_rate": 4.674638034813731e-06,
"loss": 0.7927,
"step": 13200
},
{
"epoch": 0.22,
"learning_rate": 4.6644704734016595e-06,
"loss": 0.8064,
"step": 13300
},
{
"epoch": 0.23,
"learning_rate": 4.654302911989589e-06,
"loss": 0.8314,
"step": 13400
},
{
"epoch": 0.23,
"learning_rate": 4.644135350577518e-06,
"loss": 0.8067,
"step": 13500
},
{
"epoch": 0.23,
"learning_rate": 4.6339677891654475e-06,
"loss": 0.8384,
"step": 13600
},
{
"epoch": 0.23,
"learning_rate": 4.623800227753376e-06,
"loss": 0.8762,
"step": 13700
},
{
"epoch": 0.23,
"learning_rate": 4.613632666341305e-06,
"loss": 0.8433,
"step": 13800
},
{
"epoch": 0.23,
"learning_rate": 4.603465104929234e-06,
"loss": 0.8425,
"step": 13900
},
{
"epoch": 0.24,
"learning_rate": 4.593297543517163e-06,
"loss": 0.8143,
"step": 14000
},
{
"epoch": 0.24,
"learning_rate": 4.583129982105092e-06,
"loss": 0.8445,
"step": 14100
},
{
"epoch": 0.24,
"learning_rate": 4.572962420693021e-06,
"loss": 0.8211,
"step": 14200
},
{
"epoch": 0.24,
"learning_rate": 4.5627948592809505e-06,
"loss": 0.823,
"step": 14300
},
{
"epoch": 0.24,
"learning_rate": 4.552627297868879e-06,
"loss": 0.8214,
"step": 14400
},
{
"epoch": 0.25,
"learning_rate": 4.542459736456809e-06,
"loss": 0.8204,
"step": 14500
},
{
"epoch": 0.25,
"learning_rate": 4.532292175044738e-06,
"loss": 0.815,
"step": 14600
},
{
"epoch": 0.25,
"learning_rate": 4.522124613632667e-06,
"loss": 0.8516,
"step": 14700
},
{
"epoch": 0.25,
"learning_rate": 4.511957052220596e-06,
"loss": 0.8202,
"step": 14800
},
{
"epoch": 0.25,
"learning_rate": 4.501789490808525e-06,
"loss": 0.8116,
"step": 14900
},
{
"epoch": 0.25,
"learning_rate": 4.491621929396454e-06,
"loss": 0.8123,
"step": 15000
},
{
"epoch": 0.26,
"learning_rate": 4.481454367984383e-06,
"loss": 0.841,
"step": 15100
},
{
"epoch": 0.26,
"learning_rate": 4.471286806572312e-06,
"loss": 0.8247,
"step": 15200
},
{
"epoch": 0.26,
"learning_rate": 4.461119245160241e-06,
"loss": 0.8678,
"step": 15300
},
{
"epoch": 0.26,
"learning_rate": 4.45095168374817e-06,
"loss": 0.8544,
"step": 15400
},
{
"epoch": 0.26,
"learning_rate": 4.440784122336099e-06,
"loss": 0.8383,
"step": 15500
},
{
"epoch": 0.26,
"learning_rate": 4.430616560924028e-06,
"loss": 0.8706,
"step": 15600
},
{
"epoch": 0.27,
"learning_rate": 4.420448999511957e-06,
"loss": 0.8835,
"step": 15700
},
{
"epoch": 0.27,
"learning_rate": 4.410281438099886e-06,
"loss": 0.8462,
"step": 15800
},
{
"epoch": 0.27,
"learning_rate": 4.400113876687816e-06,
"loss": 0.8491,
"step": 15900
},
{
"epoch": 0.27,
"learning_rate": 4.389946315275745e-06,
"loss": 0.8531,
"step": 16000
},
{
"epoch": 0.27,
"learning_rate": 4.379778753863674e-06,
"loss": 0.8263,
"step": 16100
},
{
"epoch": 0.27,
"learning_rate": 4.369611192451603e-06,
"loss": 0.8539,
"step": 16200
},
{
"epoch": 0.28,
"learning_rate": 4.3594436310395316e-06,
"loss": 0.8483,
"step": 16300
},
{
"epoch": 0.28,
"learning_rate": 4.349276069627461e-06,
"loss": 0.8691,
"step": 16400
},
{
"epoch": 0.28,
"learning_rate": 4.33910850821539e-06,
"loss": 0.8756,
"step": 16500
},
{
"epoch": 0.28,
"learning_rate": 4.328940946803319e-06,
"loss": 0.8811,
"step": 16600
},
{
"epoch": 0.28,
"learning_rate": 4.318773385391248e-06,
"loss": 0.8712,
"step": 16700
},
{
"epoch": 0.28,
"learning_rate": 4.308605823979177e-06,
"loss": 0.8612,
"step": 16800
},
{
"epoch": 0.29,
"learning_rate": 4.298438262567106e-06,
"loss": 0.8675,
"step": 16900
},
{
"epoch": 0.29,
"learning_rate": 4.288270701155035e-06,
"loss": 0.8508,
"step": 17000
},
{
"epoch": 0.29,
"learning_rate": 4.278103139742964e-06,
"loss": 0.862,
"step": 17100
},
{
"epoch": 0.29,
"learning_rate": 4.267935578330894e-06,
"loss": 0.8782,
"step": 17200
},
{
"epoch": 0.29,
"learning_rate": 4.2577680169188225e-06,
"loss": 0.8776,
"step": 17300
},
{
"epoch": 0.29,
"learning_rate": 4.247600455506752e-06,
"loss": 0.877,
"step": 17400
},
{
"epoch": 0.3,
"learning_rate": 4.237432894094681e-06,
"loss": 0.8694,
"step": 17500
},
{
"epoch": 0.3,
"learning_rate": 4.22726533268261e-06,
"loss": 0.8865,
"step": 17600
},
{
"epoch": 0.3,
"learning_rate": 4.217097771270538e-06,
"loss": 0.9107,
"step": 17700
},
{
"epoch": 0.3,
"learning_rate": 4.206930209858468e-06,
"loss": 0.8476,
"step": 17800
},
{
"epoch": 0.3,
"learning_rate": 4.196762648446397e-06,
"loss": 0.8507,
"step": 17900
},
{
"epoch": 0.3,
"learning_rate": 4.1865950870343255e-06,
"loss": 0.8885,
"step": 18000
},
{
"epoch": 0.31,
"learning_rate": 4.176427525622255e-06,
"loss": 0.8543,
"step": 18100
},
{
"epoch": 0.31,
"learning_rate": 4.166259964210184e-06,
"loss": 0.8824,
"step": 18200
},
{
"epoch": 0.31,
"learning_rate": 4.1560924027981135e-06,
"loss": 0.8662,
"step": 18300
},
{
"epoch": 0.31,
"learning_rate": 4.145924841386042e-06,
"loss": 0.8742,
"step": 18400
},
{
"epoch": 0.31,
"learning_rate": 4.135757279973972e-06,
"loss": 0.8761,
"step": 18500
},
{
"epoch": 0.31,
"learning_rate": 4.125589718561901e-06,
"loss": 0.8311,
"step": 18600
},
{
"epoch": 0.32,
"learning_rate": 4.115422157149829e-06,
"loss": 0.8782,
"step": 18700
},
{
"epoch": 0.32,
"learning_rate": 4.105254595737759e-06,
"loss": 0.8901,
"step": 18800
},
{
"epoch": 0.32,
"learning_rate": 4.095087034325688e-06,
"loss": 0.8659,
"step": 18900
},
{
"epoch": 0.32,
"learning_rate": 4.0849194729136165e-06,
"loss": 0.895,
"step": 19000
},
{
"epoch": 0.32,
"learning_rate": 4.074751911501546e-06,
"loss": 0.8541,
"step": 19100
},
{
"epoch": 0.32,
"learning_rate": 4.064584350089475e-06,
"loss": 0.8535,
"step": 19200
},
{
"epoch": 0.33,
"learning_rate": 4.054416788677404e-06,
"loss": 0.8489,
"step": 19300
},
{
"epoch": 0.33,
"learning_rate": 4.044249227265332e-06,
"loss": 0.8234,
"step": 19400
},
{
"epoch": 0.33,
"learning_rate": 4.034081665853262e-06,
"loss": 0.9029,
"step": 19500
},
{
"epoch": 0.33,
"learning_rate": 4.023914104441191e-06,
"loss": 0.8754,
"step": 19600
},
{
"epoch": 0.33,
"learning_rate": 4.01374654302912e-06,
"loss": 0.8844,
"step": 19700
},
{
"epoch": 0.33,
"learning_rate": 4.00357898161705e-06,
"loss": 0.8986,
"step": 19800
},
{
"epoch": 0.34,
"learning_rate": 3.993411420204979e-06,
"loss": 0.8772,
"step": 19900
},
{
"epoch": 0.34,
"learning_rate": 3.9832438587929074e-06,
"loss": 0.895,
"step": 20000
},
{
"epoch": 0.34,
"learning_rate": 3.973076297380837e-06,
"loss": 0.894,
"step": 20100
},
{
"epoch": 0.34,
"learning_rate": 3.962908735968766e-06,
"loss": 0.8815,
"step": 20200
},
{
"epoch": 0.34,
"learning_rate": 3.9527411745566946e-06,
"loss": 0.8819,
"step": 20300
},
{
"epoch": 0.34,
"learning_rate": 3.942573613144623e-06,
"loss": 0.8863,
"step": 20400
},
{
"epoch": 0.35,
"learning_rate": 3.932406051732553e-06,
"loss": 0.9163,
"step": 20500
},
{
"epoch": 0.35,
"learning_rate": 3.922238490320482e-06,
"loss": 0.8853,
"step": 20600
},
{
"epoch": 0.35,
"learning_rate": 3.9120709289084104e-06,
"loss": 0.9038,
"step": 20700
},
{
"epoch": 0.35,
"learning_rate": 3.90190336749634e-06,
"loss": 0.8709,
"step": 20800
},
{
"epoch": 0.35,
"learning_rate": 3.891735806084269e-06,
"loss": 0.8971,
"step": 20900
},
{
"epoch": 0.35,
"learning_rate": 3.881568244672198e-06,
"loss": 0.9209,
"step": 21000
},
{
"epoch": 0.36,
"learning_rate": 3.871400683260127e-06,
"loss": 0.8834,
"step": 21100
},
{
"epoch": 0.36,
"learning_rate": 3.861233121848057e-06,
"loss": 0.8863,
"step": 21200
},
{
"epoch": 0.36,
"learning_rate": 3.8510655604359855e-06,
"loss": 0.906,
"step": 21300
},
{
"epoch": 0.36,
"learning_rate": 3.840897999023914e-06,
"loss": 0.9189,
"step": 21400
},
{
"epoch": 0.36,
"learning_rate": 3.830730437611844e-06,
"loss": 0.93,
"step": 21500
},
{
"epoch": 0.37,
"learning_rate": 3.820562876199773e-06,
"loss": 0.8958,
"step": 21600
},
{
"epoch": 0.37,
"learning_rate": 3.8103953147877014e-06,
"loss": 0.9083,
"step": 21700
},
{
"epoch": 0.37,
"learning_rate": 3.8002277533756306e-06,
"loss": 0.9295,
"step": 21800
},
{
"epoch": 0.37,
"learning_rate": 3.7900601919635597e-06,
"loss": 0.8769,
"step": 21900
},
{
"epoch": 0.37,
"learning_rate": 3.779892630551489e-06,
"loss": 0.8945,
"step": 22000
},
{
"epoch": 0.37,
"learning_rate": 3.7697250691394177e-06,
"loss": 0.8931,
"step": 22100
},
{
"epoch": 0.38,
"learning_rate": 3.7595575077273473e-06,
"loss": 0.905,
"step": 22200
},
{
"epoch": 0.38,
"learning_rate": 3.749389946315276e-06,
"loss": 0.9113,
"step": 22300
},
{
"epoch": 0.38,
"learning_rate": 3.739222384903205e-06,
"loss": 0.937,
"step": 22400
},
{
"epoch": 0.38,
"learning_rate": 3.7290548234911344e-06,
"loss": 0.8804,
"step": 22500
},
{
"epoch": 0.38,
"learning_rate": 3.718887262079063e-06,
"loss": 0.9093,
"step": 22600
},
{
"epoch": 0.38,
"learning_rate": 3.7087197006669923e-06,
"loss": 0.9133,
"step": 22700
},
{
"epoch": 0.39,
"learning_rate": 3.698552139254921e-06,
"loss": 0.9085,
"step": 22800
},
{
"epoch": 0.39,
"learning_rate": 3.6883845778428507e-06,
"loss": 0.9428,
"step": 22900
},
{
"epoch": 0.39,
"learning_rate": 3.6782170164307795e-06,
"loss": 0.9159,
"step": 23000
},
{
"epoch": 0.39,
"learning_rate": 3.6680494550187086e-06,
"loss": 0.9268,
"step": 23100
},
{
"epoch": 0.39,
"learning_rate": 3.657881893606638e-06,
"loss": 0.9015,
"step": 23200
},
{
"epoch": 0.39,
"learning_rate": 3.647714332194567e-06,
"loss": 0.9251,
"step": 23300
},
{
"epoch": 0.4,
"learning_rate": 3.6375467707824958e-06,
"loss": 0.8898,
"step": 23400
},
{
"epoch": 0.4,
"learning_rate": 3.6273792093704245e-06,
"loss": 0.9437,
"step": 23500
},
{
"epoch": 0.4,
"learning_rate": 3.617211647958354e-06,
"loss": 0.9087,
"step": 23600
},
{
"epoch": 0.4,
"learning_rate": 3.607044086546283e-06,
"loss": 0.9256,
"step": 23700
},
{
"epoch": 0.4,
"learning_rate": 3.596876525134212e-06,
"loss": 0.9217,
"step": 23800
},
{
"epoch": 0.4,
"learning_rate": 3.5867089637221412e-06,
"loss": 0.8974,
"step": 23900
},
{
"epoch": 0.41,
"learning_rate": 3.5765414023100704e-06,
"loss": 0.9285,
"step": 24000
},
{
"epoch": 0.41,
"learning_rate": 3.566373840897999e-06,
"loss": 0.9548,
"step": 24100
},
{
"epoch": 0.41,
"learning_rate": 3.556206279485928e-06,
"loss": 0.9424,
"step": 24200
},
{
"epoch": 0.41,
"learning_rate": 3.5460387180738575e-06,
"loss": 0.9324,
"step": 24300
},
{
"epoch": 0.41,
"learning_rate": 3.5358711566617863e-06,
"loss": 0.9411,
"step": 24400
},
{
"epoch": 0.41,
"learning_rate": 3.5257035952497155e-06,
"loss": 0.9177,
"step": 24500
},
{
"epoch": 0.42,
"learning_rate": 3.5155360338376446e-06,
"loss": 0.9298,
"step": 24600
},
{
"epoch": 0.42,
"learning_rate": 3.505368472425574e-06,
"loss": 0.9467,
"step": 24700
},
{
"epoch": 0.42,
"learning_rate": 3.4952009110135026e-06,
"loss": 0.9435,
"step": 24800
},
{
"epoch": 0.42,
"learning_rate": 3.485033349601432e-06,
"loss": 0.9262,
"step": 24900
},
{
"epoch": 0.42,
"learning_rate": 3.474865788189361e-06,
"loss": 0.9273,
"step": 25000
},
{
"epoch": 0.42,
"learning_rate": 3.46469822677729e-06,
"loss": 0.9661,
"step": 25100
},
{
"epoch": 0.43,
"learning_rate": 3.454530665365219e-06,
"loss": 0.9304,
"step": 25200
},
{
"epoch": 0.43,
"learning_rate": 3.4443631039531485e-06,
"loss": 0.9337,
"step": 25300
},
{
"epoch": 0.43,
"learning_rate": 3.4341955425410772e-06,
"loss": 0.9597,
"step": 25400
},
{
"epoch": 0.43,
"learning_rate": 3.424027981129006e-06,
"loss": 0.9275,
"step": 25500
},
{
"epoch": 0.43,
"learning_rate": 3.4138604197169356e-06,
"loss": 0.9072,
"step": 25600
},
{
"epoch": 0.43,
"learning_rate": 3.4036928583048644e-06,
"loss": 0.9558,
"step": 25700
},
{
"epoch": 0.44,
"learning_rate": 3.3935252968927935e-06,
"loss": 0.9421,
"step": 25800
},
{
"epoch": 0.44,
"learning_rate": 3.3833577354807223e-06,
"loss": 0.9435,
"step": 25900
},
{
"epoch": 0.44,
"learning_rate": 3.373190174068652e-06,
"loss": 0.9397,
"step": 26000
},
{
"epoch": 0.44,
"learning_rate": 3.3630226126565807e-06,
"loss": 0.9272,
"step": 26100
},
{
"epoch": 0.44,
"learning_rate": 3.3528550512445094e-06,
"loss": 0.9527,
"step": 26200
},
{
"epoch": 0.44,
"learning_rate": 3.342687489832439e-06,
"loss": 0.9442,
"step": 26300
},
{
"epoch": 0.45,
"learning_rate": 3.3325199284203678e-06,
"loss": 0.9789,
"step": 26400
},
{
"epoch": 0.45,
"learning_rate": 3.322352367008297e-06,
"loss": 0.9775,
"step": 26500
},
{
"epoch": 0.45,
"learning_rate": 3.312184805596226e-06,
"loss": 0.9649,
"step": 26600
},
{
"epoch": 0.45,
"learning_rate": 3.3020172441841553e-06,
"loss": 0.9828,
"step": 26700
},
{
"epoch": 0.45,
"learning_rate": 3.291849682772084e-06,
"loss": 0.9506,
"step": 26800
},
{
"epoch": 0.45,
"learning_rate": 3.2816821213600133e-06,
"loss": 0.9828,
"step": 26900
},
{
"epoch": 0.46,
"learning_rate": 3.2715145599479424e-06,
"loss": 0.9549,
"step": 27000
},
{
"epoch": 0.46,
"learning_rate": 3.2613469985358716e-06,
"loss": 0.987,
"step": 27100
},
{
"epoch": 0.46,
"learning_rate": 3.2511794371238004e-06,
"loss": 0.8978,
"step": 27200
},
{
"epoch": 0.46,
"learning_rate": 3.24101187571173e-06,
"loss": 0.9694,
"step": 27300
},
{
"epoch": 0.46,
"learning_rate": 3.2308443142996587e-06,
"loss": 1.0004,
"step": 27400
},
{
"epoch": 0.46,
"learning_rate": 3.2206767528875875e-06,
"loss": 0.9503,
"step": 27500
},
{
"epoch": 0.47,
"learning_rate": 3.2105091914755167e-06,
"loss": 0.9263,
"step": 27600
},
{
"epoch": 0.47,
"learning_rate": 3.200341630063446e-06,
"loss": 0.9818,
"step": 27700
},
{
"epoch": 0.47,
"learning_rate": 3.190174068651375e-06,
"loss": 0.9753,
"step": 27800
},
{
"epoch": 0.47,
"learning_rate": 3.1800065072393038e-06,
"loss": 0.975,
"step": 27900
},
{
"epoch": 0.47,
"learning_rate": 3.1698389458272334e-06,
"loss": 0.9324,
"step": 28000
},
{
"epoch": 0.47,
"learning_rate": 3.159671384415162e-06,
"loss": 1.0101,
"step": 28100
},
{
"epoch": 0.48,
"learning_rate": 3.149503823003091e-06,
"loss": 0.9815,
"step": 28200
},
{
"epoch": 0.48,
"learning_rate": 3.13933626159102e-06,
"loss": 0.9598,
"step": 28300
},
{
"epoch": 0.48,
"learning_rate": 3.1291687001789493e-06,
"loss": 0.9791,
"step": 28400
},
{
"epoch": 0.48,
"learning_rate": 3.1190011387668784e-06,
"loss": 0.9495,
"step": 28500
},
{
"epoch": 0.48,
"learning_rate": 3.108833577354807e-06,
"loss": 0.9832,
"step": 28600
},
{
"epoch": 0.48,
"learning_rate": 3.098666015942737e-06,
"loss": 1.0214,
"step": 28700
},
{
"epoch": 0.49,
"learning_rate": 3.0884984545306656e-06,
"loss": 0.9944,
"step": 28800
},
{
"epoch": 0.49,
"learning_rate": 3.0783308931185947e-06,
"loss": 0.9976,
"step": 28900
},
{
"epoch": 0.49,
"learning_rate": 3.068163331706524e-06,
"loss": 0.9992,
"step": 29000
},
{
"epoch": 0.49,
"learning_rate": 3.057995770294453e-06,
"loss": 0.9597,
"step": 29100
},
{
"epoch": 0.49,
"learning_rate": 3.047828208882382e-06,
"loss": 0.9812,
"step": 29200
},
{
"epoch": 0.5,
"learning_rate": 3.0376606474703106e-06,
"loss": 1.0031,
"step": 29300
},
{
"epoch": 0.5,
"learning_rate": 3.0274930860582402e-06,
"loss": 0.9859,
"step": 29400
},
{
"epoch": 0.5,
"learning_rate": 3.017325524646169e-06,
"loss": 0.9966,
"step": 29500
},
{
"epoch": 0.5,
"learning_rate": 3.007157963234098e-06,
"loss": 0.9993,
"step": 29600
},
{
"epoch": 0.5,
"learning_rate": 2.9969904018220273e-06,
"loss": 1.0101,
"step": 29700
},
{
"epoch": 0.5,
"learning_rate": 2.9868228404099565e-06,
"loss": 0.9613,
"step": 29800
},
{
"epoch": 0.51,
"learning_rate": 2.9766552789978853e-06,
"loss": 1.0252,
"step": 29900
},
{
"epoch": 0.51,
"learning_rate": 2.966487717585814e-06,
"loss": 1.055,
"step": 30000
},
{
"epoch": 0.51,
"learning_rate": 2.9563201561737436e-06,
"loss": 0.9934,
"step": 30100
},
{
"epoch": 0.51,
"learning_rate": 2.9461525947616724e-06,
"loss": 0.9714,
"step": 30200
},
{
"epoch": 0.51,
"learning_rate": 2.9359850333496016e-06,
"loss": 1.0161,
"step": 30300
},
{
"epoch": 0.51,
"learning_rate": 2.9258174719375308e-06,
"loss": 0.9844,
"step": 30400
},
{
"epoch": 0.52,
"learning_rate": 2.91564991052546e-06,
"loss": 1.0098,
"step": 30500
},
{
"epoch": 0.52,
"learning_rate": 2.9054823491133887e-06,
"loss": 1.0095,
"step": 30600
},
{
"epoch": 0.52,
"learning_rate": 2.895314787701318e-06,
"loss": 1.0176,
"step": 30700
},
{
"epoch": 0.52,
"learning_rate": 2.885147226289247e-06,
"loss": 1.0313,
"step": 30800
},
{
"epoch": 0.52,
"learning_rate": 2.8749796648771762e-06,
"loss": 1.0201,
"step": 30900
},
{
"epoch": 0.52,
"learning_rate": 2.864812103465105e-06,
"loss": 1.0095,
"step": 31000
},
{
"epoch": 0.53,
"learning_rate": 2.8546445420530346e-06,
"loss": 0.9885,
"step": 31100
},
{
"epoch": 0.53,
"learning_rate": 2.8444769806409634e-06,
"loss": 1.0684,
"step": 31200
},
{
"epoch": 0.53,
"learning_rate": 2.834309419228892e-06,
"loss": 0.9972,
"step": 31300
},
{
"epoch": 0.53,
"learning_rate": 2.8241418578168217e-06,
"loss": 1.0518,
"step": 31400
},
{
"epoch": 0.53,
"learning_rate": 2.8139742964047505e-06,
"loss": 1.0115,
"step": 31500
},
{
"epoch": 0.53,
"learning_rate": 2.8038067349926796e-06,
"loss": 1.0107,
"step": 31600
},
{
"epoch": 0.54,
"learning_rate": 2.7936391735806084e-06,
"loss": 1.0607,
"step": 31700
},
{
"epoch": 0.54,
"learning_rate": 2.783471612168538e-06,
"loss": 1.0564,
"step": 31800
},
{
"epoch": 0.54,
"learning_rate": 2.7733040507564668e-06,
"loss": 1.0554,
"step": 31900
},
{
"epoch": 0.54,
"learning_rate": 2.7631364893443955e-06,
"loss": 1.001,
"step": 32000
},
{
"epoch": 0.54,
"learning_rate": 2.752968927932325e-06,
"loss": 1.0299,
"step": 32100
},
{
"epoch": 0.54,
"learning_rate": 2.742801366520254e-06,
"loss": 1.0266,
"step": 32200
},
{
"epoch": 0.55,
"learning_rate": 2.732633805108183e-06,
"loss": 1.0076,
"step": 32300
},
{
"epoch": 0.55,
"learning_rate": 2.722466243696112e-06,
"loss": 1.0152,
"step": 32400
},
{
"epoch": 0.55,
"learning_rate": 2.7122986822840414e-06,
"loss": 1.0546,
"step": 32500
},
{
"epoch": 0.55,
"learning_rate": 2.70213112087197e-06,
"loss": 1.025,
"step": 32600
},
{
"epoch": 0.55,
"learning_rate": 2.6919635594598994e-06,
"loss": 1.0748,
"step": 32700
},
{
"epoch": 0.55,
"learning_rate": 2.6817959980478285e-06,
"loss": 1.0332,
"step": 32800
},
{
"epoch": 0.56,
"learning_rate": 2.6716284366357577e-06,
"loss": 1.0211,
"step": 32900
},
{
"epoch": 0.56,
"learning_rate": 2.6614608752236865e-06,
"loss": 1.0536,
"step": 33000
},
{
"epoch": 0.56,
"learning_rate": 2.6512933138116152e-06,
"loss": 0.9919,
"step": 33100
},
{
"epoch": 0.56,
"learning_rate": 2.641125752399545e-06,
"loss": 1.0245,
"step": 33200
},
{
"epoch": 0.56,
"learning_rate": 2.6309581909874736e-06,
"loss": 1.0171,
"step": 33300
},
{
"epoch": 0.56,
"learning_rate": 2.6207906295754028e-06,
"loss": 1.0299,
"step": 33400
},
{
"epoch": 0.57,
"learning_rate": 2.610623068163332e-06,
"loss": 1.0506,
"step": 33500
},
{
"epoch": 0.57,
"learning_rate": 2.600455506751261e-06,
"loss": 1.044,
"step": 33600
},
{
"epoch": 0.57,
"learning_rate": 2.59028794533919e-06,
"loss": 1.0657,
"step": 33700
},
{
"epoch": 0.57,
"learning_rate": 2.5801203839271195e-06,
"loss": 1.0766,
"step": 33800
},
{
"epoch": 0.57,
"learning_rate": 2.5699528225150483e-06,
"loss": 1.0482,
"step": 33900
},
{
"epoch": 0.57,
"learning_rate": 2.559785261102977e-06,
"loss": 1.0502,
"step": 34000
},
{
"epoch": 0.58,
"learning_rate": 2.549617699690906e-06,
"loss": 1.0814,
"step": 34100
},
{
"epoch": 0.58,
"learning_rate": 2.5394501382788354e-06,
"loss": 1.0862,
"step": 34200
},
{
"epoch": 0.58,
"learning_rate": 2.5292825768667646e-06,
"loss": 1.0954,
"step": 34300
},
{
"epoch": 0.58,
"learning_rate": 2.5191150154546933e-06,
"loss": 1.0866,
"step": 34400
},
{
"epoch": 0.58,
"learning_rate": 2.508947454042623e-06,
"loss": 1.0649,
"step": 34500
},
{
"epoch": 0.58,
"learning_rate": 2.4987798926305517e-06,
"loss": 1.0483,
"step": 34600
},
{
"epoch": 0.59,
"learning_rate": 2.488612331218481e-06,
"loss": 1.0383,
"step": 34700
},
{
"epoch": 0.59,
"learning_rate": 2.47844476980641e-06,
"loss": 1.0459,
"step": 34800
},
{
"epoch": 0.59,
"learning_rate": 2.4682772083943392e-06,
"loss": 1.0821,
"step": 34900
},
{
"epoch": 0.59,
"learning_rate": 2.458109646982268e-06,
"loss": 1.0808,
"step": 35000
},
{
"epoch": 0.59,
"learning_rate": 2.447942085570197e-06,
"loss": 1.0552,
"step": 35100
},
{
"epoch": 0.59,
"learning_rate": 2.437774524158126e-06,
"loss": 1.094,
"step": 35200
},
{
"epoch": 0.6,
"learning_rate": 2.427606962746055e-06,
"loss": 1.0991,
"step": 35300
},
{
"epoch": 0.6,
"learning_rate": 2.4174394013339843e-06,
"loss": 1.0807,
"step": 35400
},
{
"epoch": 0.6,
"learning_rate": 2.4072718399219134e-06,
"loss": 1.1117,
"step": 35500
},
{
"epoch": 0.6,
"learning_rate": 2.3971042785098426e-06,
"loss": 1.0754,
"step": 35600
},
{
"epoch": 0.6,
"learning_rate": 2.3869367170977714e-06,
"loss": 1.1518,
"step": 35700
},
{
"epoch": 0.6,
"learning_rate": 2.3767691556857006e-06,
"loss": 1.1195,
"step": 35800
},
{
"epoch": 0.61,
"learning_rate": 2.3666015942736293e-06,
"loss": 1.0949,
"step": 35900
},
{
"epoch": 0.61,
"learning_rate": 2.3564340328615585e-06,
"loss": 1.1088,
"step": 36000
},
{
"epoch": 0.61,
"learning_rate": 2.3462664714494877e-06,
"loss": 1.1107,
"step": 36100
},
{
"epoch": 0.61,
"learning_rate": 2.336098910037417e-06,
"loss": 1.0928,
"step": 36200
},
{
"epoch": 0.61,
"learning_rate": 2.325931348625346e-06,
"loss": 1.0953,
"step": 36300
},
{
"epoch": 0.62,
"learning_rate": 2.315763787213275e-06,
"loss": 1.1044,
"step": 36400
},
{
"epoch": 0.62,
"learning_rate": 2.305596225801204e-06,
"loss": 1.0717,
"step": 36500
},
{
"epoch": 0.62,
"learning_rate": 2.295428664389133e-06,
"loss": 1.1131,
"step": 36600
},
{
"epoch": 0.62,
"learning_rate": 2.2852611029770623e-06,
"loss": 1.0786,
"step": 36700
},
{
"epoch": 0.62,
"learning_rate": 2.2750935415649915e-06,
"loss": 1.0974,
"step": 36800
},
{
"epoch": 0.62,
"learning_rate": 2.2649259801529203e-06,
"loss": 1.0983,
"step": 36900
},
{
"epoch": 0.63,
"learning_rate": 2.2547584187408495e-06,
"loss": 1.1312,
"step": 37000
},
{
"epoch": 0.63,
"learning_rate": 2.2445908573287782e-06,
"loss": 1.1265,
"step": 37100
},
{
"epoch": 0.63,
"learning_rate": 2.2344232959167074e-06,
"loss": 1.1468,
"step": 37200
},
{
"epoch": 0.63,
"learning_rate": 2.2242557345046366e-06,
"loss": 1.1186,
"step": 37300
},
{
"epoch": 0.63,
"learning_rate": 2.2140881730925658e-06,
"loss": 1.1505,
"step": 37400
},
{
"epoch": 0.63,
"learning_rate": 2.203920611680495e-06,
"loss": 1.1365,
"step": 37500
},
{
"epoch": 0.64,
"learning_rate": 2.1937530502684237e-06,
"loss": 1.1404,
"step": 37600
},
{
"epoch": 0.64,
"learning_rate": 2.183585488856353e-06,
"loss": 1.1175,
"step": 37700
},
{
"epoch": 0.64,
"learning_rate": 2.1734179274442816e-06,
"loss": 1.1552,
"step": 37800
},
{
"epoch": 0.64,
"learning_rate": 2.163250366032211e-06,
"loss": 1.1204,
"step": 37900
},
{
"epoch": 0.64,
"learning_rate": 2.15308280462014e-06,
"loss": 1.1433,
"step": 38000
},
{
"epoch": 0.64,
"learning_rate": 2.142915243208069e-06,
"loss": 1.1573,
"step": 38100
},
{
"epoch": 0.65,
"learning_rate": 2.1327476817959984e-06,
"loss": 1.1685,
"step": 38200
},
{
"epoch": 0.65,
"learning_rate": 2.122580120383927e-06,
"loss": 1.1721,
"step": 38300
},
{
"epoch": 0.65,
"learning_rate": 2.1124125589718563e-06,
"loss": 1.1155,
"step": 38400
},
{
"epoch": 0.65,
"learning_rate": 2.1022449975597855e-06,
"loss": 1.1767,
"step": 38500
},
{
"epoch": 0.65,
"learning_rate": 2.0920774361477147e-06,
"loss": 1.1768,
"step": 38600
},
{
"epoch": 0.65,
"learning_rate": 2.081909874735644e-06,
"loss": 1.1607,
"step": 38700
},
{
"epoch": 0.66,
"learning_rate": 2.0717423133235726e-06,
"loss": 1.1792,
"step": 38800
},
{
"epoch": 0.66,
"learning_rate": 2.0615747519115018e-06,
"loss": 1.1723,
"step": 38900
},
{
"epoch": 0.66,
"learning_rate": 2.0514071904994305e-06,
"loss": 1.1904,
"step": 39000
},
{
"epoch": 0.66,
"learning_rate": 2.0412396290873597e-06,
"loss": 1.1876,
"step": 39100
},
{
"epoch": 0.66,
"learning_rate": 2.031072067675289e-06,
"loss": 1.1391,
"step": 39200
},
{
"epoch": 0.66,
"learning_rate": 2.020904506263218e-06,
"loss": 1.164,
"step": 39300
},
{
"epoch": 0.67,
"learning_rate": 2.0107369448511472e-06,
"loss": 1.2149,
"step": 39400
},
{
"epoch": 0.67,
"learning_rate": 2.000569383439076e-06,
"loss": 1.1875,
"step": 39500
},
{
"epoch": 0.67,
"learning_rate": 1.990401822027005e-06,
"loss": 1.2367,
"step": 39600
},
{
"epoch": 0.67,
"learning_rate": 1.9802342606149344e-06,
"loss": 1.2065,
"step": 39700
},
{
"epoch": 0.67,
"learning_rate": 1.970066699202863e-06,
"loss": 1.2258,
"step": 39800
},
{
"epoch": 0.67,
"learning_rate": 1.9598991377907923e-06,
"loss": 1.1814,
"step": 39900
},
{
"epoch": 0.68,
"learning_rate": 1.9497315763787215e-06,
"loss": 1.1806,
"step": 40000
},
{
"epoch": 0.68,
"learning_rate": 1.9395640149666507e-06,
"loss": 1.166,
"step": 40100
},
{
"epoch": 0.68,
"learning_rate": 1.9293964535545794e-06,
"loss": 1.2064,
"step": 40200
},
{
"epoch": 0.68,
"learning_rate": 1.9192288921425086e-06,
"loss": 1.194,
"step": 40300
},
{
"epoch": 0.68,
"learning_rate": 1.9090613307304378e-06,
"loss": 1.1971,
"step": 40400
},
{
"epoch": 0.68,
"learning_rate": 1.8988937693183667e-06,
"loss": 1.1894,
"step": 40500
},
{
"epoch": 0.69,
"learning_rate": 1.888726207906296e-06,
"loss": 1.2159,
"step": 40600
},
{
"epoch": 0.69,
"learning_rate": 1.878558646494225e-06,
"loss": 1.1986,
"step": 40700
},
{
"epoch": 0.69,
"learning_rate": 1.868391085082154e-06,
"loss": 1.2189,
"step": 40800
},
{
"epoch": 0.69,
"learning_rate": 1.8582235236700833e-06,
"loss": 1.2066,
"step": 40900
},
{
"epoch": 0.69,
"learning_rate": 1.8480559622580122e-06,
"loss": 1.1802,
"step": 41000
},
{
"epoch": 0.69,
"learning_rate": 1.8378884008459414e-06,
"loss": 1.252,
"step": 41100
},
{
"epoch": 0.7,
"learning_rate": 1.8277208394338702e-06,
"loss": 1.2466,
"step": 41200
},
{
"epoch": 0.7,
"learning_rate": 1.8175532780217993e-06,
"loss": 1.2056,
"step": 41300
},
{
"epoch": 0.7,
"learning_rate": 1.8073857166097283e-06,
"loss": 1.2143,
"step": 41400
},
{
"epoch": 0.7,
"learning_rate": 1.7972181551976575e-06,
"loss": 1.2032,
"step": 41500
},
{
"epoch": 0.7,
"learning_rate": 1.7870505937855867e-06,
"loss": 1.2404,
"step": 41600
},
{
"epoch": 0.7,
"learning_rate": 1.7768830323735156e-06,
"loss": 1.2306,
"step": 41700
},
{
"epoch": 0.71,
"learning_rate": 1.7667154709614448e-06,
"loss": 1.2319,
"step": 41800
},
{
"epoch": 0.71,
"learning_rate": 1.7565479095493738e-06,
"loss": 1.2316,
"step": 41900
},
{
"epoch": 0.71,
"learning_rate": 1.746380348137303e-06,
"loss": 1.2243,
"step": 42000
},
{
"epoch": 0.71,
"learning_rate": 1.7362127867252322e-06,
"loss": 1.2149,
"step": 42100
},
{
"epoch": 0.71,
"learning_rate": 1.726045225313161e-06,
"loss": 1.2745,
"step": 42200
},
{
"epoch": 0.71,
"learning_rate": 1.71587766390109e-06,
"loss": 1.1907,
"step": 42300
},
{
"epoch": 0.72,
"learning_rate": 1.705710102489019e-06,
"loss": 1.2545,
"step": 42400
},
{
"epoch": 0.72,
"learning_rate": 1.6955425410769482e-06,
"loss": 1.2322,
"step": 42500
},
{
"epoch": 0.72,
"learning_rate": 1.6853749796648772e-06,
"loss": 1.2505,
"step": 42600
},
{
"epoch": 0.72,
"learning_rate": 1.6752074182528064e-06,
"loss": 1.273,
"step": 42700
},
{
"epoch": 0.72,
"learning_rate": 1.6650398568407356e-06,
"loss": 1.2601,
"step": 42800
},
{
"epoch": 0.72,
"learning_rate": 1.6548722954286645e-06,
"loss": 1.2768,
"step": 42900
},
{
"epoch": 0.73,
"learning_rate": 1.6447047340165937e-06,
"loss": 1.2636,
"step": 43000
},
{
"epoch": 0.73,
"learning_rate": 1.6345371726045225e-06,
"loss": 1.2736,
"step": 43100
},
{
"epoch": 0.73,
"learning_rate": 1.6243696111924517e-06,
"loss": 1.2582,
"step": 43200
},
{
"epoch": 0.73,
"learning_rate": 1.6142020497803808e-06,
"loss": 1.2922,
"step": 43300
},
{
"epoch": 0.73,
"learning_rate": 1.6040344883683098e-06,
"loss": 1.2806,
"step": 43400
},
{
"epoch": 0.74,
"learning_rate": 1.593866926956239e-06,
"loss": 1.3124,
"step": 43500
},
{
"epoch": 0.74,
"learning_rate": 1.583699365544168e-06,
"loss": 1.2964,
"step": 43600
},
{
"epoch": 0.74,
"learning_rate": 1.5735318041320971e-06,
"loss": 1.2518,
"step": 43700
},
{
"epoch": 0.74,
"learning_rate": 1.5633642427200263e-06,
"loss": 1.2706,
"step": 43800
},
{
"epoch": 0.74,
"learning_rate": 1.5531966813079553e-06,
"loss": 1.2833,
"step": 43900
},
{
"epoch": 0.74,
"learning_rate": 1.5430291198958845e-06,
"loss": 1.2996,
"step": 44000
},
{
"epoch": 0.75,
"learning_rate": 1.5328615584838132e-06,
"loss": 1.2872,
"step": 44100
},
{
"epoch": 0.75,
"learning_rate": 1.5226939970717424e-06,
"loss": 1.2789,
"step": 44200
},
{
"epoch": 0.75,
"learning_rate": 1.5125264356596714e-06,
"loss": 1.2682,
"step": 44300
},
{
"epoch": 0.75,
"learning_rate": 1.5023588742476005e-06,
"loss": 1.3165,
"step": 44400
},
{
"epoch": 0.75,
"learning_rate": 1.4921913128355297e-06,
"loss": 1.3272,
"step": 44500
},
{
"epoch": 0.75,
"learning_rate": 1.4820237514234587e-06,
"loss": 1.3175,
"step": 44600
},
{
"epoch": 0.76,
"learning_rate": 1.4718561900113879e-06,
"loss": 1.3275,
"step": 44700
},
{
"epoch": 0.76,
"learning_rate": 1.4616886285993168e-06,
"loss": 1.2995,
"step": 44800
},
{
"epoch": 0.76,
"learning_rate": 1.451521067187246e-06,
"loss": 1.3184,
"step": 44900
},
{
"epoch": 0.76,
"learning_rate": 1.4413535057751752e-06,
"loss": 1.3338,
"step": 45000
},
{
"epoch": 0.76,
"learning_rate": 1.431185944363104e-06,
"loss": 1.3071,
"step": 45100
},
{
"epoch": 0.76,
"learning_rate": 1.4210183829510331e-06,
"loss": 1.2942,
"step": 45200
},
{
"epoch": 0.77,
"learning_rate": 1.4108508215389621e-06,
"loss": 1.3169,
"step": 45300
},
{
"epoch": 0.77,
"learning_rate": 1.4006832601268913e-06,
"loss": 1.3668,
"step": 45400
},
{
"epoch": 0.77,
"learning_rate": 1.3905156987148203e-06,
"loss": 1.3148,
"step": 45500
},
{
"epoch": 0.77,
"learning_rate": 1.3803481373027494e-06,
"loss": 1.365,
"step": 45600
},
{
"epoch": 0.77,
"learning_rate": 1.3701805758906786e-06,
"loss": 1.3083,
"step": 45700
},
{
"epoch": 0.77,
"learning_rate": 1.3600130144786076e-06,
"loss": 1.3567,
"step": 45800
},
{
"epoch": 0.78,
"learning_rate": 1.3498454530665368e-06,
"loss": 1.3985,
"step": 45900
},
{
"epoch": 0.78,
"learning_rate": 1.3396778916544655e-06,
"loss": 1.38,
"step": 46000
},
{
"epoch": 0.78,
"learning_rate": 1.3295103302423947e-06,
"loss": 1.3656,
"step": 46100
},
{
"epoch": 0.78,
"learning_rate": 1.3193427688303239e-06,
"loss": 1.3911,
"step": 46200
},
{
"epoch": 0.78,
"learning_rate": 1.3091752074182529e-06,
"loss": 1.3768,
"step": 46300
},
{
"epoch": 0.78,
"learning_rate": 1.299007646006182e-06,
"loss": 1.4085,
"step": 46400
},
{
"epoch": 0.79,
"learning_rate": 1.288840084594111e-06,
"loss": 1.3772,
"step": 46500
},
{
"epoch": 0.79,
"learning_rate": 1.2786725231820402e-06,
"loss": 1.3681,
"step": 46600
},
{
"epoch": 0.79,
"learning_rate": 1.2685049617699692e-06,
"loss": 1.3595,
"step": 46700
},
{
"epoch": 0.79,
"learning_rate": 1.2583374003578983e-06,
"loss": 1.372,
"step": 46800
},
{
"epoch": 0.79,
"learning_rate": 1.2481698389458273e-06,
"loss": 1.411,
"step": 46900
},
{
"epoch": 0.79,
"learning_rate": 1.2380022775337563e-06,
"loss": 1.3747,
"step": 47000
},
{
"epoch": 0.8,
"learning_rate": 1.2278347161216855e-06,
"loss": 1.349,
"step": 47100
},
{
"epoch": 0.8,
"learning_rate": 1.2176671547096146e-06,
"loss": 1.3944,
"step": 47200
},
{
"epoch": 0.8,
"learning_rate": 1.2074995932975436e-06,
"loss": 1.4021,
"step": 47300
},
{
"epoch": 0.8,
"learning_rate": 1.1973320318854726e-06,
"loss": 1.4005,
"step": 47400
},
{
"epoch": 0.8,
"learning_rate": 1.1871644704734018e-06,
"loss": 1.4209,
"step": 47500
},
{
"epoch": 0.8,
"learning_rate": 1.1769969090613307e-06,
"loss": 1.3936,
"step": 47600
},
{
"epoch": 0.81,
"learning_rate": 1.16682934764926e-06,
"loss": 1.375,
"step": 47700
},
{
"epoch": 0.81,
"learning_rate": 1.156661786237189e-06,
"loss": 1.388,
"step": 47800
},
{
"epoch": 0.81,
"learning_rate": 1.146494224825118e-06,
"loss": 1.3496,
"step": 47900
},
{
"epoch": 0.81,
"learning_rate": 1.136326663413047e-06,
"loss": 1.4065,
"step": 48000
},
{
"epoch": 0.81,
"learning_rate": 1.1261591020009762e-06,
"loss": 1.4378,
"step": 48100
},
{
"epoch": 0.81,
"learning_rate": 1.1159915405889052e-06,
"loss": 1.492,
"step": 48200
},
{
"epoch": 0.82,
"learning_rate": 1.1058239791768343e-06,
"loss": 1.4009,
"step": 48300
},
{
"epoch": 0.82,
"learning_rate": 1.0956564177647633e-06,
"loss": 1.4632,
"step": 48400
},
{
"epoch": 0.82,
"learning_rate": 1.0854888563526925e-06,
"loss": 1.433,
"step": 48500
},
{
"epoch": 0.82,
"learning_rate": 1.0753212949406215e-06,
"loss": 1.483,
"step": 48600
},
{
"epoch": 0.82,
"learning_rate": 1.0651537335285506e-06,
"loss": 1.4401,
"step": 48700
},
{
"epoch": 0.82,
"learning_rate": 1.0549861721164796e-06,
"loss": 1.4332,
"step": 48800
},
{
"epoch": 0.83,
"learning_rate": 1.0448186107044088e-06,
"loss": 1.4229,
"step": 48900
},
{
"epoch": 0.83,
"learning_rate": 1.0346510492923378e-06,
"loss": 1.4616,
"step": 49000
},
{
"epoch": 0.83,
"learning_rate": 1.024483487880267e-06,
"loss": 1.4566,
"step": 49100
},
{
"epoch": 0.83,
"learning_rate": 1.014315926468196e-06,
"loss": 1.4524,
"step": 49200
},
{
"epoch": 0.83,
"learning_rate": 1.0041483650561249e-06,
"loss": 1.4719,
"step": 49300
},
{
"epoch": 0.83,
"learning_rate": 9.93980803644054e-07,
"loss": 1.4893,
"step": 49400
},
{
"epoch": 0.84,
"learning_rate": 9.838132422319832e-07,
"loss": 1.4656,
"step": 49500
},
{
"epoch": 0.84,
"learning_rate": 9.736456808199122e-07,
"loss": 1.4937,
"step": 49600
},
{
"epoch": 0.84,
"learning_rate": 9.634781194078414e-07,
"loss": 1.4616,
"step": 49700
},
{
"epoch": 0.84,
"learning_rate": 9.533105579957704e-07,
"loss": 1.4421,
"step": 49800
},
{
"epoch": 0.84,
"learning_rate": 9.431429965836994e-07,
"loss": 1.5097,
"step": 49900
},
{
"epoch": 0.84,
"learning_rate": 9.329754351716284e-07,
"loss": 1.499,
"step": 50000
},
{
"epoch": 0.85,
"learning_rate": 9.228078737595576e-07,
"loss": 1.488,
"step": 50100
},
{
"epoch": 0.85,
"learning_rate": 9.126403123474867e-07,
"loss": 1.5273,
"step": 50200
},
{
"epoch": 0.85,
"learning_rate": 9.024727509354157e-07,
"loss": 1.4876,
"step": 50300
},
{
"epoch": 0.85,
"learning_rate": 8.923051895233448e-07,
"loss": 1.4964,
"step": 50400
},
{
"epoch": 0.85,
"learning_rate": 8.821376281112738e-07,
"loss": 1.4922,
"step": 50500
},
{
"epoch": 0.86,
"learning_rate": 8.719700666992028e-07,
"loss": 1.4608,
"step": 50600
},
{
"epoch": 0.86,
"learning_rate": 8.61802505287132e-07,
"loss": 1.4756,
"step": 50700
},
{
"epoch": 0.86,
"learning_rate": 8.516349438750611e-07,
"loss": 1.5232,
"step": 50800
},
{
"epoch": 0.86,
"learning_rate": 8.414673824629902e-07,
"loss": 1.5272,
"step": 50900
},
{
"epoch": 0.86,
"learning_rate": 8.312998210509191e-07,
"loss": 1.5539,
"step": 51000
},
{
"epoch": 0.86,
"learning_rate": 8.211322596388482e-07,
"loss": 1.5316,
"step": 51100
},
{
"epoch": 0.87,
"learning_rate": 8.109646982267774e-07,
"loss": 1.5529,
"step": 51200
},
{
"epoch": 0.87,
"learning_rate": 8.007971368147065e-07,
"loss": 1.5013,
"step": 51300
},
{
"epoch": 0.87,
"learning_rate": 7.906295754026355e-07,
"loss": 1.565,
"step": 51400
},
{
"epoch": 0.87,
"learning_rate": 7.804620139905645e-07,
"loss": 1.5304,
"step": 51500
},
{
"epoch": 0.87,
"learning_rate": 7.702944525784936e-07,
"loss": 1.5279,
"step": 51600
},
{
"epoch": 0.87,
"learning_rate": 7.601268911664227e-07,
"loss": 1.5389,
"step": 51700
},
{
"epoch": 0.88,
"learning_rate": 7.499593297543518e-07,
"loss": 1.5408,
"step": 51800
},
{
"epoch": 0.88,
"learning_rate": 7.397917683422809e-07,
"loss": 1.5557,
"step": 51900
},
{
"epoch": 0.88,
"learning_rate": 7.296242069302099e-07,
"loss": 1.5694,
"step": 52000
},
{
"epoch": 0.88,
"learning_rate": 7.19456645518139e-07,
"loss": 1.5553,
"step": 52100
},
{
"epoch": 0.88,
"learning_rate": 7.09289084106068e-07,
"loss": 1.5764,
"step": 52200
},
{
"epoch": 0.88,
"learning_rate": 6.991215226939971e-07,
"loss": 1.5792,
"step": 52300
},
{
"epoch": 0.89,
"learning_rate": 6.889539612819263e-07,
"loss": 1.5821,
"step": 52400
},
{
"epoch": 0.89,
"learning_rate": 6.787863998698553e-07,
"loss": 1.5484,
"step": 52500
},
{
"epoch": 0.89,
"learning_rate": 6.686188384577843e-07,
"loss": 1.5772,
"step": 52600
},
{
"epoch": 0.89,
"learning_rate": 6.584512770457134e-07,
"loss": 1.5898,
"step": 52700
},
{
"epoch": 0.89,
"learning_rate": 6.482837156336425e-07,
"loss": 1.5195,
"step": 52800
},
{
"epoch": 0.89,
"learning_rate": 6.381161542215715e-07,
"loss": 1.5598,
"step": 52900
},
{
"epoch": 0.9,
"learning_rate": 6.279485928095006e-07,
"loss": 1.6432,
"step": 53000
},
{
"epoch": 0.9,
"learning_rate": 6.177810313974297e-07,
"loss": 1.5635,
"step": 53100
},
{
"epoch": 0.9,
"learning_rate": 6.076134699853588e-07,
"loss": 1.5919,
"step": 53200
},
{
"epoch": 0.9,
"learning_rate": 5.974459085732879e-07,
"loss": 1.5913,
"step": 53300
},
{
"epoch": 0.9,
"learning_rate": 5.872783471612168e-07,
"loss": 1.5627,
"step": 53400
},
{
"epoch": 0.9,
"learning_rate": 5.77110785749146e-07,
"loss": 1.6507,
"step": 53500
},
{
"epoch": 0.91,
"learning_rate": 5.669432243370751e-07,
"loss": 1.7103,
"step": 53600
},
{
"epoch": 0.91,
"learning_rate": 5.56775662925004e-07,
"loss": 1.6273,
"step": 53700
},
{
"epoch": 0.91,
"learning_rate": 5.466081015129332e-07,
"loss": 1.6157,
"step": 53800
},
{
"epoch": 0.91,
"learning_rate": 5.364405401008622e-07,
"loss": 1.6314,
"step": 53900
},
{
"epoch": 0.91,
"learning_rate": 5.262729786887913e-07,
"loss": 1.6679,
"step": 54000
},
{
"epoch": 0.91,
"learning_rate": 5.161054172767205e-07,
"loss": 1.6815,
"step": 54100
},
{
"epoch": 0.92,
"learning_rate": 5.059378558646494e-07,
"loss": 1.6441,
"step": 54200
},
{
"epoch": 0.92,
"learning_rate": 4.957702944525785e-07,
"loss": 1.6241,
"step": 54300
},
{
"epoch": 0.92,
"learning_rate": 4.856027330405076e-07,
"loss": 1.6909,
"step": 54400
},
{
"epoch": 0.92,
"learning_rate": 4.7543517162843665e-07,
"loss": 1.7092,
"step": 54500
},
{
"epoch": 0.92,
"learning_rate": 4.652676102163657e-07,
"loss": 1.6423,
"step": 54600
},
{
"epoch": 0.92,
"learning_rate": 4.5510004880429485e-07,
"loss": 1.667,
"step": 54700
},
{
"epoch": 0.93,
"learning_rate": 4.4493248739222387e-07,
"loss": 1.6544,
"step": 54800
},
{
"epoch": 0.93,
"learning_rate": 4.3476492598015294e-07,
"loss": 1.674,
"step": 54900
},
{
"epoch": 0.93,
"learning_rate": 4.24597364568082e-07,
"loss": 1.6642,
"step": 55000
},
{
"epoch": 0.93,
"learning_rate": 4.144298031560111e-07,
"loss": 1.6554,
"step": 55100
},
{
"epoch": 0.93,
"learning_rate": 4.042622417439402e-07,
"loss": 1.7157,
"step": 55200
},
{
"epoch": 0.93,
"learning_rate": 3.9409468033186924e-07,
"loss": 1.6089,
"step": 55300
},
{
"epoch": 0.94,
"learning_rate": 3.839271189197983e-07,
"loss": 1.689,
"step": 55400
},
{
"epoch": 0.94,
"learning_rate": 3.737595575077274e-07,
"loss": 1.7004,
"step": 55500
},
{
"epoch": 0.94,
"learning_rate": 3.6359199609565647e-07,
"loss": 1.6773,
"step": 55600
},
{
"epoch": 0.94,
"learning_rate": 3.534244346835855e-07,
"loss": 1.6339,
"step": 55700
},
{
"epoch": 0.94,
"learning_rate": 3.432568732715146e-07,
"loss": 1.6879,
"step": 55800
},
{
"epoch": 0.94,
"learning_rate": 3.330893118594437e-07,
"loss": 1.7352,
"step": 55900
},
{
"epoch": 0.95,
"learning_rate": 3.229217504473727e-07,
"loss": 1.7616,
"step": 56000
},
{
"epoch": 0.95,
"learning_rate": 3.1275418903530184e-07,
"loss": 1.7308,
"step": 56100
},
{
"epoch": 0.95,
"learning_rate": 3.0258662762323086e-07,
"loss": 1.767,
"step": 56200
},
{
"epoch": 0.95,
"learning_rate": 2.9241906621115993e-07,
"loss": 1.7031,
"step": 56300
},
{
"epoch": 0.95,
"learning_rate": 2.82251504799089e-07,
"loss": 1.714,
"step": 56400
},
{
"epoch": 0.95,
"learning_rate": 2.720839433870181e-07,
"loss": 1.7357,
"step": 56500
},
{
"epoch": 0.96,
"learning_rate": 2.6191638197494716e-07,
"loss": 1.7049,
"step": 56600
},
{
"epoch": 0.96,
"learning_rate": 2.5174882056287623e-07,
"loss": 1.7434,
"step": 56700
},
{
"epoch": 0.96,
"learning_rate": 2.415812591508053e-07,
"loss": 1.75,
"step": 56800
},
{
"epoch": 0.96,
"learning_rate": 2.3141369773873435e-07,
"loss": 1.7449,
"step": 56900
},
{
"epoch": 0.96,
"learning_rate": 2.2124613632666343e-07,
"loss": 1.7693,
"step": 57000
},
{
"epoch": 0.96,
"learning_rate": 2.110785749145925e-07,
"loss": 1.7759,
"step": 57100
},
{
"epoch": 0.97,
"learning_rate": 2.0091101350252158e-07,
"loss": 1.805,
"step": 57200
},
{
"epoch": 0.97,
"learning_rate": 1.9074345209045063e-07,
"loss": 1.7565,
"step": 57300
},
{
"epoch": 0.97,
"learning_rate": 1.8057589067837973e-07,
"loss": 1.7891,
"step": 57400
},
{
"epoch": 0.97,
"learning_rate": 1.704083292663088e-07,
"loss": 1.7562,
"step": 57500
},
{
"epoch": 0.97,
"learning_rate": 1.6024076785423785e-07,
"loss": 1.7761,
"step": 57600
},
{
"epoch": 0.98,
"learning_rate": 1.5007320644216692e-07,
"loss": 1.798,
"step": 57700
},
{
"epoch": 0.98,
"learning_rate": 1.39905645030096e-07,
"loss": 1.7808,
"step": 57800
},
{
"epoch": 0.98,
"learning_rate": 1.2973808361802505e-07,
"loss": 1.7764,
"step": 57900
},
{
"epoch": 0.98,
"learning_rate": 1.1957052220595415e-07,
"loss": 1.7831,
"step": 58000
},
{
"epoch": 0.98,
"learning_rate": 1.094029607938832e-07,
"loss": 1.8296,
"step": 58100
},
{
"epoch": 0.98,
"learning_rate": 9.923539938181228e-08,
"loss": 1.7863,
"step": 58200
},
{
"epoch": 0.99,
"learning_rate": 8.906783796974134e-08,
"loss": 1.7902,
"step": 58300
},
{
"epoch": 0.99,
"learning_rate": 7.89002765576704e-08,
"loss": 1.8269,
"step": 58400
},
{
"epoch": 0.99,
"learning_rate": 6.873271514559948e-08,
"loss": 1.8619,
"step": 58500
},
{
"epoch": 0.99,
"learning_rate": 5.8565153733528555e-08,
"loss": 1.8395,
"step": 58600
},
{
"epoch": 0.99,
"learning_rate": 4.839759232145763e-08,
"loss": 1.7979,
"step": 58700
},
{
"epoch": 0.99,
"learning_rate": 3.82300309093867e-08,
"loss": 1.8391,
"step": 58800
},
{
"epoch": 1.0,
"learning_rate": 2.8062469497315768e-08,
"loss": 1.8435,
"step": 58900
},
{
"epoch": 1.0,
"learning_rate": 1.7894908085244836e-08,
"loss": 1.7877,
"step": 59000
},
{
"epoch": 1.0,
"learning_rate": 7.727346673173906e-09,
"loss": 1.8712,
"step": 59100
},
{
"epoch": 1.0,
"eval_loss": 2.2859742641448975,
"eval_runtime": 193.5251,
"eval_samples_per_second": 129.255,
"eval_steps_per_second": 2.02,
"step": 59176
}
],
"max_steps": 59176,
"num_train_epochs": 1,
"total_flos": 4.501774968361135e+19,
"trial_name": null,
"trial_params": null
}