joelniklaus's picture
Training in progress, step 650000
8fde545
raw
history blame
82.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.182836,
"global_step": 650000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 5.5406,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 3.7083,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 3.0627,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 2.7998,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 2.6425,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 2.5589,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.4647,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.432,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 2.3395,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 2.268,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.1699,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 2.2278,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.8529,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.7047,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.6762,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.1632,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.0574,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 2.0309,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 2.0596,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 1.923,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 1.8665,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.8216,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 1.7746,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 1.738,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 1.7621,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.4583,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.3901,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.2028,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.1564,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.3146,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 1.253,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.4678,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.3828,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3896,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 1.2786,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 1.2617,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 1.2258,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 1.1949,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 1.2313,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.166,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 1.135,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 1.1184,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 1.1188,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 1.0766,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 1.1467,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 1.2094,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 1.1808,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 1.1104,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 1.0752,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.1378,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.9520693421363831,
"eval_runtime": 23.3729,
"eval_samples_per_second": 213.923,
"eval_steps_per_second": 1.711,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 1.062,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 1.213,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 1.2887,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 1.1635,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 1.0488,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 1.219,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 0.96,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 0.7237,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 0.7869,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 1.0635,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 1.1039,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 1.0344,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 1.0226,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 1.0823,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0319,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 1.01,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 1.0433,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 1.0019,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 1.0647,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 0.9993,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 1.0423,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 1.106,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 0.906,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 1.0415,
"step": 74000
},
{
"epoch": 0.07,
"learning_rate": 9.98292246503335e-05,
"loss": 0.9777,
"step": 75000
},
{
"epoch": 0.08,
"learning_rate": 9.981529796748134e-05,
"loss": 1.1837,
"step": 76000
},
{
"epoch": 0.08,
"learning_rate": 9.980082651251175e-05,
"loss": 1.0263,
"step": 77000
},
{
"epoch": 0.08,
"learning_rate": 9.97858104436822e-05,
"loss": 1.0564,
"step": 78000
},
{
"epoch": 0.08,
"learning_rate": 9.977024992520602e-05,
"loss": 1.1334,
"step": 79000
},
{
"epoch": 0.08,
"learning_rate": 9.975414512725057e-05,
"loss": 0.9738,
"step": 80000
},
{
"epoch": 0.08,
"learning_rate": 9.973749622593534e-05,
"loss": 0.9563,
"step": 81000
},
{
"epoch": 0.08,
"learning_rate": 9.972030340333001e-05,
"loss": 0.9526,
"step": 82000
},
{
"epoch": 0.08,
"learning_rate": 9.970256684745258e-05,
"loss": 1.0087,
"step": 83000
},
{
"epoch": 0.08,
"learning_rate": 9.968428675226714e-05,
"loss": 0.9702,
"step": 84000
},
{
"epoch": 0.09,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9558,
"step": 85000
},
{
"epoch": 0.09,
"learning_rate": 9.964609674954696e-05,
"loss": 0.9797,
"step": 86000
},
{
"epoch": 0.09,
"learning_rate": 9.962618725965196e-05,
"loss": 0.971,
"step": 87000
},
{
"epoch": 0.09,
"learning_rate": 9.96057350657239e-05,
"loss": 0.9795,
"step": 88000
},
{
"epoch": 0.09,
"learning_rate": 9.95847403914247e-05,
"loss": 1.0089,
"step": 89000
},
{
"epoch": 0.09,
"learning_rate": 9.956320346634876e-05,
"loss": 1.0765,
"step": 90000
},
{
"epoch": 0.09,
"learning_rate": 9.954112452602045e-05,
"loss": 1.1708,
"step": 91000
},
{
"epoch": 0.09,
"learning_rate": 9.95185038118915e-05,
"loss": 1.1234,
"step": 92000
},
{
"epoch": 0.09,
"learning_rate": 9.949534157133844e-05,
"loss": 1.059,
"step": 93000
},
{
"epoch": 0.09,
"learning_rate": 9.94716380576598e-05,
"loss": 1.0153,
"step": 94000
},
{
"epoch": 0.1,
"learning_rate": 9.944739353007344e-05,
"loss": 0.9817,
"step": 95000
},
{
"epoch": 0.1,
"learning_rate": 9.942260825371358e-05,
"loss": 1.0508,
"step": 96000
},
{
"epoch": 0.1,
"learning_rate": 9.939728249962807e-05,
"loss": 1.0584,
"step": 97000
},
{
"epoch": 0.1,
"learning_rate": 9.937141654477528e-05,
"loss": 1.0159,
"step": 98000
},
{
"epoch": 0.1,
"learning_rate": 9.934501067202117e-05,
"loss": 1.0099,
"step": 99000
},
{
"epoch": 0.1,
"learning_rate": 9.931806517013612e-05,
"loss": 0.9323,
"step": 100000
},
{
"epoch": 0.1,
"eval_loss": 0.8298289179801941,
"eval_runtime": 18.3792,
"eval_samples_per_second": 272.046,
"eval_steps_per_second": 2.176,
"step": 100000
},
{
"epoch": 0.1,
"learning_rate": 9.929058033379181e-05,
"loss": 0.972,
"step": 101000
},
{
"epoch": 0.1,
"learning_rate": 9.926255646355804e-05,
"loss": 0.6894,
"step": 102000
},
{
"epoch": 0.1,
"learning_rate": 9.923399386589933e-05,
"loss": 0.6525,
"step": 103000
},
{
"epoch": 0.1,
"learning_rate": 9.92048928531717e-05,
"loss": 0.8249,
"step": 104000
},
{
"epoch": 0.1,
"learning_rate": 9.917525374361912e-05,
"loss": 1.0445,
"step": 105000
},
{
"epoch": 0.11,
"learning_rate": 9.914507686137019e-05,
"loss": 0.9613,
"step": 106000
},
{
"epoch": 0.11,
"learning_rate": 9.911436253643445e-05,
"loss": 0.9396,
"step": 107000
},
{
"epoch": 0.11,
"learning_rate": 9.90831111046988e-05,
"loss": 1.0517,
"step": 108000
},
{
"epoch": 0.11,
"learning_rate": 9.905132290792394e-05,
"loss": 1.0215,
"step": 109000
},
{
"epoch": 0.11,
"learning_rate": 9.901899829374047e-05,
"loss": 1.0032,
"step": 110000
},
{
"epoch": 0.11,
"learning_rate": 9.89861376156452e-05,
"loss": 1.0618,
"step": 111000
},
{
"epoch": 0.11,
"learning_rate": 9.895274123299723e-05,
"loss": 1.0749,
"step": 112000
},
{
"epoch": 0.11,
"learning_rate": 9.891880951101407e-05,
"loss": 1.0837,
"step": 113000
},
{
"epoch": 0.11,
"learning_rate": 9.888434282076758e-05,
"loss": 0.9592,
"step": 114000
},
{
"epoch": 0.12,
"learning_rate": 9.884934153917997e-05,
"loss": 1.0298,
"step": 115000
},
{
"epoch": 0.12,
"learning_rate": 9.881380604901964e-05,
"loss": 1.0163,
"step": 116000
},
{
"epoch": 0.12,
"learning_rate": 9.877773673889701e-05,
"loss": 0.8,
"step": 117000
},
{
"epoch": 0.12,
"learning_rate": 9.87411340032603e-05,
"loss": 0.9133,
"step": 118000
},
{
"epoch": 0.12,
"learning_rate": 9.870399824239117e-05,
"loss": 0.9643,
"step": 119000
},
{
"epoch": 0.12,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9112,
"step": 120000
},
{
"epoch": 0.12,
"learning_rate": 9.862812927522309e-05,
"loss": 1.023,
"step": 121000
},
{
"epoch": 0.12,
"learning_rate": 9.858939689861506e-05,
"loss": 0.9952,
"step": 122000
},
{
"epoch": 0.12,
"learning_rate": 9.855013315614725e-05,
"loss": 0.984,
"step": 123000
},
{
"epoch": 0.12,
"learning_rate": 9.851033847720166e-05,
"loss": 0.9928,
"step": 124000
},
{
"epoch": 0.12,
"learning_rate": 9.847001329696653e-05,
"loss": 0.9131,
"step": 125000
},
{
"epoch": 0.13,
"learning_rate": 9.842915805643155e-05,
"loss": 0.9251,
"step": 126000
},
{
"epoch": 0.13,
"learning_rate": 9.838777320238312e-05,
"loss": 0.9687,
"step": 127000
},
{
"epoch": 0.13,
"learning_rate": 9.834585918739936e-05,
"loss": 1.0081,
"step": 128000
},
{
"epoch": 0.13,
"learning_rate": 9.830341646984521e-05,
"loss": 0.9352,
"step": 129000
},
{
"epoch": 0.13,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9909,
"step": 130000
},
{
"epoch": 0.13,
"learning_rate": 9.821694678938953e-05,
"loss": 1.0289,
"step": 131000
},
{
"epoch": 0.13,
"learning_rate": 9.817292077210659e-05,
"loss": 1.0766,
"step": 132000
},
{
"epoch": 0.13,
"learning_rate": 9.812836794348004e-05,
"loss": 0.9957,
"step": 133000
},
{
"epoch": 0.13,
"learning_rate": 9.808328879073251e-05,
"loss": 1.0035,
"step": 134000
},
{
"epoch": 0.14,
"learning_rate": 9.803768380684242e-05,
"loss": 1.2201,
"step": 135000
},
{
"epoch": 0.14,
"learning_rate": 9.799155349053851e-05,
"loss": 1.0479,
"step": 136000
},
{
"epoch": 0.14,
"learning_rate": 9.794489834629455e-05,
"loss": 0.916,
"step": 137000
},
{
"epoch": 0.14,
"learning_rate": 9.789771888432375e-05,
"loss": 0.9751,
"step": 138000
},
{
"epoch": 0.14,
"learning_rate": 9.785001562057309e-05,
"loss": 0.9485,
"step": 139000
},
{
"epoch": 0.14,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9192,
"step": 140000
},
{
"epoch": 0.14,
"learning_rate": 9.775303978015585e-05,
"loss": 0.9877,
"step": 141000
},
{
"epoch": 0.14,
"learning_rate": 9.77037682640015e-05,
"loss": 0.989,
"step": 142000
},
{
"epoch": 0.14,
"learning_rate": 9.765397506708023e-05,
"loss": 0.9245,
"step": 143000
},
{
"epoch": 0.14,
"learning_rate": 9.760366073392246e-05,
"loss": 0.9223,
"step": 144000
},
{
"epoch": 0.14,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9474,
"step": 145000
},
{
"epoch": 0.15,
"learning_rate": 9.750147086550844e-05,
"loss": 0.7895,
"step": 146000
},
{
"epoch": 0.15,
"learning_rate": 9.744959644778422e-05,
"loss": 0.6734,
"step": 147000
},
{
"epoch": 0.15,
"learning_rate": 9.739720312887535e-05,
"loss": 0.6778,
"step": 148000
},
{
"epoch": 0.15,
"learning_rate": 9.734429148174675e-05,
"loss": 1.0325,
"step": 149000
},
{
"epoch": 0.15,
"learning_rate": 9.729086208503174e-05,
"loss": 1.017,
"step": 150000
},
{
"epoch": 0.15,
"eval_loss": 0.791193425655365,
"eval_runtime": 27.8851,
"eval_samples_per_second": 179.307,
"eval_steps_per_second": 1.434,
"step": 150000
},
{
"epoch": 0.15,
"learning_rate": 9.723691552302562e-05,
"loss": 1.0169,
"step": 151000
},
{
"epoch": 0.15,
"learning_rate": 9.718245238567939e-05,
"loss": 1.0745,
"step": 152000
},
{
"epoch": 0.15,
"learning_rate": 9.712747326859315e-05,
"loss": 1.0231,
"step": 153000
},
{
"epoch": 0.15,
"learning_rate": 9.707197877300974e-05,
"loss": 0.9675,
"step": 154000
},
{
"epoch": 0.15,
"learning_rate": 9.701596950580806e-05,
"loss": 1.0511,
"step": 155000
},
{
"epoch": 0.16,
"learning_rate": 9.695944607949649e-05,
"loss": 0.9275,
"step": 156000
},
{
"epoch": 0.16,
"learning_rate": 9.690240911220618e-05,
"loss": 0.9136,
"step": 157000
},
{
"epoch": 0.16,
"learning_rate": 9.684485922768422e-05,
"loss": 1.0036,
"step": 158000
},
{
"epoch": 0.16,
"learning_rate": 9.6786797055287e-05,
"loss": 0.8431,
"step": 159000
},
{
"epoch": 0.16,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9113,
"step": 160000
},
{
"epoch": 0.16,
"learning_rate": 9.66691383922964e-05,
"loss": 0.8725,
"step": 161000
},
{
"epoch": 0.16,
"learning_rate": 9.660954318839933e-05,
"loss": 0.7145,
"step": 162000
},
{
"epoch": 0.16,
"learning_rate": 9.654943827000548e-05,
"loss": 0.8835,
"step": 163000
},
{
"epoch": 0.16,
"learning_rate": 9.648882429441257e-05,
"loss": 0.8595,
"step": 164000
},
{
"epoch": 0.17,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9792,
"step": 165000
},
{
"epoch": 0.17,
"learning_rate": 9.636607182864827e-05,
"loss": 0.9287,
"step": 166000
},
{
"epoch": 0.17,
"learning_rate": 9.630393468087818e-05,
"loss": 0.974,
"step": 167000
},
{
"epoch": 0.17,
"learning_rate": 9.624129116069694e-05,
"loss": 1.0263,
"step": 168000
},
{
"epoch": 0.17,
"learning_rate": 9.617814195316411e-05,
"loss": 0.9184,
"step": 169000
},
{
"epoch": 0.17,
"learning_rate": 9.611448774886924e-05,
"loss": 0.9548,
"step": 170000
},
{
"epoch": 0.17,
"learning_rate": 9.605032924392457e-05,
"loss": 0.9853,
"step": 171000
},
{
"epoch": 0.17,
"learning_rate": 9.598566713995718e-05,
"loss": 1.0607,
"step": 172000
},
{
"epoch": 0.17,
"learning_rate": 9.59205021441015e-05,
"loss": 0.925,
"step": 173000
},
{
"epoch": 0.17,
"learning_rate": 9.58548349689915e-05,
"loss": 0.9668,
"step": 174000
},
{
"epoch": 0.17,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9848,
"step": 175000
},
{
"epoch": 0.18,
"learning_rate": 9.572199695899522e-05,
"loss": 0.8986,
"step": 176000
},
{
"epoch": 0.18,
"learning_rate": 9.565482757680415e-05,
"loss": 0.9121,
"step": 177000
},
{
"epoch": 0.18,
"learning_rate": 9.558715892073323e-05,
"loss": 0.9679,
"step": 178000
},
{
"epoch": 0.18,
"learning_rate": 9.551899173079607e-05,
"loss": 0.985,
"step": 179000
},
{
"epoch": 0.18,
"learning_rate": 9.545032675245813e-05,
"loss": 1.0038,
"step": 180000
},
{
"epoch": 0.18,
"learning_rate": 9.538116473662861e-05,
"loss": 0.9433,
"step": 181000
},
{
"epoch": 0.18,
"learning_rate": 9.531150643965223e-05,
"loss": 0.8326,
"step": 182000
},
{
"epoch": 0.18,
"learning_rate": 9.524135262330098e-05,
"loss": 0.9301,
"step": 183000
},
{
"epoch": 0.18,
"learning_rate": 9.517070405476575e-05,
"loss": 0.8511,
"step": 184000
},
{
"epoch": 0.18,
"learning_rate": 9.509956150664796e-05,
"loss": 0.9257,
"step": 185000
},
{
"epoch": 0.19,
"learning_rate": 9.502792575695112e-05,
"loss": 0.9687,
"step": 186000
},
{
"epoch": 0.19,
"learning_rate": 9.49557975890723e-05,
"loss": 0.9373,
"step": 187000
},
{
"epoch": 0.19,
"learning_rate": 9.488317779179361e-05,
"loss": 0.9251,
"step": 188000
},
{
"epoch": 0.19,
"learning_rate": 9.481006715927351e-05,
"loss": 0.9134,
"step": 189000
},
{
"epoch": 0.19,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9581,
"step": 190000
},
{
"epoch": 0.19,
"learning_rate": 9.46623765919727e-05,
"loss": 0.7549,
"step": 191000
},
{
"epoch": 0.19,
"learning_rate": 9.458779827231237e-05,
"loss": 0.7225,
"step": 192000
},
{
"epoch": 0.19,
"learning_rate": 9.451273234763371e-05,
"loss": 0.839,
"step": 193000
},
{
"epoch": 0.19,
"learning_rate": 9.443717963884569e-05,
"loss": 1.1109,
"step": 194000
},
{
"epoch": 0.2,
"learning_rate": 9.43611409721806e-05,
"loss": 0.916,
"step": 195000
},
{
"epoch": 0.2,
"learning_rate": 9.428461717918511e-05,
"loss": 0.8708,
"step": 196000
},
{
"epoch": 0.2,
"learning_rate": 9.420760909671118e-05,
"loss": 1.0268,
"step": 197000
},
{
"epoch": 0.2,
"learning_rate": 9.413011756690685e-05,
"loss": 0.922,
"step": 198000
},
{
"epoch": 0.2,
"learning_rate": 9.405214343720707e-05,
"loss": 0.8987,
"step": 199000
},
{
"epoch": 0.2,
"learning_rate": 9.397368756032445e-05,
"loss": 0.896,
"step": 200000
},
{
"epoch": 0.2,
"eval_loss": 0.7616699934005737,
"eval_runtime": 18.6652,
"eval_samples_per_second": 267.878,
"eval_steps_per_second": 2.143,
"step": 200000
},
{
"epoch": 0.2,
"learning_rate": 9.389475079423988e-05,
"loss": 0.8859,
"step": 201000
},
{
"epoch": 0.2,
"learning_rate": 9.381533400219318e-05,
"loss": 0.9032,
"step": 202000
},
{
"epoch": 0.2,
"learning_rate": 9.373543805267368e-05,
"loss": 0.8627,
"step": 203000
},
{
"epoch": 0.2,
"learning_rate": 9.365506381941066e-05,
"loss": 0.8528,
"step": 204000
},
{
"epoch": 0.2,
"learning_rate": 9.357421218136386e-05,
"loss": 0.9027,
"step": 205000
},
{
"epoch": 0.21,
"learning_rate": 9.349288402271388e-05,
"loss": 0.7006,
"step": 206000
},
{
"epoch": 0.21,
"learning_rate": 9.341108023285238e-05,
"loss": 0.8853,
"step": 207000
},
{
"epoch": 0.21,
"learning_rate": 9.332880170637252e-05,
"loss": 0.885,
"step": 208000
},
{
"epoch": 0.21,
"learning_rate": 9.32460493430591e-05,
"loss": 0.9231,
"step": 209000
},
{
"epoch": 0.21,
"learning_rate": 9.316282404787871e-05,
"loss": 1.0182,
"step": 210000
},
{
"epoch": 0.21,
"learning_rate": 9.30791267309698e-05,
"loss": 1.0948,
"step": 211000
},
{
"epoch": 0.21,
"learning_rate": 9.299495830763286e-05,
"loss": 1.0267,
"step": 212000
},
{
"epoch": 0.21,
"learning_rate": 9.291031969832026e-05,
"loss": 0.9211,
"step": 213000
},
{
"epoch": 0.21,
"learning_rate": 9.282521182862629e-05,
"loss": 1.0041,
"step": 214000
},
{
"epoch": 0.21,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8605,
"step": 215000
},
{
"epoch": 0.22,
"learning_rate": 9.265359203611987e-05,
"loss": 0.9107,
"step": 216000
},
{
"epoch": 0.22,
"learning_rate": 9.256708199011401e-05,
"loss": 0.9696,
"step": 217000
},
{
"epoch": 0.22,
"learning_rate": 9.248010643731935e-05,
"loss": 0.8412,
"step": 218000
},
{
"epoch": 0.22,
"learning_rate": 9.239266632888659e-05,
"loss": 0.896,
"step": 219000
},
{
"epoch": 0.22,
"learning_rate": 9.230476262104677e-05,
"loss": 0.866,
"step": 220000
},
{
"epoch": 0.22,
"learning_rate": 9.221639627510076e-05,
"loss": 0.8752,
"step": 221000
},
{
"epoch": 0.22,
"learning_rate": 9.212756825740873e-05,
"loss": 0.8538,
"step": 222000
},
{
"epoch": 0.22,
"learning_rate": 9.20382795393797e-05,
"loss": 0.9473,
"step": 223000
},
{
"epoch": 0.22,
"learning_rate": 9.194853109746074e-05,
"loss": 0.9972,
"step": 224000
},
{
"epoch": 0.23,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9866,
"step": 225000
},
{
"epoch": 0.23,
"learning_rate": 9.176765897286813e-05,
"loss": 0.8537,
"step": 226000
},
{
"epoch": 0.23,
"learning_rate": 9.167653726818305e-05,
"loss": 0.908,
"step": 227000
},
{
"epoch": 0.23,
"learning_rate": 9.158495979556358e-05,
"loss": 0.8834,
"step": 228000
},
{
"epoch": 0.23,
"learning_rate": 9.14929275564863e-05,
"loss": 0.9218,
"step": 229000
},
{
"epoch": 0.23,
"learning_rate": 9.140044155740101e-05,
"loss": 1.0485,
"step": 230000
},
{
"epoch": 0.23,
"learning_rate": 9.130750280971978e-05,
"loss": 1.0703,
"step": 231000
},
{
"epoch": 0.23,
"learning_rate": 9.121411232980588e-05,
"loss": 0.924,
"step": 232000
},
{
"epoch": 0.23,
"learning_rate": 9.112027113896262e-05,
"loss": 0.8991,
"step": 233000
},
{
"epoch": 0.23,
"learning_rate": 9.102598026342222e-05,
"loss": 1.0302,
"step": 234000
},
{
"epoch": 0.23,
"learning_rate": 9.093124073433463e-05,
"loss": 0.6593,
"step": 235000
},
{
"epoch": 0.24,
"learning_rate": 9.083605358775612e-05,
"loss": 0.6215,
"step": 236000
},
{
"epoch": 0.24,
"learning_rate": 9.074041986463808e-05,
"loss": 0.7131,
"step": 237000
},
{
"epoch": 0.24,
"learning_rate": 9.064434061081562e-05,
"loss": 0.9729,
"step": 238000
},
{
"epoch": 0.24,
"learning_rate": 9.0547816876996e-05,
"loss": 0.8938,
"step": 239000
},
{
"epoch": 0.24,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8624,
"step": 240000
},
{
"epoch": 0.24,
"learning_rate": 9.035344019648702e-05,
"loss": 0.9094,
"step": 241000
},
{
"epoch": 0.24,
"learning_rate": 9.025558937546988e-05,
"loss": 0.9128,
"step": 242000
},
{
"epoch": 0.24,
"learning_rate": 9.015729832577681e-05,
"loss": 0.8819,
"step": 243000
},
{
"epoch": 0.24,
"learning_rate": 9.005856812230304e-05,
"loss": 0.8803,
"step": 244000
},
{
"epoch": 0.24,
"learning_rate": 8.995939984474624e-05,
"loss": 0.8916,
"step": 245000
},
{
"epoch": 0.25,
"learning_rate": 8.98597945775948e-05,
"loss": 0.8937,
"step": 246000
},
{
"epoch": 0.25,
"learning_rate": 8.975975341011596e-05,
"loss": 0.9264,
"step": 247000
},
{
"epoch": 0.25,
"learning_rate": 8.965927743634391e-05,
"loss": 0.8509,
"step": 248000
},
{
"epoch": 0.25,
"learning_rate": 8.955836775506776e-05,
"loss": 0.9534,
"step": 249000
},
{
"epoch": 0.25,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8742,
"step": 250000
},
{
"epoch": 0.25,
"eval_loss": 0.7655419111251831,
"eval_runtime": 18.5521,
"eval_samples_per_second": 269.511,
"eval_steps_per_second": 2.156,
"step": 250000
},
{
"epoch": 0.25,
"learning_rate": 8.935525168886262e-05,
"loss": 0.8662,
"step": 251000
},
{
"epoch": 0.25,
"learning_rate": 8.92530475251784e-05,
"loss": 0.8763,
"step": 252000
},
{
"epoch": 0.25,
"learning_rate": 8.91504140964553e-05,
"loss": 0.8976,
"step": 253000
},
{
"epoch": 0.25,
"learning_rate": 8.90473525250761e-05,
"loss": 1.0331,
"step": 254000
},
{
"epoch": 0.26,
"learning_rate": 8.894386393810563e-05,
"loss": 0.91,
"step": 255000
},
{
"epoch": 0.26,
"learning_rate": 8.883994946727849e-05,
"loss": 0.9419,
"step": 256000
},
{
"epoch": 0.26,
"learning_rate": 8.873561024898668e-05,
"loss": 0.9802,
"step": 257000
},
{
"epoch": 0.26,
"learning_rate": 8.863084742426719e-05,
"loss": 0.8297,
"step": 258000
},
{
"epoch": 0.26,
"learning_rate": 8.852566213878947e-05,
"loss": 0.8449,
"step": 259000
},
{
"epoch": 0.26,
"learning_rate": 8.842005554284296e-05,
"loss": 0.8681,
"step": 260000
},
{
"epoch": 0.26,
"learning_rate": 8.831402879132446e-05,
"loss": 0.876,
"step": 261000
},
{
"epoch": 0.26,
"learning_rate": 8.820758304372557e-05,
"loss": 0.8508,
"step": 262000
},
{
"epoch": 0.26,
"learning_rate": 8.810071946411989e-05,
"loss": 0.866,
"step": 263000
},
{
"epoch": 0.26,
"learning_rate": 8.799343922115044e-05,
"loss": 0.8764,
"step": 264000
},
{
"epoch": 0.27,
"learning_rate": 8.788574348801675e-05,
"loss": 0.8526,
"step": 265000
},
{
"epoch": 0.27,
"learning_rate": 8.77776334424621e-05,
"loss": 0.8841,
"step": 266000
},
{
"epoch": 0.27,
"learning_rate": 8.766911026676064e-05,
"loss": 0.9241,
"step": 267000
},
{
"epoch": 0.27,
"learning_rate": 8.756017514770443e-05,
"loss": 1.0003,
"step": 268000
},
{
"epoch": 0.27,
"learning_rate": 8.745082927659047e-05,
"loss": 1.0552,
"step": 269000
},
{
"epoch": 0.27,
"learning_rate": 8.73410738492077e-05,
"loss": 1.004,
"step": 270000
},
{
"epoch": 0.27,
"learning_rate": 8.723091006582389e-05,
"loss": 0.9244,
"step": 271000
},
{
"epoch": 0.27,
"learning_rate": 8.71203391311725e-05,
"loss": 0.9025,
"step": 272000
},
{
"epoch": 0.27,
"learning_rate": 8.700936225443959e-05,
"loss": 0.9588,
"step": 273000
},
{
"epoch": 0.27,
"learning_rate": 8.689798064925049e-05,
"loss": 0.9329,
"step": 274000
},
{
"epoch": 0.28,
"learning_rate": 8.678619553365659e-05,
"loss": 0.9308,
"step": 275000
},
{
"epoch": 0.28,
"learning_rate": 8.6674008130122e-05,
"loss": 0.9316,
"step": 276000
},
{
"epoch": 0.28,
"learning_rate": 8.656141966551019e-05,
"loss": 0.8706,
"step": 277000
},
{
"epoch": 0.28,
"learning_rate": 8.644843137107059e-05,
"loss": 0.868,
"step": 278000
},
{
"epoch": 0.28,
"learning_rate": 8.633504448242505e-05,
"loss": 0.7627,
"step": 279000
},
{
"epoch": 0.28,
"learning_rate": 8.622126023955446e-05,
"loss": 0.6164,
"step": 280000
},
{
"epoch": 0.28,
"learning_rate": 8.610707988678503e-05,
"loss": 0.5858,
"step": 281000
},
{
"epoch": 0.28,
"learning_rate": 8.599250467277483e-05,
"loss": 0.8624,
"step": 282000
},
{
"epoch": 0.28,
"learning_rate": 8.587753585050004e-05,
"loss": 0.9191,
"step": 283000
},
{
"epoch": 0.28,
"learning_rate": 8.576217467724128e-05,
"loss": 0.862,
"step": 284000
},
{
"epoch": 0.28,
"learning_rate": 8.564642241456986e-05,
"loss": 0.8491,
"step": 285000
},
{
"epoch": 0.29,
"learning_rate": 8.553028032833397e-05,
"loss": 0.9656,
"step": 286000
},
{
"epoch": 0.29,
"learning_rate": 8.541374968864487e-05,
"loss": 0.8991,
"step": 287000
},
{
"epoch": 0.29,
"learning_rate": 8.529683176986295e-05,
"loss": 0.8953,
"step": 288000
},
{
"epoch": 0.29,
"learning_rate": 8.517952785058385e-05,
"loss": 0.9358,
"step": 289000
},
{
"epoch": 0.29,
"learning_rate": 8.506183921362443e-05,
"loss": 0.9938,
"step": 290000
},
{
"epoch": 0.29,
"learning_rate": 8.494376714600878e-05,
"loss": 0.9488,
"step": 291000
},
{
"epoch": 0.29,
"learning_rate": 8.482531293895412e-05,
"loss": 0.8374,
"step": 292000
},
{
"epoch": 0.29,
"learning_rate": 8.470647788785665e-05,
"loss": 0.978,
"step": 293000
},
{
"epoch": 0.29,
"learning_rate": 8.458726329227747e-05,
"loss": 0.8783,
"step": 294000
},
{
"epoch": 0.29,
"learning_rate": 8.44676704559283e-05,
"loss": 0.6261,
"step": 295000
},
{
"epoch": 0.3,
"learning_rate": 8.434770068665723e-05,
"loss": 0.9222,
"step": 296000
},
{
"epoch": 0.3,
"learning_rate": 8.422735529643444e-05,
"loss": 0.8115,
"step": 297000
},
{
"epoch": 0.3,
"learning_rate": 8.410663560133784e-05,
"loss": 0.8912,
"step": 298000
},
{
"epoch": 0.3,
"learning_rate": 8.398554292153866e-05,
"loss": 0.8791,
"step": 299000
},
{
"epoch": 0.3,
"learning_rate": 8.386407858128706e-05,
"loss": 0.9148,
"step": 300000
},
{
"epoch": 0.3,
"eval_loss": 0.7172731161117554,
"eval_runtime": 15.5496,
"eval_samples_per_second": 321.552,
"eval_steps_per_second": 2.572,
"step": 300000
},
{
"epoch": 0.3,
"learning_rate": 8.37422439088976e-05,
"loss": 0.915,
"step": 301000
},
{
"epoch": 0.3,
"learning_rate": 8.362004023673474e-05,
"loss": 0.8523,
"step": 302000
},
{
"epoch": 0.3,
"learning_rate": 8.349746890119826e-05,
"loss": 0.826,
"step": 303000
},
{
"epoch": 0.3,
"learning_rate": 8.337453124270863e-05,
"loss": 0.8494,
"step": 304000
},
{
"epoch": 0.3,
"learning_rate": 8.32512286056924e-05,
"loss": 0.9075,
"step": 305000
},
{
"epoch": 0.31,
"learning_rate": 8.31275623385675e-05,
"loss": 0.8903,
"step": 306000
},
{
"epoch": 0.31,
"learning_rate": 8.300353379372834e-05,
"loss": 0.8592,
"step": 307000
},
{
"epoch": 0.31,
"learning_rate": 8.287914432753123e-05,
"loss": 0.9229,
"step": 308000
},
{
"epoch": 0.31,
"learning_rate": 8.275439530027948e-05,
"loss": 0.932,
"step": 309000
},
{
"epoch": 0.31,
"learning_rate": 8.262928807620843e-05,
"loss": 0.9863,
"step": 310000
},
{
"epoch": 0.31,
"learning_rate": 8.250382402347065e-05,
"loss": 0.903,
"step": 311000
},
{
"epoch": 0.31,
"learning_rate": 8.237800451412095e-05,
"loss": 0.9851,
"step": 312000
},
{
"epoch": 0.31,
"learning_rate": 8.225183092410128e-05,
"loss": 1.0789,
"step": 313000
},
{
"epoch": 0.31,
"learning_rate": 8.212530463322583e-05,
"loss": 0.9383,
"step": 314000
},
{
"epoch": 0.32,
"learning_rate": 8.199842702516583e-05,
"loss": 0.8237,
"step": 315000
},
{
"epoch": 0.32,
"learning_rate": 8.18711994874345e-05,
"loss": 0.9242,
"step": 316000
},
{
"epoch": 0.32,
"learning_rate": 8.174362341137177e-05,
"loss": 0.7982,
"step": 317000
},
{
"epoch": 0.32,
"learning_rate": 8.161570019212921e-05,
"loss": 0.8621,
"step": 318000
},
{
"epoch": 0.32,
"learning_rate": 8.148743122865463e-05,
"loss": 0.9245,
"step": 319000
},
{
"epoch": 0.32,
"learning_rate": 8.135881792367686e-05,
"loss": 0.8692,
"step": 320000
},
{
"epoch": 0.32,
"learning_rate": 8.12298616836904e-05,
"loss": 0.8591,
"step": 321000
},
{
"epoch": 0.32,
"learning_rate": 8.110056391894005e-05,
"loss": 0.8333,
"step": 322000
},
{
"epoch": 0.32,
"learning_rate": 8.097092604340542e-05,
"loss": 0.8595,
"step": 323000
},
{
"epoch": 0.32,
"learning_rate": 8.084094947478556e-05,
"loss": 0.625,
"step": 324000
},
{
"epoch": 0.33,
"learning_rate": 8.07106356344834e-05,
"loss": 0.6157,
"step": 325000
},
{
"epoch": 0.33,
"learning_rate": 8.057998594759022e-05,
"loss": 0.7733,
"step": 326000
},
{
"epoch": 0.33,
"learning_rate": 8.044900184287007e-05,
"loss": 0.9738,
"step": 327000
},
{
"epoch": 0.33,
"learning_rate": 8.031768475274413e-05,
"loss": 0.9321,
"step": 328000
},
{
"epoch": 0.33,
"learning_rate": 8.018603611327504e-05,
"loss": 0.9248,
"step": 329000
},
{
"epoch": 0.33,
"learning_rate": 8.005405736415126e-05,
"loss": 1.0366,
"step": 330000
},
{
"epoch": 0.33,
"learning_rate": 7.992174994867123e-05,
"loss": 0.9022,
"step": 331000
},
{
"epoch": 0.33,
"learning_rate": 7.978911531372765e-05,
"loss": 0.9623,
"step": 332000
},
{
"epoch": 0.33,
"learning_rate": 7.965615490979163e-05,
"loss": 0.9118,
"step": 333000
},
{
"epoch": 0.33,
"learning_rate": 7.952287019089685e-05,
"loss": 0.8619,
"step": 334000
},
{
"epoch": 0.34,
"learning_rate": 7.938926261462366e-05,
"loss": 0.8891,
"step": 335000
},
{
"epoch": 0.34,
"learning_rate": 7.925533364208309e-05,
"loss": 0.8817,
"step": 336000
},
{
"epoch": 0.34,
"learning_rate": 7.912108473790092e-05,
"loss": 0.8017,
"step": 337000
},
{
"epoch": 0.34,
"learning_rate": 7.898651737020166e-05,
"loss": 0.8516,
"step": 338000
},
{
"epoch": 0.34,
"learning_rate": 7.88516330105925e-05,
"loss": 0.7118,
"step": 339000
},
{
"epoch": 0.34,
"learning_rate": 7.871643313414718e-05,
"loss": 0.7548,
"step": 340000
},
{
"epoch": 0.34,
"learning_rate": 7.858091921938988e-05,
"loss": 0.8295,
"step": 341000
},
{
"epoch": 0.34,
"learning_rate": 7.844509274827907e-05,
"loss": 0.8011,
"step": 342000
},
{
"epoch": 0.34,
"learning_rate": 7.830895520619128e-05,
"loss": 0.9296,
"step": 343000
},
{
"epoch": 0.34,
"learning_rate": 7.817250808190483e-05,
"loss": 0.893,
"step": 344000
},
{
"epoch": 0.34,
"learning_rate": 7.803575286758364e-05,
"loss": 0.9352,
"step": 345000
},
{
"epoch": 0.35,
"learning_rate": 7.789869105876083e-05,
"loss": 0.9199,
"step": 346000
},
{
"epoch": 0.35,
"learning_rate": 7.776132415432234e-05,
"loss": 0.839,
"step": 347000
},
{
"epoch": 0.35,
"learning_rate": 7.762365365649067e-05,
"loss": 0.9137,
"step": 348000
},
{
"epoch": 0.35,
"learning_rate": 7.748568107080832e-05,
"loss": 0.9874,
"step": 349000
},
{
"epoch": 0.35,
"learning_rate": 7.734740790612136e-05,
"loss": 0.963,
"step": 350000
},
{
"epoch": 0.35,
"eval_loss": 0.7136013507843018,
"eval_runtime": 20.6051,
"eval_samples_per_second": 242.658,
"eval_steps_per_second": 1.941,
"step": 350000
},
{
"epoch": 0.35,
"learning_rate": 7.720883567456298e-05,
"loss": 0.8143,
"step": 351000
},
{
"epoch": 0.35,
"learning_rate": 7.70699658915369e-05,
"loss": 0.9945,
"step": 352000
},
{
"epoch": 0.35,
"learning_rate": 7.693080007570084e-05,
"loss": 0.8641,
"step": 353000
},
{
"epoch": 0.35,
"learning_rate": 7.679133974894983e-05,
"loss": 0.8163,
"step": 354000
},
{
"epoch": 0.35,
"learning_rate": 7.66515864363997e-05,
"loss": 0.8874,
"step": 355000
},
{
"epoch": 0.36,
"learning_rate": 7.651154166637025e-05,
"loss": 0.9054,
"step": 356000
},
{
"epoch": 0.36,
"learning_rate": 7.637120697036866e-05,
"loss": 0.9617,
"step": 357000
},
{
"epoch": 0.36,
"learning_rate": 7.623058388307269e-05,
"loss": 0.9316,
"step": 358000
},
{
"epoch": 0.36,
"learning_rate": 7.608967394231387e-05,
"loss": 0.8401,
"step": 359000
},
{
"epoch": 0.36,
"learning_rate": 7.594847868906076e-05,
"loss": 0.794,
"step": 360000
},
{
"epoch": 0.36,
"learning_rate": 7.580699966740201e-05,
"loss": 0.8542,
"step": 361000
},
{
"epoch": 0.36,
"learning_rate": 7.566523842452958e-05,
"loss": 0.8194,
"step": 362000
},
{
"epoch": 0.36,
"learning_rate": 7.552319651072164e-05,
"loss": 0.9125,
"step": 363000
},
{
"epoch": 0.36,
"learning_rate": 7.538087547932585e-05,
"loss": 0.9038,
"step": 364000
},
{
"epoch": 0.36,
"learning_rate": 7.52382768867422e-05,
"loss": 0.8814,
"step": 365000
},
{
"epoch": 0.37,
"learning_rate": 7.509540229240601e-05,
"loss": 0.856,
"step": 366000
},
{
"epoch": 0.37,
"learning_rate": 7.495225325877103e-05,
"loss": 0.9046,
"step": 367000
},
{
"epoch": 0.37,
"learning_rate": 7.480883135129211e-05,
"loss": 0.7691,
"step": 368000
},
{
"epoch": 0.37,
"learning_rate": 7.466513813840825e-05,
"loss": 0.7425,
"step": 369000
},
{
"epoch": 0.37,
"learning_rate": 7.452117519152542e-05,
"loss": 0.644,
"step": 370000
},
{
"epoch": 0.37,
"learning_rate": 7.437694408499933e-05,
"loss": 0.9492,
"step": 371000
},
{
"epoch": 0.37,
"learning_rate": 7.423244639611826e-05,
"loss": 1.021,
"step": 372000
},
{
"epoch": 0.37,
"learning_rate": 7.408768370508576e-05,
"loss": 0.8502,
"step": 373000
},
{
"epoch": 0.37,
"learning_rate": 7.394265759500348e-05,
"loss": 0.8453,
"step": 374000
},
{
"epoch": 0.38,
"learning_rate": 7.379736965185368e-05,
"loss": 0.971,
"step": 375000
},
{
"epoch": 0.38,
"learning_rate": 7.365182146448205e-05,
"loss": 0.8415,
"step": 376000
},
{
"epoch": 0.38,
"learning_rate": 7.350601462458024e-05,
"loss": 0.8354,
"step": 377000
},
{
"epoch": 0.38,
"learning_rate": 7.335995072666848e-05,
"loss": 0.8512,
"step": 378000
},
{
"epoch": 0.38,
"learning_rate": 7.32136313680782e-05,
"loss": 0.83,
"step": 379000
},
{
"epoch": 0.38,
"learning_rate": 7.30670581489344e-05,
"loss": 0.8613,
"step": 380000
},
{
"epoch": 0.38,
"learning_rate": 7.292023267213835e-05,
"loss": 0.7769,
"step": 381000
},
{
"epoch": 0.38,
"learning_rate": 7.277315654334997e-05,
"loss": 0.8355,
"step": 382000
},
{
"epoch": 0.38,
"learning_rate": 7.262583137097018e-05,
"loss": 0.8239,
"step": 383000
},
{
"epoch": 0.38,
"learning_rate": 7.247825876612353e-05,
"loss": 0.679,
"step": 384000
},
{
"epoch": 0.39,
"learning_rate": 7.233044034264034e-05,
"loss": 0.8585,
"step": 385000
},
{
"epoch": 0.39,
"learning_rate": 7.218237771703921e-05,
"loss": 0.8158,
"step": 386000
},
{
"epoch": 0.39,
"learning_rate": 7.203407250850928e-05,
"loss": 0.9722,
"step": 387000
},
{
"epoch": 0.39,
"learning_rate": 7.188552633889259e-05,
"loss": 0.948,
"step": 388000
},
{
"epoch": 0.39,
"learning_rate": 7.173674083266624e-05,
"loss": 1.0357,
"step": 389000
},
{
"epoch": 0.39,
"learning_rate": 7.158771761692464e-05,
"loss": 0.965,
"step": 390000
},
{
"epoch": 0.39,
"learning_rate": 7.143845832136188e-05,
"loss": 0.873,
"step": 391000
},
{
"epoch": 0.39,
"learning_rate": 7.128896457825364e-05,
"loss": 0.9059,
"step": 392000
},
{
"epoch": 0.39,
"learning_rate": 7.113923802243957e-05,
"loss": 0.8347,
"step": 393000
},
{
"epoch": 0.39,
"learning_rate": 7.09892802913053e-05,
"loss": 0.8842,
"step": 394000
},
{
"epoch": 0.4,
"learning_rate": 7.083909302476453e-05,
"loss": 0.8766,
"step": 395000
},
{
"epoch": 0.4,
"learning_rate": 7.068867786524116e-05,
"loss": 0.8141,
"step": 396000
},
{
"epoch": 0.4,
"learning_rate": 7.053803645765128e-05,
"loss": 0.845,
"step": 397000
},
{
"epoch": 0.4,
"learning_rate": 7.038717044938519e-05,
"loss": 0.8139,
"step": 398000
},
{
"epoch": 0.4,
"learning_rate": 7.023608149028937e-05,
"loss": 0.8064,
"step": 399000
},
{
"epoch": 0.4,
"learning_rate": 7.008477123264848e-05,
"loss": 0.8716,
"step": 400000
},
{
"epoch": 0.4,
"eval_loss": 0.6985334753990173,
"eval_runtime": 17.8249,
"eval_samples_per_second": 280.507,
"eval_steps_per_second": 2.244,
"step": 400000
},
{
"epoch": 0.4,
"learning_rate": 6.993324133116726e-05,
"loss": 0.9256,
"step": 401000
},
{
"epoch": 0.4,
"learning_rate": 6.978149344295242e-05,
"loss": 0.9333,
"step": 402000
},
{
"epoch": 0.4,
"learning_rate": 6.962952922749457e-05,
"loss": 0.8892,
"step": 403000
},
{
"epoch": 0.4,
"learning_rate": 6.947735034665002e-05,
"loss": 0.8067,
"step": 404000
},
{
"epoch": 0.41,
"learning_rate": 6.932495846462261e-05,
"loss": 0.9025,
"step": 405000
},
{
"epoch": 0.41,
"learning_rate": 6.917235524794558e-05,
"loss": 0.8224,
"step": 406000
},
{
"epoch": 0.41,
"learning_rate": 6.901954236546323e-05,
"loss": 0.9447,
"step": 407000
},
{
"epoch": 0.41,
"learning_rate": 6.886652148831279e-05,
"loss": 1.0075,
"step": 408000
},
{
"epoch": 0.41,
"learning_rate": 6.871329428990602e-05,
"loss": 0.9633,
"step": 409000
},
{
"epoch": 0.41,
"learning_rate": 6.855986244591104e-05,
"loss": 0.8465,
"step": 410000
},
{
"epoch": 0.41,
"learning_rate": 6.840622763423391e-05,
"loss": 0.9227,
"step": 411000
},
{
"epoch": 0.41,
"learning_rate": 6.825239153500029e-05,
"loss": 0.8564,
"step": 412000
},
{
"epoch": 0.41,
"learning_rate": 6.809835583053715e-05,
"loss": 0.5901,
"step": 413000
},
{
"epoch": 0.41,
"learning_rate": 6.794412220535426e-05,
"loss": 0.603,
"step": 414000
},
{
"epoch": 0.41,
"learning_rate": 6.778969234612584e-05,
"loss": 0.819,
"step": 415000
},
{
"epoch": 0.42,
"learning_rate": 6.763506794167208e-05,
"loss": 0.9204,
"step": 416000
},
{
"epoch": 0.42,
"learning_rate": 6.748025068294067e-05,
"loss": 0.8098,
"step": 417000
},
{
"epoch": 0.42,
"learning_rate": 6.732524226298841e-05,
"loss": 0.82,
"step": 418000
},
{
"epoch": 0.42,
"learning_rate": 6.71700443769625e-05,
"loss": 0.89,
"step": 419000
},
{
"epoch": 0.42,
"learning_rate": 6.701465872208216e-05,
"loss": 0.8434,
"step": 420000
},
{
"epoch": 0.42,
"learning_rate": 6.685908699762002e-05,
"loss": 0.8372,
"step": 421000
},
{
"epoch": 0.42,
"learning_rate": 6.670333090488356e-05,
"loss": 0.8512,
"step": 422000
},
{
"epoch": 0.42,
"learning_rate": 6.654739214719641e-05,
"loss": 0.8313,
"step": 423000
},
{
"epoch": 0.42,
"learning_rate": 6.639127242987988e-05,
"loss": 0.8953,
"step": 424000
},
{
"epoch": 0.42,
"learning_rate": 6.623497346023418e-05,
"loss": 0.8422,
"step": 425000
},
{
"epoch": 0.43,
"learning_rate": 6.607849694751977e-05,
"loss": 0.8229,
"step": 426000
},
{
"epoch": 0.43,
"learning_rate": 6.592184460293877e-05,
"loss": 0.9336,
"step": 427000
},
{
"epoch": 0.43,
"learning_rate": 6.576501813961609e-05,
"loss": 0.763,
"step": 428000
},
{
"epoch": 0.43,
"learning_rate": 6.56080192725808e-05,
"loss": 0.8887,
"step": 429000
},
{
"epoch": 0.43,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8105,
"step": 430000
},
{
"epoch": 0.43,
"learning_rate": 6.529351119689688e-05,
"loss": 0.9753,
"step": 431000
},
{
"epoch": 0.43,
"learning_rate": 6.513600542765817e-05,
"loss": 0.8983,
"step": 432000
},
{
"epoch": 0.43,
"learning_rate": 6.497833413348909e-05,
"loss": 0.8644,
"step": 433000
},
{
"epoch": 0.43,
"learning_rate": 6.48204990386577e-05,
"loss": 0.9647,
"step": 434000
},
{
"epoch": 0.43,
"learning_rate": 6.466250186922325e-05,
"loss": 0.8607,
"step": 435000
},
{
"epoch": 0.44,
"learning_rate": 6.450434435301751e-05,
"loss": 0.8015,
"step": 436000
},
{
"epoch": 0.44,
"learning_rate": 6.43460282196257e-05,
"loss": 0.7931,
"step": 437000
},
{
"epoch": 0.44,
"learning_rate": 6.418755520036775e-05,
"loss": 0.8734,
"step": 438000
},
{
"epoch": 0.44,
"learning_rate": 6.402892702827916e-05,
"loss": 0.825,
"step": 439000
},
{
"epoch": 0.44,
"learning_rate": 6.387014543809223e-05,
"loss": 0.7931,
"step": 440000
},
{
"epoch": 0.44,
"learning_rate": 6.371121216621698e-05,
"loss": 0.8351,
"step": 441000
},
{
"epoch": 0.44,
"learning_rate": 6.355212895072223e-05,
"loss": 0.8346,
"step": 442000
},
{
"epoch": 0.44,
"learning_rate": 6.339289753131649e-05,
"loss": 0.8269,
"step": 443000
},
{
"epoch": 0.44,
"learning_rate": 6.323351964932908e-05,
"loss": 0.8478,
"step": 444000
},
{
"epoch": 0.45,
"learning_rate": 6.307399704769099e-05,
"loss": 0.9235,
"step": 445000
},
{
"epoch": 0.45,
"learning_rate": 6.291433147091583e-05,
"loss": 0.9879,
"step": 446000
},
{
"epoch": 0.45,
"learning_rate": 6.275452466508077e-05,
"loss": 1.0008,
"step": 447000
},
{
"epoch": 0.45,
"learning_rate": 6.259457837780742e-05,
"loss": 0.9376,
"step": 448000
},
{
"epoch": 0.45,
"learning_rate": 6.243449435824276e-05,
"loss": 0.8869,
"step": 449000
},
{
"epoch": 0.45,
"learning_rate": 6.227427435703997e-05,
"loss": 0.8355,
"step": 450000
},
{
"epoch": 0.45,
"eval_loss": 0.697124719619751,
"eval_runtime": 17.5819,
"eval_samples_per_second": 284.383,
"eval_steps_per_second": 2.275,
"step": 450000
},
{
"epoch": 0.45,
"learning_rate": 6.211392012633932e-05,
"loss": 0.9502,
"step": 451000
},
{
"epoch": 0.45,
"learning_rate": 6.195343341974899e-05,
"loss": 0.9108,
"step": 452000
},
{
"epoch": 0.45,
"learning_rate": 6.179281599232591e-05,
"loss": 0.8777,
"step": 453000
},
{
"epoch": 0.45,
"learning_rate": 6.163206960055651e-05,
"loss": 0.8867,
"step": 454000
},
{
"epoch": 0.46,
"learning_rate": 6.147119600233758e-05,
"loss": 0.7928,
"step": 455000
},
{
"epoch": 0.46,
"learning_rate": 6.131019695695702e-05,
"loss": 0.8494,
"step": 456000
},
{
"epoch": 0.46,
"learning_rate": 6.11490742250746e-05,
"loss": 0.6217,
"step": 457000
},
{
"epoch": 0.46,
"learning_rate": 6.0987829568702656e-05,
"loss": 0.5812,
"step": 458000
},
{
"epoch": 0.46,
"learning_rate": 6.0826464751186994e-05,
"loss": 0.6252,
"step": 459000
},
{
"epoch": 0.46,
"learning_rate": 6.066498153718735e-05,
"loss": 0.9303,
"step": 460000
},
{
"epoch": 0.46,
"learning_rate": 6.05033816926583e-05,
"loss": 0.84,
"step": 461000
},
{
"epoch": 0.46,
"learning_rate": 6.034166698482984e-05,
"loss": 0.8353,
"step": 462000
},
{
"epoch": 0.46,
"learning_rate": 6.017983918218812e-05,
"loss": 0.8815,
"step": 463000
},
{
"epoch": 0.46,
"learning_rate": 6.001790005445607e-05,
"loss": 0.9098,
"step": 464000
},
{
"epoch": 0.47,
"learning_rate": 5.985585137257401e-05,
"loss": 0.867,
"step": 465000
},
{
"epoch": 0.47,
"learning_rate": 5.969369490868042e-05,
"loss": 0.9113,
"step": 466000
},
{
"epoch": 0.47,
"learning_rate": 5.953143243609235e-05,
"loss": 0.9342,
"step": 467000
},
{
"epoch": 1.0,
"learning_rate": 5.9369065729286245e-05,
"loss": 0.8846,
"step": 468000
},
{
"epoch": 1.0,
"learning_rate": 5.9206596563878357e-05,
"loss": 0.9301,
"step": 469000
},
{
"epoch": 1.0,
"learning_rate": 5.90440267166055e-05,
"loss": 0.9152,
"step": 470000
},
{
"epoch": 1.0,
"learning_rate": 5.888135796530544e-05,
"loss": 0.799,
"step": 471000
},
{
"epoch": 1.0,
"learning_rate": 5.871859208889759e-05,
"loss": 0.7726,
"step": 472000
},
{
"epoch": 1.01,
"learning_rate": 5.85557308673635e-05,
"loss": 0.8203,
"step": 473000
},
{
"epoch": 1.01,
"learning_rate": 5.8392776081727385e-05,
"loss": 0.797,
"step": 474000
},
{
"epoch": 1.01,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.8938,
"step": 475000
},
{
"epoch": 1.01,
"learning_rate": 5.8066592947342555e-05,
"loss": 0.8762,
"step": 476000
},
{
"epoch": 1.01,
"learning_rate": 5.7903368165680327e-05,
"loss": 0.8453,
"step": 477000
},
{
"epoch": 1.01,
"learning_rate": 5.7740056954050084e-05,
"loss": 0.8266,
"step": 478000
},
{
"epoch": 1.01,
"learning_rate": 5.757666109839702e-05,
"loss": 0.879,
"step": 479000
},
{
"epoch": 1.01,
"learning_rate": 5.74131823855921e-05,
"loss": 0.7411,
"step": 480000
},
{
"epoch": 1.01,
"learning_rate": 5.72496226034123e-05,
"loss": 0.7136,
"step": 481000
},
{
"epoch": 1.01,
"learning_rate": 5.7085983540521216e-05,
"loss": 0.6234,
"step": 482000
},
{
"epoch": 1.02,
"learning_rate": 5.692226698644938e-05,
"loss": 0.9437,
"step": 483000
},
{
"epoch": 1.02,
"learning_rate": 5.675847473157485e-05,
"loss": 0.9815,
"step": 484000
},
{
"epoch": 1.02,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.823,
"step": 485000
},
{
"epoch": 1.02,
"learning_rate": 5.6430670285049314e-05,
"loss": 0.8444,
"step": 486000
},
{
"epoch": 1.02,
"learning_rate": 5.6266661678215216e-05,
"loss": 0.9281,
"step": 487000
},
{
"epoch": 1.02,
"learning_rate": 5.6102584540173006e-05,
"loss": 0.8186,
"step": 488000
},
{
"epoch": 1.02,
"learning_rate": 5.5938440665244006e-05,
"loss": 0.8222,
"step": 489000
},
{
"epoch": 1.02,
"learning_rate": 5.577423184847932e-05,
"loss": 0.8257,
"step": 490000
},
{
"epoch": 1.02,
"learning_rate": 5.560995988564023e-05,
"loss": 0.8054,
"step": 491000
},
{
"epoch": 1.02,
"learning_rate": 5.544562657317863e-05,
"loss": 0.8528,
"step": 492000
},
{
"epoch": 1.03,
"learning_rate": 5.52812337082173e-05,
"loss": 0.7576,
"step": 493000
},
{
"epoch": 1.03,
"learning_rate": 5.511678308853026e-05,
"loss": 0.8198,
"step": 494000
},
{
"epoch": 1.03,
"learning_rate": 5.495227651252315e-05,
"loss": 0.7852,
"step": 495000
},
{
"epoch": 1.03,
"learning_rate": 5.478771577921351e-05,
"loss": 0.6855,
"step": 496000
},
{
"epoch": 1.03,
"learning_rate": 5.462310268821118e-05,
"loss": 0.8479,
"step": 497000
},
{
"epoch": 1.03,
"learning_rate": 5.445843903969854e-05,
"loss": 0.8115,
"step": 498000
},
{
"epoch": 1.03,
"learning_rate": 5.4293726634410855e-05,
"loss": 0.9621,
"step": 499000
},
{
"epoch": 1.03,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.9168,
"step": 500000
},
{
"epoch": 1.03,
"eval_loss": 0.674498975276947,
"eval_runtime": 16.0771,
"eval_samples_per_second": 311.002,
"eval_steps_per_second": 2.488,
"step": 500000
},
{
"epoch": 1.03,
"learning_rate": 5.396416275909779e-05,
"loss": 0.9973,
"step": 501000
},
{
"epoch": 1.03,
"learning_rate": 5.379931489313016e-05,
"loss": 0.9341,
"step": 502000
},
{
"epoch": 1.04,
"learning_rate": 5.363442547846356e-05,
"loss": 0.8718,
"step": 503000
},
{
"epoch": 1.04,
"learning_rate": 5.3469496318302204e-05,
"loss": 0.875,
"step": 504000
},
{
"epoch": 1.04,
"learning_rate": 5.330452921628497e-05,
"loss": 0.8277,
"step": 505000
},
{
"epoch": 1.04,
"learning_rate": 5.313952597646568e-05,
"loss": 0.8664,
"step": 506000
},
{
"epoch": 1.04,
"learning_rate": 5.297448840329329e-05,
"loss": 0.8438,
"step": 507000
},
{
"epoch": 1.04,
"learning_rate": 5.280941830159227e-05,
"loss": 0.806,
"step": 508000
},
{
"epoch": 1.04,
"learning_rate": 5.264431747654284e-05,
"loss": 0.8429,
"step": 509000
},
{
"epoch": 1.04,
"learning_rate": 5.247918773366112e-05,
"loss": 0.812,
"step": 510000
},
{
"epoch": 1.04,
"learning_rate": 5.231403087877955e-05,
"loss": 0.7825,
"step": 511000
},
{
"epoch": 1.04,
"learning_rate": 5.214884871802703e-05,
"loss": 0.8497,
"step": 512000
},
{
"epoch": 1.05,
"learning_rate": 5.198364305780922e-05,
"loss": 0.8943,
"step": 513000
},
{
"epoch": 1.05,
"learning_rate": 5.1818415704788725e-05,
"loss": 0.902,
"step": 514000
},
{
"epoch": 1.05,
"learning_rate": 5.165316846586541e-05,
"loss": 0.8598,
"step": 515000
},
{
"epoch": 1.05,
"learning_rate": 5.148790314815663e-05,
"loss": 0.8136,
"step": 516000
},
{
"epoch": 1.05,
"learning_rate": 5.132262155897739e-05,
"loss": 0.8697,
"step": 517000
},
{
"epoch": 1.05,
"learning_rate": 5.1157325505820694e-05,
"loss": 0.81,
"step": 518000
},
{
"epoch": 1.05,
"learning_rate": 5.0992016796337686e-05,
"loss": 0.9347,
"step": 519000
},
{
"epoch": 1.05,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.9681,
"step": 520000
},
{
"epoch": 1.05,
"learning_rate": 5.066136863966963e-05,
"loss": 0.8955,
"step": 521000
},
{
"epoch": 1.05,
"learning_rate": 5.0496032808399815e-05,
"loss": 0.7938,
"step": 522000
},
{
"epoch": 1.06,
"learning_rate": 5.033069155259471e-05,
"loss": 0.9381,
"step": 523000
},
{
"epoch": 1.06,
"learning_rate": 5.016534668039976e-05,
"loss": 0.8194,
"step": 524000
},
{
"epoch": 1.06,
"learning_rate": 5e-05,
"loss": 0.5973,
"step": 525000
},
{
"epoch": 1.06,
"learning_rate": 4.9834653319600246e-05,
"loss": 0.6418,
"step": 526000
},
{
"epoch": 1.06,
"learning_rate": 4.96693084474053e-05,
"loss": 0.812,
"step": 527000
},
{
"epoch": 1.06,
"learning_rate": 4.950396719160018e-05,
"loss": 0.8911,
"step": 528000
},
{
"epoch": 1.06,
"learning_rate": 4.93386313603304e-05,
"loss": 0.7858,
"step": 529000
},
{
"epoch": 1.06,
"learning_rate": 4.917330276168208e-05,
"loss": 0.8034,
"step": 530000
},
{
"epoch": 1.06,
"learning_rate": 4.9007983203662326e-05,
"loss": 0.8688,
"step": 531000
},
{
"epoch": 1.06,
"learning_rate": 4.884267449417931e-05,
"loss": 0.8252,
"step": 532000
},
{
"epoch": 1.07,
"learning_rate": 4.867737844102261e-05,
"loss": 0.8071,
"step": 533000
},
{
"epoch": 1.07,
"learning_rate": 4.851209685184338e-05,
"loss": 0.8314,
"step": 534000
},
{
"epoch": 1.07,
"learning_rate": 4.834683153413459e-05,
"loss": 0.8104,
"step": 535000
},
{
"epoch": 1.07,
"learning_rate": 4.818158429521129e-05,
"loss": 0.8502,
"step": 536000
},
{
"epoch": 1.07,
"learning_rate": 4.801635694219079e-05,
"loss": 0.8218,
"step": 537000
},
{
"epoch": 1.07,
"learning_rate": 4.785115128197298e-05,
"loss": 0.8166,
"step": 538000
},
{
"epoch": 1.07,
"learning_rate": 4.7685969121220456e-05,
"loss": 0.9017,
"step": 539000
},
{
"epoch": 1.07,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.7798,
"step": 540000
},
{
"epoch": 1.07,
"learning_rate": 4.735568252345718e-05,
"loss": 0.87,
"step": 541000
},
{
"epoch": 1.07,
"learning_rate": 4.7190581698407725e-05,
"loss": 0.8164,
"step": 542000
},
{
"epoch": 1.08,
"learning_rate": 4.702551159670672e-05,
"loss": 0.9666,
"step": 543000
},
{
"epoch": 1.08,
"learning_rate": 4.6860474023534335e-05,
"loss": 0.8515,
"step": 544000
},
{
"epoch": 1.08,
"learning_rate": 4.669547078371504e-05,
"loss": 0.8472,
"step": 545000
},
{
"epoch": 1.08,
"learning_rate": 4.65305036816978e-05,
"loss": 0.9444,
"step": 546000
},
{
"epoch": 1.08,
"learning_rate": 4.6365574521536445e-05,
"loss": 0.8187,
"step": 547000
},
{
"epoch": 1.08,
"learning_rate": 4.620068510686985e-05,
"loss": 0.785,
"step": 548000
},
{
"epoch": 1.08,
"learning_rate": 4.60358372409022e-05,
"loss": 0.7807,
"step": 549000
},
{
"epoch": 1.08,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.8409,
"step": 550000
},
{
"epoch": 1.08,
"eval_loss": 0.6636775135993958,
"eval_runtime": 17.9783,
"eval_samples_per_second": 278.113,
"eval_steps_per_second": 2.225,
"step": 550000
},
{
"epoch": 1.08,
"learning_rate": 4.570627336558915e-05,
"loss": 0.7968,
"step": 551000
},
{
"epoch": 1.08,
"learning_rate": 4.554156096030149e-05,
"loss": 0.7846,
"step": 552000
},
{
"epoch": 1.09,
"learning_rate": 4.537689731178883e-05,
"loss": 0.8321,
"step": 553000
},
{
"epoch": 1.09,
"learning_rate": 4.5212284220786494e-05,
"loss": 0.8271,
"step": 554000
},
{
"epoch": 1.09,
"learning_rate": 4.504772348747687e-05,
"loss": 0.8188,
"step": 555000
},
{
"epoch": 1.09,
"learning_rate": 4.488321691146975e-05,
"loss": 0.8242,
"step": 556000
},
{
"epoch": 1.09,
"learning_rate": 4.471876629178273e-05,
"loss": 0.8932,
"step": 557000
},
{
"epoch": 1.09,
"learning_rate": 4.4554373426821374e-05,
"loss": 0.9601,
"step": 558000
},
{
"epoch": 1.09,
"learning_rate": 4.439004011435979e-05,
"loss": 0.9741,
"step": 559000
},
{
"epoch": 1.09,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.9242,
"step": 560000
},
{
"epoch": 1.09,
"learning_rate": 4.406155933475599e-05,
"loss": 0.8644,
"step": 561000
},
{
"epoch": 1.09,
"learning_rate": 4.3897415459827e-05,
"loss": 0.8362,
"step": 562000
},
{
"epoch": 1.1,
"learning_rate": 4.373333832178478e-05,
"loss": 0.9213,
"step": 563000
},
{
"epoch": 1.1,
"learning_rate": 4.3569329714950704e-05,
"loss": 0.8705,
"step": 564000
},
{
"epoch": 1.1,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.8364,
"step": 565000
},
{
"epoch": 1.1,
"learning_rate": 4.324152526842517e-05,
"loss": 0.8189,
"step": 566000
},
{
"epoch": 1.1,
"learning_rate": 4.307773301355062e-05,
"loss": 0.7703,
"step": 567000
},
{
"epoch": 1.1,
"learning_rate": 4.291401645947879e-05,
"loss": 0.8481,
"step": 568000
},
{
"epoch": 1.1,
"learning_rate": 4.275037739658771e-05,
"loss": 0.6138,
"step": 569000
},
{
"epoch": 1.1,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.5879,
"step": 570000
},
{
"epoch": 1.1,
"learning_rate": 4.2423338901602985e-05,
"loss": 0.6654,
"step": 571000
},
{
"epoch": 1.1,
"learning_rate": 4.2259943045949934e-05,
"loss": 0.9013,
"step": 572000
},
{
"epoch": 1.11,
"learning_rate": 4.209663183431969e-05,
"loss": 0.8264,
"step": 573000
},
{
"epoch": 1.11,
"learning_rate": 4.1933407052657456e-05,
"loss": 0.8106,
"step": 574000
},
{
"epoch": 1.11,
"learning_rate": 4.17702704859633e-05,
"loss": 0.8735,
"step": 575000
},
{
"epoch": 1.11,
"learning_rate": 4.160722391827262e-05,
"loss": 0.89,
"step": 576000
},
{
"epoch": 1.11,
"learning_rate": 4.14442691326365e-05,
"loss": 0.8614,
"step": 577000
},
{
"epoch": 1.11,
"learning_rate": 4.1281407911102425e-05,
"loss": 0.8948,
"step": 578000
},
{
"epoch": 1.11,
"learning_rate": 4.111864203469457e-05,
"loss": 0.9226,
"step": 579000
},
{
"epoch": 1.11,
"learning_rate": 4.095597328339452e-05,
"loss": 0.9281,
"step": 580000
},
{
"epoch": 1.11,
"learning_rate": 4.079340343612165e-05,
"loss": 0.8609,
"step": 581000
},
{
"epoch": 1.11,
"learning_rate": 4.063093427071376e-05,
"loss": 0.867,
"step": 582000
},
{
"epoch": 1.12,
"learning_rate": 4.046856756390767e-05,
"loss": 0.889,
"step": 583000
},
{
"epoch": 1.12,
"learning_rate": 4.0306305091319595e-05,
"loss": 0.7524,
"step": 584000
},
{
"epoch": 1.12,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.7564,
"step": 585000
},
{
"epoch": 1.12,
"learning_rate": 3.9982099945543945e-05,
"loss": 0.8495,
"step": 586000
},
{
"epoch": 1.12,
"learning_rate": 3.982016081781189e-05,
"loss": 0.7789,
"step": 587000
},
{
"epoch": 1.12,
"learning_rate": 3.965833301517017e-05,
"loss": 0.8923,
"step": 588000
},
{
"epoch": 1.12,
"learning_rate": 3.949661830734172e-05,
"loss": 0.8434,
"step": 589000
},
{
"epoch": 1.12,
"learning_rate": 3.933501846281267e-05,
"loss": 0.8489,
"step": 590000
},
{
"epoch": 1.12,
"learning_rate": 3.917353524881302e-05,
"loss": 0.8898,
"step": 591000
},
{
"epoch": 1.12,
"learning_rate": 3.901217043129735e-05,
"loss": 0.7854,
"step": 592000
},
{
"epoch": 1.13,
"learning_rate": 3.8850925774925425e-05,
"loss": 0.8117,
"step": 593000
},
{
"epoch": 1.13,
"learning_rate": 3.8689803043043e-05,
"loss": 0.8306,
"step": 594000
},
{
"epoch": 1.13,
"learning_rate": 3.852880399766243e-05,
"loss": 0.8714,
"step": 595000
},
{
"epoch": 1.13,
"learning_rate": 3.836793039944349e-05,
"loss": 0.8211,
"step": 596000
},
{
"epoch": 1.13,
"learning_rate": 3.820718400767409e-05,
"loss": 0.8571,
"step": 597000
},
{
"epoch": 1.13,
"learning_rate": 3.8046566580251e-05,
"loss": 0.9326,
"step": 598000
},
{
"epoch": 1.13,
"learning_rate": 3.788607987366069e-05,
"loss": 0.9272,
"step": 599000
},
{
"epoch": 1.13,
"learning_rate": 3.772572564296005e-05,
"loss": 0.8941,
"step": 600000
},
{
"epoch": 1.13,
"eval_loss": 0.6667138934135437,
"eval_runtime": 20.0379,
"eval_samples_per_second": 249.527,
"eval_steps_per_second": 1.996,
"step": 600000
},
{
"epoch": 1.13,
"learning_rate": 3.756550564175727e-05,
"loss": 0.8701,
"step": 601000
},
{
"epoch": 1.13,
"learning_rate": 3.74054216221926e-05,
"loss": 1.0681,
"step": 602000
},
{
"epoch": 1.14,
"learning_rate": 3.7245475334919246e-05,
"loss": 0.9387,
"step": 603000
},
{
"epoch": 1.14,
"learning_rate": 3.7085668529084184e-05,
"loss": 0.8274,
"step": 604000
},
{
"epoch": 1.14,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.8394,
"step": 605000
},
{
"epoch": 1.14,
"learning_rate": 3.676648035067093e-05,
"loss": 0.8616,
"step": 606000
},
{
"epoch": 1.14,
"learning_rate": 3.6607102468683526e-05,
"loss": 0.7878,
"step": 607000
},
{
"epoch": 1.14,
"learning_rate": 3.6447871049277796e-05,
"loss": 0.851,
"step": 608000
},
{
"epoch": 1.14,
"learning_rate": 3.628878783378302e-05,
"loss": 0.8921,
"step": 609000
},
{
"epoch": 1.14,
"learning_rate": 3.612985456190778e-05,
"loss": 0.8103,
"step": 610000
},
{
"epoch": 1.14,
"learning_rate": 3.597107297172084e-05,
"loss": 0.7994,
"step": 611000
},
{
"epoch": 1.14,
"learning_rate": 3.581244479963225e-05,
"loss": 0.8195,
"step": 612000
},
{
"epoch": 1.15,
"learning_rate": 3.5653971780374295e-05,
"loss": 0.7297,
"step": 613000
},
{
"epoch": 1.15,
"learning_rate": 3.5495655646982505e-05,
"loss": 0.5922,
"step": 614000
},
{
"epoch": 1.15,
"learning_rate": 3.533749813077677e-05,
"loss": 0.5985,
"step": 615000
},
{
"epoch": 1.15,
"learning_rate": 3.517950096134232e-05,
"loss": 0.8612,
"step": 616000
},
{
"epoch": 1.15,
"learning_rate": 3.5021665866510925e-05,
"loss": 0.9064,
"step": 617000
},
{
"epoch": 1.15,
"learning_rate": 3.4863994572341843e-05,
"loss": 0.8714,
"step": 618000
},
{
"epoch": 1.15,
"learning_rate": 3.470648880310313e-05,
"loss": 0.9363,
"step": 619000
},
{
"epoch": 1.15,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.9445,
"step": 620000
},
{
"epoch": 1.15,
"learning_rate": 3.439198072741921e-05,
"loss": 0.8435,
"step": 621000
},
{
"epoch": 1.15,
"learning_rate": 3.423498186038393e-05,
"loss": 0.9403,
"step": 622000
},
{
"epoch": 1.16,
"learning_rate": 3.407815539706124e-05,
"loss": 0.8306,
"step": 623000
},
{
"epoch": 1.16,
"learning_rate": 3.392150305248024e-05,
"loss": 0.7926,
"step": 624000
},
{
"epoch": 1.16,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.9036,
"step": 625000
},
{
"epoch": 1.16,
"learning_rate": 3.360872757012011e-05,
"loss": 0.7548,
"step": 626000
},
{
"epoch": 1.16,
"learning_rate": 3.3452607852803584e-05,
"loss": 0.7814,
"step": 627000
},
{
"epoch": 1.16,
"learning_rate": 3.329666909511645e-05,
"loss": 0.8012,
"step": 628000
},
{
"epoch": 1.16,
"learning_rate": 3.3140913002379995e-05,
"loss": 0.5988,
"step": 629000
},
{
"epoch": 1.16,
"learning_rate": 3.298534127791785e-05,
"loss": 0.7778,
"step": 630000
},
{
"epoch": 1.16,
"learning_rate": 3.282995562303754e-05,
"loss": 0.7613,
"step": 631000
},
{
"epoch": 1.16,
"learning_rate": 3.267475773701161e-05,
"loss": 0.8414,
"step": 632000
},
{
"epoch": 1.17,
"learning_rate": 3.251974931705933e-05,
"loss": 0.8397,
"step": 633000
},
{
"epoch": 1.17,
"learning_rate": 3.236493205832795e-05,
"loss": 0.867,
"step": 634000
},
{
"epoch": 1.17,
"learning_rate": 3.221030765387417e-05,
"loss": 0.9058,
"step": 635000
},
{
"epoch": 1.17,
"learning_rate": 3.205587779464576e-05,
"loss": 0.8261,
"step": 636000
},
{
"epoch": 1.17,
"learning_rate": 3.190164416946285e-05,
"loss": 0.8263,
"step": 637000
},
{
"epoch": 1.17,
"learning_rate": 3.1747608464999725e-05,
"loss": 0.867,
"step": 638000
},
{
"epoch": 1.17,
"learning_rate": 3.1593772365766105e-05,
"loss": 0.9696,
"step": 639000
},
{
"epoch": 1.17,
"learning_rate": 3.144013755408895e-05,
"loss": 0.8438,
"step": 640000
},
{
"epoch": 1.17,
"learning_rate": 3.128670571009399e-05,
"loss": 0.8345,
"step": 641000
},
{
"epoch": 1.17,
"learning_rate": 3.113347851168721e-05,
"loss": 0.9103,
"step": 642000
},
{
"epoch": 1.18,
"learning_rate": 3.098045763453678e-05,
"loss": 0.7886,
"step": 643000
},
{
"epoch": 1.18,
"learning_rate": 3.082764475205442e-05,
"loss": 0.806,
"step": 644000
},
{
"epoch": 1.18,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.8494,
"step": 645000
},
{
"epoch": 1.18,
"learning_rate": 3.052264965335e-05,
"loss": 0.8645,
"step": 646000
},
{
"epoch": 1.18,
"learning_rate": 3.0370470772505433e-05,
"loss": 0.9104,
"step": 647000
},
{
"epoch": 1.18,
"learning_rate": 3.0218506557047598e-05,
"loss": 0.8603,
"step": 648000
},
{
"epoch": 1.18,
"learning_rate": 3.006675866883275e-05,
"loss": 0.74,
"step": 649000
},
{
"epoch": 1.18,
"learning_rate": 2.991522876735154e-05,
"loss": 0.8312,
"step": 650000
},
{
"epoch": 1.18,
"eval_loss": 0.6602705121040344,
"eval_runtime": 21.6119,
"eval_samples_per_second": 231.354,
"eval_steps_per_second": 1.851,
"step": 650000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.0949517516484903e+19,
"trial_name": null,
"trial_params": null
}