joelniklaus's picture
Training in progress, step 1000000
b0f5e50
raw
history blame
127 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 13.044672,
"global_step": 1000000,
"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": 6.3672,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 4.2266,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 3.455,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 3.1273,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 2.9742,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 2.512,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.4775,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.3822,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 2.3201,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 1.9967,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.0182,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 1.9828,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.9629,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.7017,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.7443,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.7487,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.7432,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 1.5099,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 1.5699,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 1.5984,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 1.6125,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.3986,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 1.4639,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 1.5011,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 1.5123,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.1547,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.0934,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.1841,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.1414,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 0.932,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 0.9457,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.0372,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.0318,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 0.853,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 0.8694,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 0.9591,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 0.9554,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 0.7879,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 0.8222,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 0.9203,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 0.8901,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 0.7294,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 0.8641,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 0.9008,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 0.8812,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 0.7237,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 0.7512,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 0.8537,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 0.875,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.6754,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.7630542516708374,
"eval_runtime": 18.8077,
"eval_samples_per_second": 265.849,
"eval_steps_per_second": 2.127,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 0.6769,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 0.791,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 0.7444,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 0.5965,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 0.6098,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 0.793,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 0.763,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 0.6073,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 0.6535,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 0.726,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 0.7172,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 0.6354,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 0.732,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 0.8263,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 0.7744,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 0.6703,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 0.6941,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 0.7965,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 0.7626,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 0.6523,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 0.6779,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 0.7793,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 0.7288,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 0.6309,
"step": 74000
},
{
"epoch": 1.0,
"learning_rate": 9.98292246503335e-05,
"loss": 0.6925,
"step": 75000
},
{
"epoch": 1.0,
"learning_rate": 9.981529796748134e-05,
"loss": 0.7533,
"step": 76000
},
{
"epoch": 1.0,
"learning_rate": 9.980082651251175e-05,
"loss": 0.6479,
"step": 77000
},
{
"epoch": 1.0,
"learning_rate": 9.97858104436822e-05,
"loss": 0.6771,
"step": 78000
},
{
"epoch": 1.0,
"learning_rate": 9.977024992520602e-05,
"loss": 0.7804,
"step": 79000
},
{
"epoch": 1.01,
"learning_rate": 9.975414512725057e-05,
"loss": 0.7307,
"step": 80000
},
{
"epoch": 1.01,
"learning_rate": 9.973749622593534e-05,
"loss": 0.6237,
"step": 81000
},
{
"epoch": 1.01,
"learning_rate": 9.972030340333001e-05,
"loss": 0.6588,
"step": 82000
},
{
"epoch": 1.01,
"learning_rate": 9.970256684745258e-05,
"loss": 0.7606,
"step": 83000
},
{
"epoch": 1.01,
"learning_rate": 9.968428675226714e-05,
"loss": 0.7172,
"step": 84000
},
{
"epoch": 1.01,
"learning_rate": 9.966546331768191e-05,
"loss": 0.6364,
"step": 85000
},
{
"epoch": 1.01,
"learning_rate": 9.964609674954696e-05,
"loss": 0.6548,
"step": 86000
},
{
"epoch": 1.01,
"learning_rate": 9.962618725965196e-05,
"loss": 0.7607,
"step": 87000
},
{
"epoch": 1.01,
"learning_rate": 9.96057350657239e-05,
"loss": 0.7034,
"step": 88000
},
{
"epoch": 1.01,
"learning_rate": 9.95847403914247e-05,
"loss": 0.6235,
"step": 89000
},
{
"epoch": 1.02,
"learning_rate": 9.956320346634876e-05,
"loss": 0.6536,
"step": 90000
},
{
"epoch": 1.02,
"learning_rate": 9.954112452602045e-05,
"loss": 0.751,
"step": 91000
},
{
"epoch": 1.02,
"learning_rate": 9.95185038118915e-05,
"loss": 0.6947,
"step": 92000
},
{
"epoch": 1.02,
"learning_rate": 9.949534157133844e-05,
"loss": 0.6093,
"step": 93000
},
{
"epoch": 1.02,
"learning_rate": 9.94716380576598e-05,
"loss": 0.6381,
"step": 94000
},
{
"epoch": 1.02,
"learning_rate": 9.944739353007344e-05,
"loss": 0.7458,
"step": 95000
},
{
"epoch": 1.02,
"learning_rate": 9.942260825371358e-05,
"loss": 0.6852,
"step": 96000
},
{
"epoch": 1.02,
"learning_rate": 9.939728249962807e-05,
"loss": 0.6071,
"step": 97000
},
{
"epoch": 1.02,
"learning_rate": 9.937141654477528e-05,
"loss": 0.643,
"step": 98000
},
{
"epoch": 1.02,
"learning_rate": 9.934501067202117e-05,
"loss": 0.7379,
"step": 99000
},
{
"epoch": 1.03,
"learning_rate": 9.931806517013612e-05,
"loss": 0.6769,
"step": 100000
},
{
"epoch": 1.03,
"eval_loss": 0.6102472543716431,
"eval_runtime": 11.7254,
"eval_samples_per_second": 426.425,
"eval_steps_per_second": 3.411,
"step": 100000
},
{
"epoch": 1.03,
"learning_rate": 9.929058033379181e-05,
"loss": 0.6087,
"step": 101000
},
{
"epoch": 1.03,
"learning_rate": 9.926255646355804e-05,
"loss": 0.6345,
"step": 102000
},
{
"epoch": 1.03,
"learning_rate": 9.923399386589933e-05,
"loss": 0.7874,
"step": 103000
},
{
"epoch": 1.03,
"learning_rate": 9.92048928531717e-05,
"loss": 0.7083,
"step": 104000
},
{
"epoch": 1.03,
"learning_rate": 9.917525374361912e-05,
"loss": 0.6389,
"step": 105000
},
{
"epoch": 1.03,
"learning_rate": 9.914507686137019e-05,
"loss": 0.6606,
"step": 106000
},
{
"epoch": 1.03,
"learning_rate": 9.911436253643445e-05,
"loss": 0.7553,
"step": 107000
},
{
"epoch": 1.03,
"learning_rate": 9.90831111046988e-05,
"loss": 0.6917,
"step": 108000
},
{
"epoch": 1.03,
"learning_rate": 9.905132290792394e-05,
"loss": 0.6292,
"step": 109000
},
{
"epoch": 1.04,
"learning_rate": 9.901899829374047e-05,
"loss": 0.6451,
"step": 110000
},
{
"epoch": 1.04,
"learning_rate": 9.89861376156452e-05,
"loss": 0.737,
"step": 111000
},
{
"epoch": 1.04,
"learning_rate": 9.895274123299723e-05,
"loss": 0.6705,
"step": 112000
},
{
"epoch": 1.04,
"learning_rate": 9.891880951101407e-05,
"loss": 0.6131,
"step": 113000
},
{
"epoch": 1.04,
"learning_rate": 9.888434282076758e-05,
"loss": 0.6409,
"step": 114000
},
{
"epoch": 1.04,
"learning_rate": 9.884934153917997e-05,
"loss": 0.7323,
"step": 115000
},
{
"epoch": 1.04,
"learning_rate": 9.881380604901964e-05,
"loss": 0.6435,
"step": 116000
},
{
"epoch": 1.04,
"learning_rate": 9.877773673889701e-05,
"loss": 0.5864,
"step": 117000
},
{
"epoch": 1.04,
"learning_rate": 9.87411340032603e-05,
"loss": 0.7054,
"step": 118000
},
{
"epoch": 1.04,
"learning_rate": 9.870399824239117e-05,
"loss": 0.7264,
"step": 119000
},
{
"epoch": 1.05,
"learning_rate": 9.86663298624003e-05,
"loss": 0.6552,
"step": 120000
},
{
"epoch": 1.05,
"learning_rate": 9.862812927522309e-05,
"loss": 0.5895,
"step": 121000
},
{
"epoch": 1.05,
"learning_rate": 9.858939689861506e-05,
"loss": 0.6186,
"step": 122000
},
{
"epoch": 1.05,
"learning_rate": 9.855013315614725e-05,
"loss": 0.7107,
"step": 123000
},
{
"epoch": 1.05,
"learning_rate": 9.851033847720166e-05,
"loss": 0.6597,
"step": 124000
},
{
"epoch": 1.05,
"learning_rate": 9.847001329696653e-05,
"loss": 0.5509,
"step": 125000
},
{
"epoch": 1.05,
"learning_rate": 9.842915805643155e-05,
"loss": 0.5652,
"step": 126000
},
{
"epoch": 1.05,
"learning_rate": 9.838777320238312e-05,
"loss": 0.6696,
"step": 127000
},
{
"epoch": 1.05,
"learning_rate": 9.834585918739936e-05,
"loss": 0.576,
"step": 128000
},
{
"epoch": 1.05,
"learning_rate": 9.830341646984521e-05,
"loss": 0.5011,
"step": 129000
},
{
"epoch": 1.06,
"learning_rate": 9.826044551386744e-05,
"loss": 0.5285,
"step": 130000
},
{
"epoch": 1.06,
"learning_rate": 9.821694678938953e-05,
"loss": 0.6968,
"step": 131000
},
{
"epoch": 1.06,
"learning_rate": 9.817292077210659e-05,
"loss": 0.6078,
"step": 132000
},
{
"epoch": 1.06,
"learning_rate": 9.812836794348004e-05,
"loss": 0.528,
"step": 133000
},
{
"epoch": 1.06,
"learning_rate": 9.808328879073251e-05,
"loss": 0.5604,
"step": 134000
},
{
"epoch": 1.06,
"learning_rate": 9.803768380684242e-05,
"loss": 0.6439,
"step": 135000
},
{
"epoch": 1.06,
"learning_rate": 9.799155349053851e-05,
"loss": 0.5815,
"step": 136000
},
{
"epoch": 1.06,
"learning_rate": 9.794489834629455e-05,
"loss": 0.5637,
"step": 137000
},
{
"epoch": 1.06,
"learning_rate": 9.789771888432375e-05,
"loss": 0.6391,
"step": 138000
},
{
"epoch": 1.06,
"learning_rate": 9.785001562057309e-05,
"loss": 0.7222,
"step": 139000
},
{
"epoch": 1.07,
"learning_rate": 9.780178907671789e-05,
"loss": 0.636,
"step": 140000
},
{
"epoch": 1.07,
"learning_rate": 9.775303978015585e-05,
"loss": 0.5804,
"step": 141000
},
{
"epoch": 1.07,
"learning_rate": 9.77037682640015e-05,
"loss": 0.6218,
"step": 142000
},
{
"epoch": 1.07,
"learning_rate": 9.765397506708023e-05,
"loss": 0.7073,
"step": 143000
},
{
"epoch": 1.07,
"learning_rate": 9.760366073392246e-05,
"loss": 0.637,
"step": 144000
},
{
"epoch": 1.07,
"learning_rate": 9.755282581475769e-05,
"loss": 0.5743,
"step": 145000
},
{
"epoch": 1.07,
"learning_rate": 9.750147086550844e-05,
"loss": 0.6157,
"step": 146000
},
{
"epoch": 1.07,
"learning_rate": 9.744959644778422e-05,
"loss": 0.6953,
"step": 147000
},
{
"epoch": 1.07,
"learning_rate": 9.739720312887535e-05,
"loss": 0.6186,
"step": 148000
},
{
"epoch": 1.07,
"learning_rate": 9.734429148174675e-05,
"loss": 0.558,
"step": 149000
},
{
"epoch": 2.0,
"learning_rate": 9.729086208503174e-05,
"loss": 0.6412,
"step": 150000
},
{
"epoch": 2.0,
"eval_loss": 0.5495593547821045,
"eval_runtime": 13.9203,
"eval_samples_per_second": 359.188,
"eval_steps_per_second": 2.874,
"step": 150000
},
{
"epoch": 2.0,
"learning_rate": 9.723691552302562e-05,
"loss": 0.6384,
"step": 151000
},
{
"epoch": 2.0,
"learning_rate": 9.718245238567939e-05,
"loss": 0.5805,
"step": 152000
},
{
"epoch": 2.0,
"learning_rate": 9.712747326859315e-05,
"loss": 0.6239,
"step": 153000
},
{
"epoch": 2.0,
"learning_rate": 9.707197877300974e-05,
"loss": 0.7055,
"step": 154000
},
{
"epoch": 2.01,
"learning_rate": 9.701596950580806e-05,
"loss": 0.6253,
"step": 155000
},
{
"epoch": 2.01,
"learning_rate": 9.695944607949649e-05,
"loss": 0.5609,
"step": 156000
},
{
"epoch": 2.01,
"learning_rate": 9.690240911220618e-05,
"loss": 0.6131,
"step": 157000
},
{
"epoch": 2.01,
"learning_rate": 9.684485922768422e-05,
"loss": 0.6929,
"step": 158000
},
{
"epoch": 2.01,
"learning_rate": 9.6786797055287e-05,
"loss": 0.6254,
"step": 159000
},
{
"epoch": 2.01,
"learning_rate": 9.672822322997305e-05,
"loss": 0.5704,
"step": 160000
},
{
"epoch": 2.01,
"learning_rate": 9.66691383922964e-05,
"loss": 0.6173,
"step": 161000
},
{
"epoch": 2.01,
"learning_rate": 9.660954318839933e-05,
"loss": 0.6923,
"step": 162000
},
{
"epoch": 2.01,
"learning_rate": 9.654943827000548e-05,
"loss": 0.6177,
"step": 163000
},
{
"epoch": 2.01,
"learning_rate": 9.648882429441257e-05,
"loss": 0.5645,
"step": 164000
},
{
"epoch": 2.02,
"learning_rate": 9.642770192448536e-05,
"loss": 0.6195,
"step": 165000
},
{
"epoch": 2.02,
"learning_rate": 9.636607182864827e-05,
"loss": 0.6855,
"step": 166000
},
{
"epoch": 2.02,
"learning_rate": 9.630393468087818e-05,
"loss": 0.6098,
"step": 167000
},
{
"epoch": 2.02,
"learning_rate": 9.624129116069694e-05,
"loss": 0.5529,
"step": 168000
},
{
"epoch": 2.02,
"learning_rate": 9.617814195316411e-05,
"loss": 0.6117,
"step": 169000
},
{
"epoch": 2.02,
"learning_rate": 9.611448774886924e-05,
"loss": 0.6863,
"step": 170000
},
{
"epoch": 2.02,
"learning_rate": 9.605032924392457e-05,
"loss": 0.6045,
"step": 171000
},
{
"epoch": 2.02,
"learning_rate": 9.598566713995718e-05,
"loss": 0.5543,
"step": 172000
},
{
"epoch": 2.02,
"learning_rate": 9.59205021441015e-05,
"loss": 0.6172,
"step": 173000
},
{
"epoch": 2.02,
"learning_rate": 9.58548349689915e-05,
"loss": 0.6812,
"step": 174000
},
{
"epoch": 2.03,
"learning_rate": 9.578866633275288e-05,
"loss": 0.6001,
"step": 175000
},
{
"epoch": 2.03,
"learning_rate": 9.572199695899522e-05,
"loss": 0.5586,
"step": 176000
},
{
"epoch": 2.03,
"learning_rate": 9.565482757680415e-05,
"loss": 0.6131,
"step": 177000
},
{
"epoch": 2.03,
"learning_rate": 9.558715892073323e-05,
"loss": 0.7337,
"step": 178000
},
{
"epoch": 2.03,
"learning_rate": 9.551899173079607e-05,
"loss": 0.6354,
"step": 179000
},
{
"epoch": 2.03,
"learning_rate": 9.545032675245813e-05,
"loss": 0.5862,
"step": 180000
},
{
"epoch": 2.03,
"learning_rate": 9.538116473662861e-05,
"loss": 0.6405,
"step": 181000
},
{
"epoch": 2.03,
"learning_rate": 9.531150643965223e-05,
"loss": 0.7012,
"step": 182000
},
{
"epoch": 2.03,
"learning_rate": 9.524135262330098e-05,
"loss": 0.6251,
"step": 183000
},
{
"epoch": 2.03,
"learning_rate": 9.517070405476575e-05,
"loss": 0.5769,
"step": 184000
},
{
"epoch": 2.04,
"learning_rate": 9.509956150664796e-05,
"loss": 0.6236,
"step": 185000
},
{
"epoch": 2.04,
"learning_rate": 9.502792575695112e-05,
"loss": 0.6861,
"step": 186000
},
{
"epoch": 2.04,
"learning_rate": 9.49557975890723e-05,
"loss": 0.6085,
"step": 187000
},
{
"epoch": 2.04,
"learning_rate": 9.488317779179361e-05,
"loss": 0.5646,
"step": 188000
},
{
"epoch": 2.04,
"learning_rate": 9.481006715927351e-05,
"loss": 0.6233,
"step": 189000
},
{
"epoch": 2.04,
"learning_rate": 9.473646649103818e-05,
"loss": 0.6826,
"step": 190000
},
{
"epoch": 2.04,
"learning_rate": 9.46623765919727e-05,
"loss": 0.5821,
"step": 191000
},
{
"epoch": 2.04,
"learning_rate": 9.458779827231237e-05,
"loss": 0.5434,
"step": 192000
},
{
"epoch": 2.04,
"learning_rate": 9.451273234763371e-05,
"loss": 0.6866,
"step": 193000
},
{
"epoch": 2.04,
"learning_rate": 9.443717963884569e-05,
"loss": 0.6754,
"step": 194000
},
{
"epoch": 2.05,
"learning_rate": 9.43611409721806e-05,
"loss": 0.595,
"step": 195000
},
{
"epoch": 2.05,
"learning_rate": 9.428461717918511e-05,
"loss": 0.5455,
"step": 196000
},
{
"epoch": 2.05,
"learning_rate": 9.420760909671118e-05,
"loss": 0.6074,
"step": 197000
},
{
"epoch": 2.05,
"learning_rate": 9.413011756690685e-05,
"loss": 0.6704,
"step": 198000
},
{
"epoch": 2.05,
"learning_rate": 9.405214343720707e-05,
"loss": 0.5826,
"step": 199000
},
{
"epoch": 2.05,
"learning_rate": 9.397368756032445e-05,
"loss": 0.5053,
"step": 200000
},
{
"epoch": 2.05,
"eval_loss": 0.5608457326889038,
"eval_runtime": 17.3418,
"eval_samples_per_second": 288.321,
"eval_steps_per_second": 2.307,
"step": 200000
},
{
"epoch": 2.05,
"learning_rate": 9.389475079423988e-05,
"loss": 0.5538,
"step": 201000
},
{
"epoch": 2.05,
"learning_rate": 9.381533400219318e-05,
"loss": 0.6221,
"step": 202000
},
{
"epoch": 2.05,
"learning_rate": 9.373543805267368e-05,
"loss": 0.5195,
"step": 203000
},
{
"epoch": 2.05,
"learning_rate": 9.365506381941066e-05,
"loss": 0.4605,
"step": 204000
},
{
"epoch": 2.06,
"learning_rate": 9.357421218136386e-05,
"loss": 0.5422,
"step": 205000
},
{
"epoch": 2.06,
"learning_rate": 9.349288402271388e-05,
"loss": 0.6484,
"step": 206000
},
{
"epoch": 2.06,
"learning_rate": 9.341108023285238e-05,
"loss": 0.5452,
"step": 207000
},
{
"epoch": 2.06,
"learning_rate": 9.332880170637252e-05,
"loss": 0.4941,
"step": 208000
},
{
"epoch": 2.06,
"learning_rate": 9.32460493430591e-05,
"loss": 0.5471,
"step": 209000
},
{
"epoch": 2.06,
"learning_rate": 9.316282404787871e-05,
"loss": 0.6098,
"step": 210000
},
{
"epoch": 2.06,
"learning_rate": 9.30791267309698e-05,
"loss": 0.5248,
"step": 211000
},
{
"epoch": 2.06,
"learning_rate": 9.299495830763286e-05,
"loss": 0.5404,
"step": 212000
},
{
"epoch": 2.06,
"learning_rate": 9.291031969832026e-05,
"loss": 0.6299,
"step": 213000
},
{
"epoch": 2.06,
"learning_rate": 9.282521182862629e-05,
"loss": 0.6772,
"step": 214000
},
{
"epoch": 2.07,
"learning_rate": 9.273963562927695e-05,
"loss": 0.5821,
"step": 215000
},
{
"epoch": 2.07,
"learning_rate": 9.265359203611987e-05,
"loss": 0.5431,
"step": 216000
},
{
"epoch": 2.07,
"learning_rate": 9.256708199011401e-05,
"loss": 0.6144,
"step": 217000
},
{
"epoch": 2.07,
"learning_rate": 9.248010643731935e-05,
"loss": 0.6669,
"step": 218000
},
{
"epoch": 2.07,
"learning_rate": 9.239266632888659e-05,
"loss": 0.5825,
"step": 219000
},
{
"epoch": 2.07,
"learning_rate": 9.230476262104677e-05,
"loss": 0.538,
"step": 220000
},
{
"epoch": 2.07,
"learning_rate": 9.221639627510076e-05,
"loss": 0.6098,
"step": 221000
},
{
"epoch": 2.07,
"learning_rate": 9.212756825740873e-05,
"loss": 0.6585,
"step": 222000
},
{
"epoch": 2.07,
"learning_rate": 9.20382795393797e-05,
"loss": 0.5626,
"step": 223000
},
{
"epoch": 2.07,
"learning_rate": 9.194853109746074e-05,
"loss": 0.5253,
"step": 224000
},
{
"epoch": 3.0,
"learning_rate": 9.185832391312644e-05,
"loss": 0.6331,
"step": 225000
},
{
"epoch": 3.0,
"learning_rate": 9.176765897286813e-05,
"loss": 0.5881,
"step": 226000
},
{
"epoch": 3.0,
"learning_rate": 9.167653726818305e-05,
"loss": 0.5461,
"step": 227000
},
{
"epoch": 3.0,
"learning_rate": 9.158495979556358e-05,
"loss": 0.6214,
"step": 228000
},
{
"epoch": 3.0,
"learning_rate": 9.14929275564863e-05,
"loss": 0.6674,
"step": 229000
},
{
"epoch": 3.01,
"learning_rate": 9.140044155740101e-05,
"loss": 0.5701,
"step": 230000
},
{
"epoch": 3.01,
"learning_rate": 9.130750280971978e-05,
"loss": 0.5298,
"step": 231000
},
{
"epoch": 3.01,
"learning_rate": 9.121411232980588e-05,
"loss": 0.6117,
"step": 232000
},
{
"epoch": 3.01,
"learning_rate": 9.112027113896262e-05,
"loss": 0.6592,
"step": 233000
},
{
"epoch": 3.01,
"learning_rate": 9.102598026342222e-05,
"loss": 0.5754,
"step": 234000
},
{
"epoch": 3.01,
"learning_rate": 9.093124073433463e-05,
"loss": 0.5375,
"step": 235000
},
{
"epoch": 3.01,
"learning_rate": 9.083605358775612e-05,
"loss": 0.6183,
"step": 236000
},
{
"epoch": 3.01,
"learning_rate": 9.074041986463808e-05,
"loss": 0.6569,
"step": 237000
},
{
"epoch": 3.01,
"learning_rate": 9.064434061081562e-05,
"loss": 0.5674,
"step": 238000
},
{
"epoch": 3.01,
"learning_rate": 9.0547816876996e-05,
"loss": 0.5347,
"step": 239000
},
{
"epoch": 3.02,
"learning_rate": 9.045084971874738e-05,
"loss": 0.6205,
"step": 240000
},
{
"epoch": 3.02,
"learning_rate": 9.035344019648702e-05,
"loss": 0.6481,
"step": 241000
},
{
"epoch": 3.02,
"learning_rate": 9.025558937546988e-05,
"loss": 0.5655,
"step": 242000
},
{
"epoch": 3.02,
"learning_rate": 9.015729832577681e-05,
"loss": 0.5187,
"step": 243000
},
{
"epoch": 3.02,
"learning_rate": 9.005856812230304e-05,
"loss": 0.6164,
"step": 244000
},
{
"epoch": 3.02,
"learning_rate": 8.995939984474624e-05,
"loss": 0.6533,
"step": 245000
},
{
"epoch": 3.02,
"learning_rate": 8.98597945775948e-05,
"loss": 0.5609,
"step": 246000
},
{
"epoch": 3.02,
"learning_rate": 8.975975341011596e-05,
"loss": 0.519,
"step": 247000
},
{
"epoch": 3.02,
"learning_rate": 8.965927743634391e-05,
"loss": 0.621,
"step": 248000
},
{
"epoch": 3.02,
"learning_rate": 8.955836775506776e-05,
"loss": 0.6486,
"step": 249000
},
{
"epoch": 3.03,
"learning_rate": 8.945702546981969e-05,
"loss": 0.559,
"step": 250000
},
{
"epoch": 3.03,
"eval_loss": 0.5268664360046387,
"eval_runtime": 11.4435,
"eval_samples_per_second": 436.928,
"eval_steps_per_second": 3.495,
"step": 250000
},
{
"epoch": 3.03,
"learning_rate": 8.935525168886262e-05,
"loss": 0.5209,
"step": 251000
},
{
"epoch": 3.03,
"learning_rate": 8.92530475251784e-05,
"loss": 0.6308,
"step": 252000
},
{
"epoch": 3.03,
"learning_rate": 8.91504140964553e-05,
"loss": 0.6974,
"step": 253000
},
{
"epoch": 3.03,
"learning_rate": 8.90473525250761e-05,
"loss": 0.5908,
"step": 254000
},
{
"epoch": 3.03,
"learning_rate": 8.894386393810563e-05,
"loss": 0.5479,
"step": 255000
},
{
"epoch": 3.03,
"learning_rate": 8.883994946727849e-05,
"loss": 0.6469,
"step": 256000
},
{
"epoch": 3.03,
"learning_rate": 8.873561024898668e-05,
"loss": 0.6698,
"step": 257000
},
{
"epoch": 3.03,
"learning_rate": 8.863084742426719e-05,
"loss": 0.5853,
"step": 258000
},
{
"epoch": 3.03,
"learning_rate": 8.852566213878947e-05,
"loss": 0.5375,
"step": 259000
},
{
"epoch": 3.04,
"learning_rate": 8.842005554284296e-05,
"loss": 0.6279,
"step": 260000
},
{
"epoch": 3.04,
"learning_rate": 8.831402879132446e-05,
"loss": 0.6603,
"step": 261000
},
{
"epoch": 3.04,
"learning_rate": 8.820758304372557e-05,
"loss": 0.5651,
"step": 262000
},
{
"epoch": 3.04,
"learning_rate": 8.810071946411989e-05,
"loss": 0.5273,
"step": 263000
},
{
"epoch": 3.04,
"learning_rate": 8.799343922115044e-05,
"loss": 0.6326,
"step": 264000
},
{
"epoch": 3.04,
"learning_rate": 8.788574348801675e-05,
"loss": 0.65,
"step": 265000
},
{
"epoch": 3.04,
"learning_rate": 8.77776334424621e-05,
"loss": 0.5387,
"step": 266000
},
{
"epoch": 3.04,
"learning_rate": 8.766911026676064e-05,
"loss": 0.5295,
"step": 267000
},
{
"epoch": 3.04,
"learning_rate": 8.756017514770443e-05,
"loss": 0.6781,
"step": 268000
},
{
"epoch": 3.04,
"learning_rate": 8.745082927659047e-05,
"loss": 0.6467,
"step": 269000
},
{
"epoch": 3.05,
"learning_rate": 8.73410738492077e-05,
"loss": 0.5519,
"step": 270000
},
{
"epoch": 3.05,
"learning_rate": 8.723091006582389e-05,
"loss": 0.5124,
"step": 271000
},
{
"epoch": 3.05,
"learning_rate": 8.71203391311725e-05,
"loss": 0.6158,
"step": 272000
},
{
"epoch": 3.05,
"learning_rate": 8.700936225443959e-05,
"loss": 0.6507,
"step": 273000
},
{
"epoch": 3.05,
"learning_rate": 8.689798064925049e-05,
"loss": 0.5282,
"step": 274000
},
{
"epoch": 3.05,
"learning_rate": 8.678619553365659e-05,
"loss": 0.469,
"step": 275000
},
{
"epoch": 3.05,
"learning_rate": 8.6674008130122e-05,
"loss": 0.5651,
"step": 276000
},
{
"epoch": 3.05,
"learning_rate": 8.656141966551019e-05,
"loss": 0.5938,
"step": 277000
},
{
"epoch": 3.05,
"learning_rate": 8.644843137107059e-05,
"loss": 0.4783,
"step": 278000
},
{
"epoch": 3.05,
"learning_rate": 8.633504448242505e-05,
"loss": 0.4277,
"step": 279000
},
{
"epoch": 3.06,
"learning_rate": 8.622126023955446e-05,
"loss": 0.5687,
"step": 280000
},
{
"epoch": 3.06,
"learning_rate": 8.610707988678503e-05,
"loss": 0.6185,
"step": 281000
},
{
"epoch": 3.06,
"learning_rate": 8.599250467277483e-05,
"loss": 0.5009,
"step": 282000
},
{
"epoch": 3.06,
"learning_rate": 8.587753585050004e-05,
"loss": 0.4683,
"step": 283000
},
{
"epoch": 3.06,
"learning_rate": 8.576217467724128e-05,
"loss": 0.5506,
"step": 284000
},
{
"epoch": 3.06,
"learning_rate": 8.564642241456986e-05,
"loss": 0.5913,
"step": 285000
},
{
"epoch": 3.06,
"learning_rate": 8.553028032833397e-05,
"loss": 0.4842,
"step": 286000
},
{
"epoch": 3.06,
"learning_rate": 8.541374968864487e-05,
"loss": 0.5228,
"step": 287000
},
{
"epoch": 3.06,
"learning_rate": 8.529683176986295e-05,
"loss": 0.6378,
"step": 288000
},
{
"epoch": 3.06,
"learning_rate": 8.517952785058385e-05,
"loss": 0.6458,
"step": 289000
},
{
"epoch": 3.07,
"learning_rate": 8.506183921362443e-05,
"loss": 0.5461,
"step": 290000
},
{
"epoch": 3.07,
"learning_rate": 8.494376714600878e-05,
"loss": 0.5145,
"step": 291000
},
{
"epoch": 3.07,
"learning_rate": 8.482531293895412e-05,
"loss": 0.6218,
"step": 292000
},
{
"epoch": 3.07,
"learning_rate": 8.470647788785665e-05,
"loss": 0.6423,
"step": 293000
},
{
"epoch": 3.07,
"learning_rate": 8.458726329227747e-05,
"loss": 0.5416,
"step": 294000
},
{
"epoch": 3.07,
"learning_rate": 8.44676704559283e-05,
"loss": 0.5123,
"step": 295000
},
{
"epoch": 3.07,
"learning_rate": 8.434770068665723e-05,
"loss": 0.616,
"step": 296000
},
{
"epoch": 3.07,
"learning_rate": 8.422735529643444e-05,
"loss": 0.633,
"step": 297000
},
{
"epoch": 3.07,
"learning_rate": 8.410663560133784e-05,
"loss": 0.5251,
"step": 298000
},
{
"epoch": 3.07,
"learning_rate": 8.398554292153866e-05,
"loss": 0.505,
"step": 299000
},
{
"epoch": 4.0,
"learning_rate": 8.386407858128706e-05,
"loss": 0.6352,
"step": 300000
},
{
"epoch": 4.0,
"eval_loss": 0.4907972514629364,
"eval_runtime": 11.7344,
"eval_samples_per_second": 426.098,
"eval_steps_per_second": 3.409,
"step": 300000
},
{
"epoch": 4.0,
"learning_rate": 8.37422439088976e-05,
"loss": 0.5502,
"step": 301000
},
{
"epoch": 4.0,
"learning_rate": 8.362004023673474e-05,
"loss": 0.5196,
"step": 302000
},
{
"epoch": 4.0,
"learning_rate": 8.349746890119826e-05,
"loss": 0.6284,
"step": 303000
},
{
"epoch": 4.0,
"learning_rate": 8.337453124270863e-05,
"loss": 0.6416,
"step": 304000
},
{
"epoch": 4.01,
"learning_rate": 8.32512286056924e-05,
"loss": 0.5316,
"step": 305000
},
{
"epoch": 4.01,
"learning_rate": 8.31275623385675e-05,
"loss": 0.508,
"step": 306000
},
{
"epoch": 4.01,
"learning_rate": 8.300353379372834e-05,
"loss": 0.6176,
"step": 307000
},
{
"epoch": 4.01,
"learning_rate": 8.287914432753123e-05,
"loss": 0.6347,
"step": 308000
},
{
"epoch": 4.01,
"learning_rate": 8.275439530027948e-05,
"loss": 0.5405,
"step": 309000
},
{
"epoch": 4.01,
"learning_rate": 8.262928807620843e-05,
"loss": 0.5162,
"step": 310000
},
{
"epoch": 4.01,
"learning_rate": 8.250382402347065e-05,
"loss": 0.6232,
"step": 311000
},
{
"epoch": 4.01,
"learning_rate": 8.237800451412095e-05,
"loss": 0.632,
"step": 312000
},
{
"epoch": 4.01,
"learning_rate": 8.225183092410128e-05,
"loss": 0.5304,
"step": 313000
},
{
"epoch": 4.01,
"learning_rate": 8.212530463322583e-05,
"loss": 0.5176,
"step": 314000
},
{
"epoch": 4.02,
"learning_rate": 8.199842702516583e-05,
"loss": 0.6215,
"step": 315000
},
{
"epoch": 4.02,
"learning_rate": 8.18711994874345e-05,
"loss": 0.6231,
"step": 316000
},
{
"epoch": 4.02,
"learning_rate": 8.174362341137177e-05,
"loss": 0.5305,
"step": 317000
},
{
"epoch": 4.02,
"learning_rate": 8.161570019212921e-05,
"loss": 0.5038,
"step": 318000
},
{
"epoch": 4.02,
"learning_rate": 8.148743122865463e-05,
"loss": 0.6186,
"step": 319000
},
{
"epoch": 4.02,
"learning_rate": 8.135881792367686e-05,
"loss": 0.6294,
"step": 320000
},
{
"epoch": 4.02,
"learning_rate": 8.12298616836904e-05,
"loss": 0.5251,
"step": 321000
},
{
"epoch": 4.02,
"learning_rate": 8.110056391894005e-05,
"loss": 0.508,
"step": 322000
},
{
"epoch": 4.02,
"learning_rate": 8.097092604340542e-05,
"loss": 0.617,
"step": 323000
},
{
"epoch": 4.02,
"learning_rate": 8.084094947478556e-05,
"loss": 0.6255,
"step": 324000
},
{
"epoch": 4.03,
"learning_rate": 8.07106356344834e-05,
"loss": 0.5239,
"step": 325000
},
{
"epoch": 4.03,
"learning_rate": 8.057998594759022e-05,
"loss": 0.5088,
"step": 326000
},
{
"epoch": 4.03,
"learning_rate": 8.044900184287007e-05,
"loss": 0.6405,
"step": 327000
},
{
"epoch": 4.03,
"learning_rate": 8.031768475274413e-05,
"loss": 0.6711,
"step": 328000
},
{
"epoch": 4.03,
"learning_rate": 8.018603611327504e-05,
"loss": 0.5553,
"step": 329000
},
{
"epoch": 4.03,
"learning_rate": 8.005405736415126e-05,
"loss": 0.5375,
"step": 330000
},
{
"epoch": 4.03,
"learning_rate": 7.992174994867123e-05,
"loss": 0.6427,
"step": 331000
},
{
"epoch": 4.03,
"learning_rate": 7.978911531372765e-05,
"loss": 0.6478,
"step": 332000
},
{
"epoch": 4.03,
"learning_rate": 7.965615490979163e-05,
"loss": 0.5483,
"step": 333000
},
{
"epoch": 4.03,
"learning_rate": 7.952287019089685e-05,
"loss": 0.5285,
"step": 334000
},
{
"epoch": 4.04,
"learning_rate": 7.938926261462366e-05,
"loss": 0.6242,
"step": 335000
},
{
"epoch": 4.04,
"learning_rate": 7.925533364208309e-05,
"loss": 0.6353,
"step": 336000
},
{
"epoch": 4.04,
"learning_rate": 7.912108473790092e-05,
"loss": 0.5325,
"step": 337000
},
{
"epoch": 4.04,
"learning_rate": 7.898651737020166e-05,
"loss": 0.5217,
"step": 338000
},
{
"epoch": 4.04,
"learning_rate": 7.88516330105925e-05,
"loss": 0.6253,
"step": 339000
},
{
"epoch": 4.04,
"learning_rate": 7.871643313414718e-05,
"loss": 0.6219,
"step": 340000
},
{
"epoch": 4.04,
"learning_rate": 7.858091921938988e-05,
"loss": 0.5077,
"step": 341000
},
{
"epoch": 4.04,
"learning_rate": 7.844509274827907e-05,
"loss": 0.5587,
"step": 342000
},
{
"epoch": 4.04,
"learning_rate": 7.830895520619128e-05,
"loss": 0.6375,
"step": 343000
},
{
"epoch": 4.04,
"learning_rate": 7.817250808190483e-05,
"loss": 0.6241,
"step": 344000
},
{
"epoch": 4.05,
"learning_rate": 7.803575286758364e-05,
"loss": 0.516,
"step": 345000
},
{
"epoch": 4.05,
"learning_rate": 7.789869105876083e-05,
"loss": 0.5062,
"step": 346000
},
{
"epoch": 4.05,
"learning_rate": 7.776132415432234e-05,
"loss": 0.6103,
"step": 347000
},
{
"epoch": 4.05,
"learning_rate": 7.762365365649067e-05,
"loss": 0.624,
"step": 348000
},
{
"epoch": 4.05,
"learning_rate": 7.748568107080832e-05,
"loss": 0.4879,
"step": 349000
},
{
"epoch": 4.05,
"learning_rate": 7.734740790612136e-05,
"loss": 0.4626,
"step": 350000
},
{
"epoch": 4.05,
"eval_loss": 0.5095008611679077,
"eval_runtime": 11.72,
"eval_samples_per_second": 426.623,
"eval_steps_per_second": 3.413,
"step": 350000
},
{
"epoch": 4.05,
"learning_rate": 7.720883567456298e-05,
"loss": 0.5629,
"step": 351000
},
{
"epoch": 4.05,
"learning_rate": 7.70699658915369e-05,
"loss": 0.5622,
"step": 352000
},
{
"epoch": 4.05,
"learning_rate": 7.693080007570084e-05,
"loss": 0.4433,
"step": 353000
},
{
"epoch": 4.05,
"learning_rate": 7.679133974894983e-05,
"loss": 0.4263,
"step": 354000
},
{
"epoch": 4.06,
"learning_rate": 7.66515864363997e-05,
"loss": 0.5752,
"step": 355000
},
{
"epoch": 4.06,
"learning_rate": 7.651154166637025e-05,
"loss": 0.5937,
"step": 356000
},
{
"epoch": 4.06,
"learning_rate": 7.637120697036866e-05,
"loss": 0.466,
"step": 357000
},
{
"epoch": 4.06,
"learning_rate": 7.623058388307269e-05,
"loss": 0.4671,
"step": 358000
},
{
"epoch": 4.06,
"learning_rate": 7.608967394231387e-05,
"loss": 0.5396,
"step": 359000
},
{
"epoch": 4.06,
"learning_rate": 7.594847868906076e-05,
"loss": 0.5744,
"step": 360000
},
{
"epoch": 4.06,
"learning_rate": 7.580699966740201e-05,
"loss": 0.4573,
"step": 361000
},
{
"epoch": 4.06,
"learning_rate": 7.566523842452958e-05,
"loss": 0.53,
"step": 362000
},
{
"epoch": 4.06,
"learning_rate": 7.552319651072164e-05,
"loss": 0.6274,
"step": 363000
},
{
"epoch": 4.06,
"learning_rate": 7.538087547932585e-05,
"loss": 0.6165,
"step": 364000
},
{
"epoch": 4.07,
"learning_rate": 7.52382768867422e-05,
"loss": 0.5159,
"step": 365000
},
{
"epoch": 4.07,
"learning_rate": 7.509540229240601e-05,
"loss": 0.5151,
"step": 366000
},
{
"epoch": 4.07,
"learning_rate": 7.495225325877103e-05,
"loss": 0.6124,
"step": 367000
},
{
"epoch": 4.07,
"learning_rate": 7.480883135129211e-05,
"loss": 0.6173,
"step": 368000
},
{
"epoch": 4.07,
"learning_rate": 7.466513813840825e-05,
"loss": 0.5121,
"step": 369000
},
{
"epoch": 4.07,
"learning_rate": 7.452117519152542e-05,
"loss": 0.5105,
"step": 370000
},
{
"epoch": 4.07,
"learning_rate": 7.437694408499933e-05,
"loss": 0.6066,
"step": 371000
},
{
"epoch": 4.07,
"learning_rate": 7.423244639611826e-05,
"loss": 0.6069,
"step": 372000
},
{
"epoch": 4.07,
"learning_rate": 7.408768370508576e-05,
"loss": 0.4973,
"step": 373000
},
{
"epoch": 4.07,
"learning_rate": 7.394265759500348e-05,
"loss": 0.5046,
"step": 374000
},
{
"epoch": 5.0,
"learning_rate": 7.379736965185368e-05,
"loss": 0.6213,
"step": 375000
},
{
"epoch": 5.0,
"learning_rate": 7.365182146448205e-05,
"loss": 0.5205,
"step": 376000
},
{
"epoch": 5.0,
"learning_rate": 7.350601462458024e-05,
"loss": 0.5161,
"step": 377000
},
{
"epoch": 5.0,
"learning_rate": 7.335995072666848e-05,
"loss": 0.6207,
"step": 378000
},
{
"epoch": 5.0,
"learning_rate": 7.32136313680782e-05,
"loss": 0.6142,
"step": 379000
},
{
"epoch": 5.01,
"learning_rate": 7.30670581489344e-05,
"loss": 0.5039,
"step": 380000
},
{
"epoch": 5.01,
"learning_rate": 7.292023267213835e-05,
"loss": 0.508,
"step": 381000
},
{
"epoch": 5.01,
"learning_rate": 7.277315654334997e-05,
"loss": 0.6106,
"step": 382000
},
{
"epoch": 5.01,
"learning_rate": 7.262583137097018e-05,
"loss": 0.61,
"step": 383000
},
{
"epoch": 5.01,
"learning_rate": 7.247825876612353e-05,
"loss": 0.513,
"step": 384000
},
{
"epoch": 5.01,
"learning_rate": 7.233044034264034e-05,
"loss": 0.5135,
"step": 385000
},
{
"epoch": 5.01,
"learning_rate": 7.218237771703921e-05,
"loss": 0.6155,
"step": 386000
},
{
"epoch": 5.01,
"learning_rate": 7.203407250850928e-05,
"loss": 0.6053,
"step": 387000
},
{
"epoch": 5.01,
"learning_rate": 7.188552633889259e-05,
"loss": 0.5045,
"step": 388000
},
{
"epoch": 5.01,
"learning_rate": 7.173674083266624e-05,
"loss": 0.518,
"step": 389000
},
{
"epoch": 5.02,
"learning_rate": 7.158771761692464e-05,
"loss": 0.6129,
"step": 390000
},
{
"epoch": 5.02,
"learning_rate": 7.143845832136188e-05,
"loss": 0.598,
"step": 391000
},
{
"epoch": 5.02,
"learning_rate": 7.128896457825364e-05,
"loss": 0.5032,
"step": 392000
},
{
"epoch": 5.02,
"learning_rate": 7.113923802243957e-05,
"loss": 0.5039,
"step": 393000
},
{
"epoch": 5.02,
"learning_rate": 7.09892802913053e-05,
"loss": 0.6147,
"step": 394000
},
{
"epoch": 5.02,
"learning_rate": 7.083909302476453e-05,
"loss": 0.6031,
"step": 395000
},
{
"epoch": 5.02,
"learning_rate": 7.068867786524116e-05,
"loss": 0.4966,
"step": 396000
},
{
"epoch": 5.02,
"learning_rate": 7.053803645765128e-05,
"loss": 0.5087,
"step": 397000
},
{
"epoch": 5.02,
"learning_rate": 7.038717044938519e-05,
"loss": 0.6122,
"step": 398000
},
{
"epoch": 5.02,
"learning_rate": 7.023608149028937e-05,
"loss": 0.5982,
"step": 399000
},
{
"epoch": 5.03,
"learning_rate": 7.008477123264848e-05,
"loss": 0.4977,
"step": 400000
},
{
"epoch": 5.03,
"eval_loss": 0.49361830949783325,
"eval_runtime": 12.3111,
"eval_samples_per_second": 406.137,
"eval_steps_per_second": 3.249,
"step": 400000
},
{
"epoch": 5.03,
"learning_rate": 6.993324133116726e-05,
"loss": 0.509,
"step": 401000
},
{
"epoch": 5.03,
"learning_rate": 6.978149344295242e-05,
"loss": 0.647,
"step": 402000
},
{
"epoch": 5.03,
"learning_rate": 6.962952922749457e-05,
"loss": 0.64,
"step": 403000
},
{
"epoch": 5.03,
"learning_rate": 6.947735034665002e-05,
"loss": 0.5288,
"step": 404000
},
{
"epoch": 5.03,
"learning_rate": 6.932495846462261e-05,
"loss": 0.5367,
"step": 405000
},
{
"epoch": 5.03,
"learning_rate": 6.917235524794558e-05,
"loss": 0.6372,
"step": 406000
},
{
"epoch": 5.03,
"learning_rate": 6.901954236546323e-05,
"loss": 0.6233,
"step": 407000
},
{
"epoch": 5.03,
"learning_rate": 6.886652148831279e-05,
"loss": 0.5195,
"step": 408000
},
{
"epoch": 5.03,
"learning_rate": 6.871329428990602e-05,
"loss": 0.5228,
"step": 409000
},
{
"epoch": 5.04,
"learning_rate": 6.855986244591104e-05,
"loss": 0.6206,
"step": 410000
},
{
"epoch": 5.04,
"learning_rate": 6.840622763423391e-05,
"loss": 0.6115,
"step": 411000
},
{
"epoch": 5.04,
"learning_rate": 6.825239153500029e-05,
"loss": 0.5049,
"step": 412000
},
{
"epoch": 5.04,
"learning_rate": 6.809835583053715e-05,
"loss": 0.5195,
"step": 413000
},
{
"epoch": 5.04,
"learning_rate": 6.794412220535426e-05,
"loss": 0.622,
"step": 414000
},
{
"epoch": 5.04,
"learning_rate": 6.778969234612584e-05,
"loss": 0.5932,
"step": 415000
},
{
"epoch": 5.04,
"learning_rate": 6.763506794167208e-05,
"loss": 0.4823,
"step": 416000
},
{
"epoch": 5.04,
"learning_rate": 6.748025068294067e-05,
"loss": 0.5757,
"step": 417000
},
{
"epoch": 5.04,
"learning_rate": 6.732524226298841e-05,
"loss": 0.6171,
"step": 418000
},
{
"epoch": 5.04,
"learning_rate": 6.71700443769625e-05,
"loss": 0.5972,
"step": 419000
},
{
"epoch": 5.05,
"learning_rate": 6.701465872208216e-05,
"loss": 0.4902,
"step": 420000
},
{
"epoch": 5.05,
"learning_rate": 6.685908699762002e-05,
"loss": 0.5021,
"step": 421000
},
{
"epoch": 5.05,
"learning_rate": 6.670333090488356e-05,
"loss": 0.6071,
"step": 422000
},
{
"epoch": 5.05,
"learning_rate": 6.654739214719641e-05,
"loss": 0.5952,
"step": 423000
},
{
"epoch": 5.05,
"learning_rate": 6.639127242987988e-05,
"loss": 0.4594,
"step": 424000
},
{
"epoch": 5.05,
"learning_rate": 6.623497346023418e-05,
"loss": 0.4587,
"step": 425000
},
{
"epoch": 5.05,
"learning_rate": 6.607849694751977e-05,
"loss": 0.5645,
"step": 426000
},
{
"epoch": 5.05,
"learning_rate": 6.592184460293877e-05,
"loss": 0.5312,
"step": 427000
},
{
"epoch": 5.05,
"learning_rate": 6.576501813961609e-05,
"loss": 0.4195,
"step": 428000
},
{
"epoch": 5.05,
"learning_rate": 6.56080192725808e-05,
"loss": 0.4244,
"step": 429000
},
{
"epoch": 5.06,
"learning_rate": 6.545084971874738e-05,
"loss": 0.5821,
"step": 430000
},
{
"epoch": 5.06,
"learning_rate": 6.529351119689688e-05,
"loss": 0.5656,
"step": 431000
},
{
"epoch": 5.06,
"learning_rate": 6.513600542765817e-05,
"loss": 0.4418,
"step": 432000
},
{
"epoch": 5.06,
"learning_rate": 6.497833413348909e-05,
"loss": 0.4634,
"step": 433000
},
{
"epoch": 5.06,
"learning_rate": 6.48204990386577e-05,
"loss": 0.5379,
"step": 434000
},
{
"epoch": 5.06,
"learning_rate": 6.466250186922325e-05,
"loss": 0.5509,
"step": 435000
},
{
"epoch": 5.06,
"learning_rate": 6.450434435301751e-05,
"loss": 0.4497,
"step": 436000
},
{
"epoch": 5.06,
"learning_rate": 6.43460282196257e-05,
"loss": 0.5231,
"step": 437000
},
{
"epoch": 5.06,
"learning_rate": 6.418755520036775e-05,
"loss": 0.6235,
"step": 438000
},
{
"epoch": 5.06,
"learning_rate": 6.402892702827916e-05,
"loss": 0.59,
"step": 439000
},
{
"epoch": 5.07,
"learning_rate": 6.387014543809223e-05,
"loss": 0.4913,
"step": 440000
},
{
"epoch": 5.07,
"learning_rate": 6.371121216621698e-05,
"loss": 0.5104,
"step": 441000
},
{
"epoch": 5.07,
"learning_rate": 6.355212895072223e-05,
"loss": 0.61,
"step": 442000
},
{
"epoch": 5.07,
"learning_rate": 6.339289753131649e-05,
"loss": 0.5922,
"step": 443000
},
{
"epoch": 5.07,
"learning_rate": 6.323351964932908e-05,
"loss": 0.4872,
"step": 444000
},
{
"epoch": 5.07,
"learning_rate": 6.307399704769099e-05,
"loss": 0.5072,
"step": 445000
},
{
"epoch": 5.07,
"learning_rate": 6.291433147091583e-05,
"loss": 0.6045,
"step": 446000
},
{
"epoch": 5.07,
"learning_rate": 6.275452466508077e-05,
"loss": 0.5784,
"step": 447000
},
{
"epoch": 5.07,
"learning_rate": 6.259457837780742e-05,
"loss": 0.4733,
"step": 448000
},
{
"epoch": 6.0,
"learning_rate": 6.243449435824276e-05,
"loss": 0.5169,
"step": 449000
},
{
"epoch": 6.0,
"learning_rate": 6.227427435703997e-05,
"loss": 0.5971,
"step": 450000
},
{
"epoch": 6.0,
"eval_loss": 0.45991742610931396,
"eval_runtime": 11.9825,
"eval_samples_per_second": 417.277,
"eval_steps_per_second": 3.338,
"step": 450000
},
{
"epoch": 6.0,
"learning_rate": 6.211392012633932e-05,
"loss": 0.4963,
"step": 451000
},
{
"epoch": 6.0,
"learning_rate": 6.195343341974899e-05,
"loss": 0.5152,
"step": 452000
},
{
"epoch": 6.0,
"learning_rate": 6.179281599232591e-05,
"loss": 0.6168,
"step": 453000
},
{
"epoch": 6.01,
"learning_rate": 6.163206960055651e-05,
"loss": 0.5881,
"step": 454000
},
{
"epoch": 6.01,
"learning_rate": 6.147119600233758e-05,
"loss": 0.4794,
"step": 455000
},
{
"epoch": 6.01,
"learning_rate": 6.131019695695702e-05,
"loss": 0.5081,
"step": 456000
},
{
"epoch": 6.01,
"learning_rate": 6.11490742250746e-05,
"loss": 0.6061,
"step": 457000
},
{
"epoch": 6.01,
"learning_rate": 6.0987829568702656e-05,
"loss": 0.5868,
"step": 458000
},
{
"epoch": 6.01,
"learning_rate": 6.0826464751186994e-05,
"loss": 0.49,
"step": 459000
},
{
"epoch": 6.01,
"learning_rate": 6.066498153718735e-05,
"loss": 0.511,
"step": 460000
},
{
"epoch": 6.01,
"learning_rate": 6.05033816926583e-05,
"loss": 0.6118,
"step": 461000
},
{
"epoch": 6.01,
"learning_rate": 6.034166698482984e-05,
"loss": 0.5817,
"step": 462000
},
{
"epoch": 6.01,
"learning_rate": 6.017983918218812e-05,
"loss": 0.4835,
"step": 463000
},
{
"epoch": 6.02,
"learning_rate": 6.001790005445607e-05,
"loss": 0.5136,
"step": 464000
},
{
"epoch": 6.02,
"learning_rate": 5.985585137257401e-05,
"loss": 0.6084,
"step": 465000
},
{
"epoch": 6.02,
"learning_rate": 5.969369490868042e-05,
"loss": 0.5788,
"step": 466000
},
{
"epoch": 6.02,
"learning_rate": 5.953143243609235e-05,
"loss": 0.4759,
"step": 467000
},
{
"epoch": 6.02,
"learning_rate": 5.9369065729286245e-05,
"loss": 0.5042,
"step": 468000
},
{
"epoch": 6.02,
"learning_rate": 5.9206596563878357e-05,
"loss": 0.6075,
"step": 469000
},
{
"epoch": 6.02,
"learning_rate": 5.90440267166055e-05,
"loss": 0.5814,
"step": 470000
},
{
"epoch": 6.02,
"learning_rate": 5.888135796530544e-05,
"loss": 0.4721,
"step": 471000
},
{
"epoch": 6.02,
"learning_rate": 5.871859208889759e-05,
"loss": 0.5112,
"step": 472000
},
{
"epoch": 6.02,
"learning_rate": 5.85557308673635e-05,
"loss": 0.6056,
"step": 473000
},
{
"epoch": 6.03,
"learning_rate": 5.8392776081727385e-05,
"loss": 0.5757,
"step": 474000
},
{
"epoch": 6.03,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.4794,
"step": 475000
},
{
"epoch": 6.03,
"learning_rate": 5.8066592947342555e-05,
"loss": 0.5169,
"step": 476000
},
{
"epoch": 6.03,
"learning_rate": 5.7903368165680327e-05,
"loss": 0.6422,
"step": 477000
},
{
"epoch": 6.03,
"learning_rate": 5.7740056954050084e-05,
"loss": 0.6091,
"step": 478000
},
{
"epoch": 6.03,
"learning_rate": 5.757666109839702e-05,
"loss": 0.5077,
"step": 479000
},
{
"epoch": 6.03,
"learning_rate": 5.74131823855921e-05,
"loss": 0.534,
"step": 480000
},
{
"epoch": 6.03,
"learning_rate": 5.72496226034123e-05,
"loss": 0.6326,
"step": 481000
},
{
"epoch": 6.03,
"learning_rate": 5.7085983540521216e-05,
"loss": 0.5986,
"step": 482000
},
{
"epoch": 6.03,
"learning_rate": 5.692226698644938e-05,
"loss": 0.5032,
"step": 483000
},
{
"epoch": 6.04,
"learning_rate": 5.675847473157485e-05,
"loss": 0.5255,
"step": 484000
},
{
"epoch": 6.04,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.6161,
"step": 485000
},
{
"epoch": 6.04,
"learning_rate": 5.6430670285049314e-05,
"loss": 0.5833,
"step": 486000
},
{
"epoch": 6.04,
"learning_rate": 5.6266661678215216e-05,
"loss": 0.4921,
"step": 487000
},
{
"epoch": 6.04,
"learning_rate": 5.6102584540173006e-05,
"loss": 0.5223,
"step": 488000
},
{
"epoch": 6.04,
"learning_rate": 5.5938440665244006e-05,
"loss": 0.6119,
"step": 489000
},
{
"epoch": 6.04,
"learning_rate": 5.577423184847932e-05,
"loss": 0.5603,
"step": 490000
},
{
"epoch": 6.04,
"learning_rate": 5.560995988564023e-05,
"loss": 0.4969,
"step": 491000
},
{
"epoch": 6.04,
"learning_rate": 5.544562657317863e-05,
"loss": 0.5575,
"step": 492000
},
{
"epoch": 6.04,
"learning_rate": 5.52812337082173e-05,
"loss": 0.6068,
"step": 493000
},
{
"epoch": 6.05,
"learning_rate": 5.511678308853026e-05,
"loss": 0.5653,
"step": 494000
},
{
"epoch": 6.05,
"learning_rate": 5.495227651252315e-05,
"loss": 0.4794,
"step": 495000
},
{
"epoch": 6.05,
"learning_rate": 5.478771577921351e-05,
"loss": 0.5142,
"step": 496000
},
{
"epoch": 6.05,
"learning_rate": 5.462310268821118e-05,
"loss": 0.6071,
"step": 497000
},
{
"epoch": 6.05,
"learning_rate": 5.445843903969854e-05,
"loss": 0.553,
"step": 498000
},
{
"epoch": 6.05,
"learning_rate": 5.4293726634410855e-05,
"loss": 0.4492,
"step": 499000
},
{
"epoch": 6.05,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.4743,
"step": 500000
},
{
"epoch": 6.05,
"eval_loss": 0.4693508446216583,
"eval_runtime": 11.8669,
"eval_samples_per_second": 421.339,
"eval_steps_per_second": 3.371,
"step": 500000
},
{
"epoch": 6.05,
"learning_rate": 5.396416275909779e-05,
"loss": 0.5595,
"step": 501000
},
{
"epoch": 6.05,
"learning_rate": 5.379931489313016e-05,
"loss": 0.5009,
"step": 502000
},
{
"epoch": 6.05,
"learning_rate": 5.363442547846356e-05,
"loss": 0.4143,
"step": 503000
},
{
"epoch": 6.06,
"learning_rate": 5.3469496318302204e-05,
"loss": 0.4563,
"step": 504000
},
{
"epoch": 6.06,
"learning_rate": 5.330452921628497e-05,
"loss": 0.5805,
"step": 505000
},
{
"epoch": 6.06,
"learning_rate": 5.313952597646568e-05,
"loss": 0.5175,
"step": 506000
},
{
"epoch": 7.0,
"learning_rate": 5.297448840329329e-05,
"loss": 0.4716,
"step": 507000
},
{
"epoch": 7.0,
"learning_rate": 5.280941830159227e-05,
"loss": 0.4961,
"step": 508000
},
{
"epoch": 7.0,
"learning_rate": 5.264431747654284e-05,
"loss": 0.5315,
"step": 509000
},
{
"epoch": 7.0,
"learning_rate": 5.247918773366112e-05,
"loss": 0.5466,
"step": 510000
},
{
"epoch": 7.0,
"learning_rate": 5.231403087877955e-05,
"loss": 0.516,
"step": 511000
},
{
"epoch": 7.01,
"learning_rate": 5.214884871802703e-05,
"loss": 0.5189,
"step": 512000
},
{
"epoch": 7.01,
"learning_rate": 5.198364305780922e-05,
"loss": 0.5637,
"step": 513000
},
{
"epoch": 7.01,
"learning_rate": 5.1818415704788725e-05,
"loss": 0.5635,
"step": 514000
},
{
"epoch": 7.01,
"learning_rate": 5.165316846586541e-05,
"loss": 0.5275,
"step": 515000
},
{
"epoch": 7.01,
"learning_rate": 5.148790314815663e-05,
"loss": 0.5149,
"step": 516000
},
{
"epoch": 7.01,
"learning_rate": 5.132262155897739e-05,
"loss": 0.5604,
"step": 517000
},
{
"epoch": 7.01,
"learning_rate": 5.1157325505820694e-05,
"loss": 0.5658,
"step": 518000
},
{
"epoch": 7.01,
"learning_rate": 5.0992016796337686e-05,
"loss": 0.5269,
"step": 519000
},
{
"epoch": 7.01,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.5099,
"step": 520000
},
{
"epoch": 7.01,
"learning_rate": 5.066136863966963e-05,
"loss": 0.5581,
"step": 521000
},
{
"epoch": 7.02,
"learning_rate": 5.0496032808399815e-05,
"loss": 0.5566,
"step": 522000
},
{
"epoch": 7.02,
"learning_rate": 5.033069155259471e-05,
"loss": 0.5168,
"step": 523000
},
{
"epoch": 7.02,
"learning_rate": 5.016534668039976e-05,
"loss": 0.522,
"step": 524000
},
{
"epoch": 7.02,
"learning_rate": 5e-05,
"loss": 0.5234,
"step": 525000
},
{
"epoch": 7.02,
"learning_rate": 4.9834653319600246e-05,
"loss": 0.5236,
"step": 526000
},
{
"epoch": 7.02,
"learning_rate": 4.96693084474053e-05,
"loss": 0.5466,
"step": 527000
},
{
"epoch": 7.02,
"learning_rate": 4.950396719160018e-05,
"loss": 0.5673,
"step": 528000
},
{
"epoch": 7.02,
"learning_rate": 4.93386313603304e-05,
"loss": 0.5191,
"step": 529000
},
{
"epoch": 7.02,
"learning_rate": 4.917330276168208e-05,
"loss": 0.5171,
"step": 530000
},
{
"epoch": 7.02,
"learning_rate": 4.9007983203662326e-05,
"loss": 0.5403,
"step": 531000
},
{
"epoch": 7.03,
"learning_rate": 4.884267449417931e-05,
"loss": 0.5609,
"step": 532000
},
{
"epoch": 7.03,
"learning_rate": 4.867737844102261e-05,
"loss": 0.5172,
"step": 533000
},
{
"epoch": 7.03,
"learning_rate": 4.851209685184338e-05,
"loss": 0.5322,
"step": 534000
},
{
"epoch": 7.03,
"learning_rate": 4.834683153413459e-05,
"loss": 0.5628,
"step": 535000
},
{
"epoch": 7.03,
"learning_rate": 4.818158429521129e-05,
"loss": 0.5773,
"step": 536000
},
{
"epoch": 7.03,
"learning_rate": 4.801635694219079e-05,
"loss": 0.5247,
"step": 537000
},
{
"epoch": 7.03,
"learning_rate": 4.785115128197298e-05,
"loss": 0.5347,
"step": 538000
},
{
"epoch": 7.03,
"learning_rate": 4.7685969121220456e-05,
"loss": 0.5563,
"step": 539000
},
{
"epoch": 7.03,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.569,
"step": 540000
},
{
"epoch": 7.03,
"learning_rate": 4.735568252345718e-05,
"loss": 0.5157,
"step": 541000
},
{
"epoch": 7.04,
"learning_rate": 4.7190581698407725e-05,
"loss": 0.5217,
"step": 542000
},
{
"epoch": 7.04,
"learning_rate": 4.702551159670672e-05,
"loss": 0.5464,
"step": 543000
},
{
"epoch": 7.04,
"learning_rate": 4.6860474023534335e-05,
"loss": 0.5659,
"step": 544000
},
{
"epoch": 7.04,
"learning_rate": 4.669547078371504e-05,
"loss": 0.5142,
"step": 545000
},
{
"epoch": 7.04,
"learning_rate": 4.65305036816978e-05,
"loss": 0.5221,
"step": 546000
},
{
"epoch": 7.04,
"learning_rate": 4.6365574521536445e-05,
"loss": 0.5483,
"step": 547000
},
{
"epoch": 7.04,
"learning_rate": 4.620068510686985e-05,
"loss": 0.5539,
"step": 548000
},
{
"epoch": 7.04,
"learning_rate": 4.60358372409022e-05,
"loss": 0.5226,
"step": 549000
},
{
"epoch": 7.04,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.5326,
"step": 550000
},
{
"epoch": 7.04,
"eval_loss": 0.4512648582458496,
"eval_runtime": 14.4816,
"eval_samples_per_second": 345.267,
"eval_steps_per_second": 2.762,
"step": 550000
},
{
"epoch": 7.04,
"learning_rate": 4.570627336558915e-05,
"loss": 0.5419,
"step": 551000
},
{
"epoch": 7.05,
"learning_rate": 4.554156096030149e-05,
"loss": 0.5872,
"step": 552000
},
{
"epoch": 7.05,
"learning_rate": 4.537689731178883e-05,
"loss": 0.532,
"step": 553000
},
{
"epoch": 7.05,
"learning_rate": 4.5212284220786494e-05,
"loss": 0.5376,
"step": 554000
},
{
"epoch": 7.05,
"learning_rate": 4.504772348747687e-05,
"loss": 0.5613,
"step": 555000
},
{
"epoch": 7.05,
"learning_rate": 4.488321691146975e-05,
"loss": 0.5699,
"step": 556000
},
{
"epoch": 7.05,
"learning_rate": 4.471876629178273e-05,
"loss": 0.5161,
"step": 557000
},
{
"epoch": 7.05,
"learning_rate": 4.4554373426821374e-05,
"loss": 0.5181,
"step": 558000
},
{
"epoch": 7.05,
"learning_rate": 4.439004011435979e-05,
"loss": 0.5374,
"step": 559000
},
{
"epoch": 7.05,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.5453,
"step": 560000
},
{
"epoch": 7.05,
"learning_rate": 4.406155933475599e-05,
"loss": 0.4937,
"step": 561000
},
{
"epoch": 7.06,
"learning_rate": 4.3897415459827e-05,
"loss": 0.5163,
"step": 562000
},
{
"epoch": 7.06,
"learning_rate": 4.373333832178478e-05,
"loss": 0.5527,
"step": 563000
},
{
"epoch": 7.06,
"learning_rate": 4.3569329714950704e-05,
"loss": 0.5543,
"step": 564000
},
{
"epoch": 7.06,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.4983,
"step": 565000
},
{
"epoch": 7.06,
"learning_rate": 4.324152526842517e-05,
"loss": 0.4972,
"step": 566000
},
{
"epoch": 7.06,
"learning_rate": 4.307773301355062e-05,
"loss": 0.5799,
"step": 567000
},
{
"epoch": 7.06,
"learning_rate": 4.291401645947879e-05,
"loss": 0.5437,
"step": 568000
},
{
"epoch": 7.06,
"learning_rate": 4.275037739658771e-05,
"loss": 0.513,
"step": 569000
},
{
"epoch": 7.06,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.5167,
"step": 570000
},
{
"epoch": 7.06,
"learning_rate": 4.2423338901602985e-05,
"loss": 0.5406,
"step": 571000
},
{
"epoch": 7.07,
"learning_rate": 4.2259943045949934e-05,
"loss": 0.5517,
"step": 572000
},
{
"epoch": 7.07,
"learning_rate": 4.209663183431969e-05,
"loss": 0.4954,
"step": 573000
},
{
"epoch": 7.07,
"learning_rate": 4.1933407052657456e-05,
"loss": 0.4904,
"step": 574000
},
{
"epoch": 7.07,
"learning_rate": 4.17702704859633e-05,
"loss": 0.5145,
"step": 575000
},
{
"epoch": 7.07,
"learning_rate": 4.160722391827262e-05,
"loss": 0.5208,
"step": 576000
},
{
"epoch": 7.07,
"learning_rate": 4.14442691326365e-05,
"loss": 0.4688,
"step": 577000
},
{
"epoch": 7.07,
"learning_rate": 4.1281407911102425e-05,
"loss": 0.467,
"step": 578000
},
{
"epoch": 7.07,
"learning_rate": 4.111864203469457e-05,
"loss": 0.4978,
"step": 579000
},
{
"epoch": 7.07,
"learning_rate": 4.095597328339452e-05,
"loss": 0.544,
"step": 580000
},
{
"epoch": 7.07,
"learning_rate": 4.079340343612165e-05,
"loss": 0.4869,
"step": 581000
},
{
"epoch": 8.0,
"learning_rate": 4.063093427071376e-05,
"loss": 0.4903,
"step": 582000
},
{
"epoch": 8.0,
"learning_rate": 4.046856756390767e-05,
"loss": 0.481,
"step": 583000
},
{
"epoch": 8.0,
"learning_rate": 4.0306305091319595e-05,
"loss": 0.5208,
"step": 584000
},
{
"epoch": 8.0,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.5219,
"step": 585000
},
{
"epoch": 8.0,
"learning_rate": 3.9982099945543945e-05,
"loss": 0.5065,
"step": 586000
},
{
"epoch": 8.01,
"learning_rate": 3.982016081781189e-05,
"loss": 0.5138,
"step": 587000
},
{
"epoch": 8.01,
"learning_rate": 3.965833301517017e-05,
"loss": 0.5546,
"step": 588000
},
{
"epoch": 8.01,
"learning_rate": 3.949661830734172e-05,
"loss": 0.5393,
"step": 589000
},
{
"epoch": 8.01,
"learning_rate": 3.933501846281267e-05,
"loss": 0.5154,
"step": 590000
},
{
"epoch": 8.01,
"learning_rate": 3.917353524881302e-05,
"loss": 0.5122,
"step": 591000
},
{
"epoch": 8.01,
"learning_rate": 3.901217043129735e-05,
"loss": 0.5535,
"step": 592000
},
{
"epoch": 8.01,
"learning_rate": 3.8850925774925425e-05,
"loss": 0.5442,
"step": 593000
},
{
"epoch": 8.01,
"learning_rate": 3.8689803043043e-05,
"loss": 0.5152,
"step": 594000
},
{
"epoch": 8.01,
"learning_rate": 3.852880399766243e-05,
"loss": 0.5085,
"step": 595000
},
{
"epoch": 8.01,
"learning_rate": 3.836793039944349e-05,
"loss": 0.5498,
"step": 596000
},
{
"epoch": 8.02,
"learning_rate": 3.820718400767409e-05,
"loss": 0.5361,
"step": 597000
},
{
"epoch": 8.02,
"learning_rate": 3.8046566580251e-05,
"loss": 0.5069,
"step": 598000
},
{
"epoch": 8.02,
"learning_rate": 3.788607987366069e-05,
"loss": 0.5196,
"step": 599000
},
{
"epoch": 8.02,
"learning_rate": 3.772572564296005e-05,
"loss": 0.5036,
"step": 600000
},
{
"epoch": 8.02,
"eval_loss": 0.4396083950996399,
"eval_runtime": 11.6262,
"eval_samples_per_second": 430.064,
"eval_steps_per_second": 3.441,
"step": 600000
},
{
"epoch": 8.02,
"learning_rate": 3.756550564175727e-05,
"loss": 0.519,
"step": 601000
},
{
"epoch": 8.02,
"learning_rate": 3.74054216221926e-05,
"loss": 0.5482,
"step": 602000
},
{
"epoch": 8.02,
"learning_rate": 3.7245475334919246e-05,
"loss": 0.5494,
"step": 603000
},
{
"epoch": 8.02,
"learning_rate": 3.7085668529084184e-05,
"loss": 0.4997,
"step": 604000
},
{
"epoch": 8.02,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.5099,
"step": 605000
},
{
"epoch": 8.02,
"learning_rate": 3.676648035067093e-05,
"loss": 0.5419,
"step": 606000
},
{
"epoch": 8.03,
"learning_rate": 3.6607102468683526e-05,
"loss": 0.5449,
"step": 607000
},
{
"epoch": 8.03,
"learning_rate": 3.6447871049277796e-05,
"loss": 0.5013,
"step": 608000
},
{
"epoch": 8.03,
"learning_rate": 3.628878783378302e-05,
"loss": 0.5281,
"step": 609000
},
{
"epoch": 8.03,
"learning_rate": 3.612985456190778e-05,
"loss": 0.5642,
"step": 610000
},
{
"epoch": 8.03,
"learning_rate": 3.597107297172084e-05,
"loss": 0.5595,
"step": 611000
},
{
"epoch": 8.03,
"learning_rate": 3.581244479963225e-05,
"loss": 0.5097,
"step": 612000
},
{
"epoch": 8.03,
"learning_rate": 3.5653971780374295e-05,
"loss": 0.5268,
"step": 613000
},
{
"epoch": 8.03,
"learning_rate": 3.5495655646982505e-05,
"loss": 0.5581,
"step": 614000
},
{
"epoch": 8.03,
"learning_rate": 3.533749813077677e-05,
"loss": 0.5494,
"step": 615000
},
{
"epoch": 8.03,
"learning_rate": 3.517950096134232e-05,
"loss": 0.5017,
"step": 616000
},
{
"epoch": 8.04,
"learning_rate": 3.5021665866510925e-05,
"loss": 0.5123,
"step": 617000
},
{
"epoch": 8.04,
"learning_rate": 3.4863994572341843e-05,
"loss": 0.5513,
"step": 618000
},
{
"epoch": 8.04,
"learning_rate": 3.470648880310313e-05,
"loss": 0.548,
"step": 619000
},
{
"epoch": 8.04,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.5005,
"step": 620000
},
{
"epoch": 8.04,
"learning_rate": 3.439198072741921e-05,
"loss": 0.5132,
"step": 621000
},
{
"epoch": 8.04,
"learning_rate": 3.423498186038393e-05,
"loss": 0.5489,
"step": 622000
},
{
"epoch": 8.04,
"learning_rate": 3.407815539706124e-05,
"loss": 0.5364,
"step": 623000
},
{
"epoch": 8.04,
"learning_rate": 3.392150305248024e-05,
"loss": 0.5226,
"step": 624000
},
{
"epoch": 8.04,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.513,
"step": 625000
},
{
"epoch": 8.04,
"learning_rate": 3.360872757012011e-05,
"loss": 0.5467,
"step": 626000
},
{
"epoch": 8.05,
"learning_rate": 3.3452607852803584e-05,
"loss": 0.5699,
"step": 627000
},
{
"epoch": 8.05,
"learning_rate": 3.329666909511645e-05,
"loss": 0.5162,
"step": 628000
},
{
"epoch": 8.05,
"learning_rate": 3.3140913002379995e-05,
"loss": 0.53,
"step": 629000
},
{
"epoch": 8.05,
"learning_rate": 3.298534127791785e-05,
"loss": 0.5628,
"step": 630000
},
{
"epoch": 8.05,
"learning_rate": 3.282995562303754e-05,
"loss": 0.5446,
"step": 631000
},
{
"epoch": 8.05,
"learning_rate": 3.267475773701161e-05,
"loss": 0.5014,
"step": 632000
},
{
"epoch": 8.05,
"learning_rate": 3.251974931705933e-05,
"loss": 0.5095,
"step": 633000
},
{
"epoch": 8.05,
"learning_rate": 3.236493205832795e-05,
"loss": 0.5348,
"step": 634000
},
{
"epoch": 8.05,
"learning_rate": 3.221030765387417e-05,
"loss": 0.5256,
"step": 635000
},
{
"epoch": 8.05,
"learning_rate": 3.205587779464576e-05,
"loss": 0.4785,
"step": 636000
},
{
"epoch": 8.06,
"learning_rate": 3.190164416946285e-05,
"loss": 0.5139,
"step": 637000
},
{
"epoch": 8.06,
"learning_rate": 3.1747608464999725e-05,
"loss": 0.5512,
"step": 638000
},
{
"epoch": 8.06,
"learning_rate": 3.1593772365766105e-05,
"loss": 0.5349,
"step": 639000
},
{
"epoch": 8.06,
"learning_rate": 3.144013755408895e-05,
"loss": 0.4793,
"step": 640000
},
{
"epoch": 8.06,
"learning_rate": 3.128670571009399e-05,
"loss": 0.4884,
"step": 641000
},
{
"epoch": 8.06,
"learning_rate": 3.113347851168721e-05,
"loss": 0.5823,
"step": 642000
},
{
"epoch": 8.06,
"learning_rate": 3.098045763453678e-05,
"loss": 0.5262,
"step": 643000
},
{
"epoch": 8.06,
"learning_rate": 3.082764475205442e-05,
"loss": 0.496,
"step": 644000
},
{
"epoch": 8.06,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.5083,
"step": 645000
},
{
"epoch": 8.06,
"learning_rate": 3.052264965335e-05,
"loss": 0.5435,
"step": 646000
},
{
"epoch": 8.07,
"learning_rate": 3.0370470772505433e-05,
"loss": 0.5317,
"step": 647000
},
{
"epoch": 8.07,
"learning_rate": 3.0218506557047598e-05,
"loss": 0.4747,
"step": 648000
},
{
"epoch": 8.07,
"learning_rate": 3.006675866883275e-05,
"loss": 0.4831,
"step": 649000
},
{
"epoch": 8.07,
"learning_rate": 2.991522876735154e-05,
"loss": 0.5174,
"step": 650000
},
{
"epoch": 8.07,
"eval_loss": 0.4389691948890686,
"eval_runtime": 12.6443,
"eval_samples_per_second": 395.436,
"eval_steps_per_second": 3.163,
"step": 650000
},
{
"epoch": 8.07,
"learning_rate": 2.976391850971065e-05,
"loss": 0.5011,
"step": 651000
},
{
"epoch": 8.07,
"learning_rate": 2.9612829550614836e-05,
"loss": 0.4514,
"step": 652000
},
{
"epoch": 8.07,
"learning_rate": 2.9461963542348737e-05,
"loss": 0.4618,
"step": 653000
},
{
"epoch": 8.07,
"learning_rate": 2.931132213475884e-05,
"loss": 0.5079,
"step": 654000
},
{
"epoch": 8.07,
"learning_rate": 2.916090697523549e-05,
"loss": 0.5232,
"step": 655000
},
{
"epoch": 8.07,
"learning_rate": 2.9010719708694722e-05,
"loss": 0.4709,
"step": 656000
},
{
"epoch": 9.0,
"learning_rate": 2.8860761977560436e-05,
"loss": 0.478,
"step": 657000
},
{
"epoch": 9.0,
"learning_rate": 2.8711035421746367e-05,
"loss": 0.4827,
"step": 658000
},
{
"epoch": 9.0,
"learning_rate": 2.8561541678638142e-05,
"loss": 0.5126,
"step": 659000
},
{
"epoch": 9.0,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.5035,
"step": 660000
},
{
"epoch": 9.0,
"learning_rate": 2.8263259167333777e-05,
"loss": 0.4969,
"step": 661000
},
{
"epoch": 9.01,
"learning_rate": 2.811447366110741e-05,
"loss": 0.5165,
"step": 662000
},
{
"epoch": 9.01,
"learning_rate": 2.7965927491490705e-05,
"loss": 0.5451,
"step": 663000
},
{
"epoch": 9.01,
"learning_rate": 2.7817622282960815e-05,
"loss": 0.525,
"step": 664000
},
{
"epoch": 9.01,
"learning_rate": 2.766955965735968e-05,
"loss": 0.4991,
"step": 665000
},
{
"epoch": 9.01,
"learning_rate": 2.7521741233876496e-05,
"loss": 0.5163,
"step": 666000
},
{
"epoch": 9.01,
"learning_rate": 2.7374168629029813e-05,
"loss": 0.5437,
"step": 667000
},
{
"epoch": 9.01,
"learning_rate": 2.7226843456650037e-05,
"loss": 0.5298,
"step": 668000
},
{
"epoch": 9.01,
"learning_rate": 2.707976732786166e-05,
"loss": 0.4964,
"step": 669000
},
{
"epoch": 9.01,
"learning_rate": 2.693294185106562e-05,
"loss": 0.5146,
"step": 670000
},
{
"epoch": 9.01,
"learning_rate": 2.6786368631921836e-05,
"loss": 0.5405,
"step": 671000
},
{
"epoch": 9.02,
"learning_rate": 2.6640049273331515e-05,
"loss": 0.5194,
"step": 672000
},
{
"epoch": 9.02,
"learning_rate": 2.6493985375419778e-05,
"loss": 0.4901,
"step": 673000
},
{
"epoch": 9.02,
"learning_rate": 2.6348178535517966e-05,
"loss": 0.5207,
"step": 674000
},
{
"epoch": 9.02,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.4908,
"step": 675000
},
{
"epoch": 9.02,
"learning_rate": 2.6057342404996522e-05,
"loss": 0.511,
"step": 676000
},
{
"epoch": 9.02,
"learning_rate": 2.591231629491423e-05,
"loss": 0.5515,
"step": 677000
},
{
"epoch": 9.02,
"learning_rate": 2.5767553603881767e-05,
"loss": 0.5337,
"step": 678000
},
{
"epoch": 9.02,
"learning_rate": 2.562305591500069e-05,
"loss": 0.4844,
"step": 679000
},
{
"epoch": 9.02,
"learning_rate": 2.547882480847461e-05,
"loss": 0.4999,
"step": 680000
},
{
"epoch": 9.02,
"learning_rate": 2.5334861861591753e-05,
"loss": 0.547,
"step": 681000
},
{
"epoch": 9.03,
"learning_rate": 2.5191168648707887e-05,
"loss": 0.5309,
"step": 682000
},
{
"epoch": 9.03,
"learning_rate": 2.5047746741228978e-05,
"loss": 0.4883,
"step": 683000
},
{
"epoch": 9.03,
"learning_rate": 2.490459770759398e-05,
"loss": 0.5196,
"step": 684000
},
{
"epoch": 9.03,
"learning_rate": 2.476172311325783e-05,
"loss": 0.5687,
"step": 685000
},
{
"epoch": 9.03,
"learning_rate": 2.4619124520674146e-05,
"loss": 0.5434,
"step": 686000
},
{
"epoch": 9.03,
"learning_rate": 2.447680348927837e-05,
"loss": 0.4971,
"step": 687000
},
{
"epoch": 9.03,
"learning_rate": 2.433476157547044e-05,
"loss": 0.5157,
"step": 688000
},
{
"epoch": 9.03,
"learning_rate": 2.419300033259798e-05,
"loss": 0.5644,
"step": 689000
},
{
"epoch": 9.03,
"learning_rate": 2.405152131093926e-05,
"loss": 0.532,
"step": 690000
},
{
"epoch": 9.03,
"learning_rate": 2.3910326057686127e-05,
"loss": 0.4905,
"step": 691000
},
{
"epoch": 9.04,
"learning_rate": 2.3769416116927335e-05,
"loss": 0.4992,
"step": 692000
},
{
"epoch": 9.04,
"learning_rate": 2.362879302963135e-05,
"loss": 0.5578,
"step": 693000
},
{
"epoch": 9.04,
"learning_rate": 2.3488458333629777e-05,
"loss": 0.5328,
"step": 694000
},
{
"epoch": 9.04,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.4886,
"step": 695000
},
{
"epoch": 9.04,
"learning_rate": 2.3208660251050158e-05,
"loss": 0.501,
"step": 696000
},
{
"epoch": 9.04,
"learning_rate": 2.3069199924299174e-05,
"loss": 0.5541,
"step": 697000
},
{
"epoch": 9.04,
"learning_rate": 2.29300341084631e-05,
"loss": 0.5236,
"step": 698000
},
{
"epoch": 9.04,
"learning_rate": 2.279116432543705e-05,
"loss": 0.5093,
"step": 699000
},
{
"epoch": 9.04,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.4986,
"step": 700000
},
{
"epoch": 9.04,
"eval_loss": 0.4312953054904938,
"eval_runtime": 11.7123,
"eval_samples_per_second": 426.903,
"eval_steps_per_second": 3.415,
"step": 700000
},
{
"epoch": 9.04,
"learning_rate": 2.251431892919171e-05,
"loss": 0.5625,
"step": 701000
},
{
"epoch": 9.05,
"learning_rate": 2.237634634350934e-05,
"loss": 0.5532,
"step": 702000
},
{
"epoch": 9.05,
"learning_rate": 2.2238675845677663e-05,
"loss": 0.5015,
"step": 703000
},
{
"epoch": 9.05,
"learning_rate": 2.2101308941239203e-05,
"loss": 0.5165,
"step": 704000
},
{
"epoch": 9.05,
"learning_rate": 2.196424713241637e-05,
"loss": 0.5689,
"step": 705000
},
{
"epoch": 9.05,
"learning_rate": 2.182749191809518e-05,
"loss": 0.5293,
"step": 706000
},
{
"epoch": 9.05,
"learning_rate": 2.1691044793808734e-05,
"loss": 0.4865,
"step": 707000
},
{
"epoch": 9.05,
"learning_rate": 2.1554907251720945e-05,
"loss": 0.4954,
"step": 708000
},
{
"epoch": 9.05,
"learning_rate": 2.1419080780610123e-05,
"loss": 0.5401,
"step": 709000
},
{
"epoch": 9.05,
"learning_rate": 2.128356686585282e-05,
"loss": 0.5117,
"step": 710000
},
{
"epoch": 9.05,
"learning_rate": 2.1148366989407496e-05,
"loss": 0.4633,
"step": 711000
},
{
"epoch": 9.06,
"learning_rate": 2.1013482629798333e-05,
"loss": 0.5056,
"step": 712000
},
{
"epoch": 9.06,
"learning_rate": 2.0878915262099098e-05,
"loss": 0.5566,
"step": 713000
},
{
"epoch": 9.06,
"learning_rate": 2.0744666357916925e-05,
"loss": 0.5181,
"step": 714000
},
{
"epoch": 9.06,
"learning_rate": 2.061073738537635e-05,
"loss": 0.4634,
"step": 715000
},
{
"epoch": 9.06,
"learning_rate": 2.0477129809103147e-05,
"loss": 0.4965,
"step": 716000
},
{
"epoch": 9.06,
"learning_rate": 2.0343845090208368e-05,
"loss": 0.5693,
"step": 717000
},
{
"epoch": 9.06,
"learning_rate": 2.0210884686272368e-05,
"loss": 0.515,
"step": 718000
},
{
"epoch": 9.06,
"learning_rate": 2.0078250051328784e-05,
"loss": 0.4807,
"step": 719000
},
{
"epoch": 9.06,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.4983,
"step": 720000
},
{
"epoch": 9.06,
"learning_rate": 1.981396388672496e-05,
"loss": 0.5469,
"step": 721000
},
{
"epoch": 9.07,
"learning_rate": 1.9682315247255894e-05,
"loss": 0.5196,
"step": 722000
},
{
"epoch": 9.07,
"learning_rate": 1.9550998157129946e-05,
"loss": 0.4588,
"step": 723000
},
{
"epoch": 9.07,
"learning_rate": 1.942001405240979e-05,
"loss": 0.4732,
"step": 724000
},
{
"epoch": 9.07,
"learning_rate": 1.928936436551661e-05,
"loss": 0.52,
"step": 725000
},
{
"epoch": 9.07,
"learning_rate": 1.9159050525214452e-05,
"loss": 0.4887,
"step": 726000
},
{
"epoch": 9.07,
"learning_rate": 1.9029073956594606e-05,
"loss": 0.4384,
"step": 727000
},
{
"epoch": 9.07,
"learning_rate": 1.8899436081059975e-05,
"loss": 0.4524,
"step": 728000
},
{
"epoch": 9.07,
"learning_rate": 1.877013831630961e-05,
"loss": 0.5182,
"step": 729000
},
{
"epoch": 9.07,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.5097,
"step": 730000
},
{
"epoch": 10.0,
"learning_rate": 1.851256877134538e-05,
"loss": 0.46,
"step": 731000
},
{
"epoch": 10.0,
"learning_rate": 1.838429980787081e-05,
"loss": 0.4649,
"step": 732000
},
{
"epoch": 10.0,
"learning_rate": 1.8256376588628238e-05,
"loss": 0.4853,
"step": 733000
},
{
"epoch": 10.0,
"learning_rate": 1.8128800512565513e-05,
"loss": 0.5125,
"step": 734000
},
{
"epoch": 10.0,
"learning_rate": 1.800157297483417e-05,
"loss": 0.4859,
"step": 735000
},
{
"epoch": 10.01,
"learning_rate": 1.787469536677419e-05,
"loss": 0.4877,
"step": 736000
},
{
"epoch": 10.01,
"learning_rate": 1.774816907589873e-05,
"loss": 0.5229,
"step": 737000
},
{
"epoch": 10.01,
"learning_rate": 1.7621995485879062e-05,
"loss": 0.5357,
"step": 738000
},
{
"epoch": 10.01,
"learning_rate": 1.749617597652934e-05,
"loss": 0.5092,
"step": 739000
},
{
"epoch": 10.01,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.4865,
"step": 740000
},
{
"epoch": 10.01,
"learning_rate": 1.7245604699720535e-05,
"loss": 0.5216,
"step": 741000
},
{
"epoch": 10.01,
"learning_rate": 1.712085567246878e-05,
"loss": 0.5378,
"step": 742000
},
{
"epoch": 10.01,
"learning_rate": 1.699646620627168e-05,
"loss": 0.5124,
"step": 743000
},
{
"epoch": 10.01,
"learning_rate": 1.6872437661432517e-05,
"loss": 0.485,
"step": 744000
},
{
"epoch": 10.01,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.5168,
"step": 745000
},
{
"epoch": 10.02,
"learning_rate": 1.662546875729138e-05,
"loss": 0.5349,
"step": 746000
},
{
"epoch": 10.02,
"learning_rate": 1.6502531098801753e-05,
"loss": 0.5031,
"step": 747000
},
{
"epoch": 10.02,
"learning_rate": 1.637995976326527e-05,
"loss": 0.4801,
"step": 748000
},
{
"epoch": 10.02,
"learning_rate": 1.62577560911024e-05,
"loss": 0.521,
"step": 749000
},
{
"epoch": 10.02,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.4806,
"step": 750000
},
{
"epoch": 10.02,
"eval_loss": 0.4225118160247803,
"eval_runtime": 11.6104,
"eval_samples_per_second": 430.647,
"eval_steps_per_second": 3.445,
"step": 750000
},
{
"epoch": 10.02,
"learning_rate": 1.6014457078461353e-05,
"loss": 0.5055,
"step": 751000
},
{
"epoch": 10.02,
"learning_rate": 1.5893364398662176e-05,
"loss": 0.5489,
"step": 752000
},
{
"epoch": 10.02,
"learning_rate": 1.5772644703565565e-05,
"loss": 0.5249,
"step": 753000
},
{
"epoch": 10.02,
"learning_rate": 1.5652299313342773e-05,
"loss": 0.4736,
"step": 754000
},
{
"epoch": 10.02,
"learning_rate": 1.553232954407171e-05,
"loss": 0.4986,
"step": 755000
},
{
"epoch": 10.03,
"learning_rate": 1.5412736707722537e-05,
"loss": 0.542,
"step": 756000
},
{
"epoch": 10.03,
"learning_rate": 1.5293522112143373e-05,
"loss": 0.5231,
"step": 757000
},
{
"epoch": 10.03,
"learning_rate": 1.517468706104589e-05,
"loss": 0.4777,
"step": 758000
},
{
"epoch": 10.03,
"learning_rate": 1.5056232853991209e-05,
"loss": 0.5213,
"step": 759000
},
{
"epoch": 10.03,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.561,
"step": 760000
},
{
"epoch": 10.03,
"learning_rate": 1.4820472149416154e-05,
"loss": 0.5361,
"step": 761000
},
{
"epoch": 10.03,
"learning_rate": 1.470316823013707e-05,
"loss": 0.4865,
"step": 762000
},
{
"epoch": 10.03,
"learning_rate": 1.4586250311355132e-05,
"loss": 0.5157,
"step": 763000
},
{
"epoch": 10.03,
"learning_rate": 1.4469719671666043e-05,
"loss": 0.5546,
"step": 764000
},
{
"epoch": 10.03,
"learning_rate": 1.435357758543015e-05,
"loss": 0.525,
"step": 765000
},
{
"epoch": 10.04,
"learning_rate": 1.4237825322758736e-05,
"loss": 0.479,
"step": 766000
},
{
"epoch": 10.04,
"learning_rate": 1.412246414949997e-05,
"loss": 0.5016,
"step": 767000
},
{
"epoch": 10.04,
"learning_rate": 1.4007495327225162e-05,
"loss": 0.5467,
"step": 768000
},
{
"epoch": 10.04,
"learning_rate": 1.389292011321498e-05,
"loss": 0.5277,
"step": 769000
},
{
"epoch": 10.04,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.4788,
"step": 770000
},
{
"epoch": 10.04,
"learning_rate": 1.3664955517574968e-05,
"loss": 0.5046,
"step": 771000
},
{
"epoch": 10.04,
"learning_rate": 1.3551568628929434e-05,
"loss": 0.5375,
"step": 772000
},
{
"epoch": 10.04,
"learning_rate": 1.343858033448982e-05,
"loss": 0.5187,
"step": 773000
},
{
"epoch": 10.04,
"learning_rate": 1.3325991869878013e-05,
"loss": 0.4998,
"step": 774000
},
{
"epoch": 10.04,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.5008,
"step": 775000
},
{
"epoch": 10.05,
"learning_rate": 1.3102019350749528e-05,
"loss": 0.5555,
"step": 776000
},
{
"epoch": 10.05,
"learning_rate": 1.299063774556042e-05,
"loss": 0.5489,
"step": 777000
},
{
"epoch": 10.05,
"learning_rate": 1.2879660868827508e-05,
"loss": 0.4922,
"step": 778000
},
{
"epoch": 10.05,
"learning_rate": 1.2769089934176126e-05,
"loss": 0.5192,
"step": 779000
},
{
"epoch": 10.05,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.5504,
"step": 780000
},
{
"epoch": 10.05,
"learning_rate": 1.2549170723409549e-05,
"loss": 0.5261,
"step": 781000
},
{
"epoch": 10.05,
"learning_rate": 1.243982485229559e-05,
"loss": 0.4768,
"step": 782000
},
{
"epoch": 10.05,
"learning_rate": 1.233088973323937e-05,
"loss": 0.494,
"step": 783000
},
{
"epoch": 10.05,
"learning_rate": 1.2222366557537911e-05,
"loss": 0.5254,
"step": 784000
},
{
"epoch": 10.05,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.5082,
"step": 785000
},
{
"epoch": 10.06,
"learning_rate": 1.2006560778849578e-05,
"loss": 0.4551,
"step": 786000
},
{
"epoch": 10.06,
"learning_rate": 1.1899280535880119e-05,
"loss": 0.5125,
"step": 787000
},
{
"epoch": 10.06,
"learning_rate": 1.1792416956274444e-05,
"loss": 0.5392,
"step": 788000
},
{
"epoch": 10.06,
"learning_rate": 1.1685971208675539e-05,
"loss": 0.511,
"step": 789000
},
{
"epoch": 10.06,
"learning_rate": 1.157994445715706e-05,
"loss": 0.4542,
"step": 790000
},
{
"epoch": 10.06,
"learning_rate": 1.1474337861210543e-05,
"loss": 0.5215,
"step": 791000
},
{
"epoch": 10.06,
"learning_rate": 1.1369152575732822e-05,
"loss": 0.5341,
"step": 792000
},
{
"epoch": 10.06,
"learning_rate": 1.1264389751013326e-05,
"loss": 0.5125,
"step": 793000
},
{
"epoch": 10.06,
"learning_rate": 1.1160050532721528e-05,
"loss": 0.4715,
"step": 794000
},
{
"epoch": 10.06,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.5013,
"step": 795000
},
{
"epoch": 10.07,
"learning_rate": 1.095264747492391e-05,
"loss": 0.5343,
"step": 796000
},
{
"epoch": 10.07,
"learning_rate": 1.0849585903544706e-05,
"loss": 0.5079,
"step": 797000
},
{
"epoch": 10.07,
"learning_rate": 1.0746952474821614e-05,
"loss": 0.4506,
"step": 798000
},
{
"epoch": 10.07,
"learning_rate": 1.0644748311137376e-05,
"loss": 0.4786,
"step": 799000
},
{
"epoch": 10.07,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.5089,
"step": 800000
},
{
"epoch": 10.07,
"eval_loss": 0.4219503402709961,
"eval_runtime": 14.0676,
"eval_samples_per_second": 355.426,
"eval_steps_per_second": 2.843,
"step": 800000
},
{
"epoch": 10.07,
"learning_rate": 1.0441632244932237e-05,
"loss": 0.4792,
"step": 801000
},
{
"epoch": 10.07,
"learning_rate": 1.0340722563656107e-05,
"loss": 0.4311,
"step": 802000
},
{
"epoch": 10.07,
"learning_rate": 1.0240246589884044e-05,
"loss": 0.4554,
"step": 803000
},
{
"epoch": 10.07,
"learning_rate": 1.0140205422405214e-05,
"loss": 0.5171,
"step": 804000
},
{
"epoch": 10.07,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.5012,
"step": 805000
},
{
"epoch": 11.0,
"learning_rate": 9.941431877696955e-06,
"loss": 0.4562,
"step": 806000
},
{
"epoch": 11.0,
"learning_rate": 9.842701674223187e-06,
"loss": 0.4558,
"step": 807000
},
{
"epoch": 11.0,
"learning_rate": 9.744410624530148e-06,
"loss": 0.4869,
"step": 808000
},
{
"epoch": 11.0,
"learning_rate": 9.646559803512994e-06,
"loss": 0.5118,
"step": 809000
},
{
"epoch": 11.0,
"learning_rate": 9.549150281252633e-06,
"loss": 0.477,
"step": 810000
},
{
"epoch": 11.01,
"learning_rate": 9.452183123004e-06,
"loss": 0.4816,
"step": 811000
},
{
"epoch": 11.01,
"learning_rate": 9.355659389184396e-06,
"loss": 0.5241,
"step": 812000
},
{
"epoch": 11.01,
"learning_rate": 9.259580135361929e-06,
"loss": 0.5285,
"step": 813000
},
{
"epoch": 11.01,
"learning_rate": 9.163946412243896e-06,
"loss": 0.4973,
"step": 814000
},
{
"epoch": 11.01,
"learning_rate": 9.068759265665384e-06,
"loss": 0.4801,
"step": 815000
},
{
"epoch": 11.01,
"learning_rate": 8.974019736577777e-06,
"loss": 0.5235,
"step": 816000
},
{
"epoch": 11.01,
"learning_rate": 8.879728861037384e-06,
"loss": 0.5333,
"step": 817000
},
{
"epoch": 11.01,
"learning_rate": 8.785887670194138e-06,
"loss": 0.4985,
"step": 818000
},
{
"epoch": 11.01,
"learning_rate": 8.692497190280224e-06,
"loss": 0.4783,
"step": 819000
},
{
"epoch": 11.01,
"learning_rate": 8.599558442598998e-06,
"loss": 0.5221,
"step": 820000
},
{
"epoch": 11.02,
"learning_rate": 8.507072443513702e-06,
"loss": 0.5295,
"step": 821000
},
{
"epoch": 11.02,
"learning_rate": 8.415040204436426e-06,
"loss": 0.4898,
"step": 822000
},
{
"epoch": 11.02,
"learning_rate": 8.323462731816961e-06,
"loss": 0.4771,
"step": 823000
},
{
"epoch": 11.02,
"learning_rate": 8.232341027131885e-06,
"loss": 0.5171,
"step": 824000
},
{
"epoch": 11.02,
"learning_rate": 8.141676086873572e-06,
"loss": 0.4768,
"step": 825000
},
{
"epoch": 11.02,
"learning_rate": 8.051468902539272e-06,
"loss": 0.5062,
"step": 826000
},
{
"epoch": 11.02,
"learning_rate": 7.96172046062032e-06,
"loss": 0.5417,
"step": 827000
},
{
"epoch": 11.02,
"learning_rate": 7.872431742591268e-06,
"loss": 0.5129,
"step": 828000
},
{
"epoch": 11.02,
"learning_rate": 7.783603724899257e-06,
"loss": 0.4705,
"step": 829000
},
{
"epoch": 11.02,
"learning_rate": 7.695237378953223e-06,
"loss": 0.5012,
"step": 830000
},
{
"epoch": 11.03,
"learning_rate": 7.607333671113409e-06,
"loss": 0.537,
"step": 831000
},
{
"epoch": 11.03,
"learning_rate": 7.519893562680663e-06,
"loss": 0.5122,
"step": 832000
},
{
"epoch": 11.03,
"learning_rate": 7.432918009885997e-06,
"loss": 0.4753,
"step": 833000
},
{
"epoch": 11.03,
"learning_rate": 7.3464079638801365e-06,
"loss": 0.5233,
"step": 834000
},
{
"epoch": 11.03,
"learning_rate": 7.260364370723044e-06,
"loss": 0.5564,
"step": 835000
},
{
"epoch": 11.03,
"learning_rate": 7.174788171373731e-06,
"loss": 0.5241,
"step": 836000
},
{
"epoch": 11.03,
"learning_rate": 7.089680301679752e-06,
"loss": 0.4848,
"step": 837000
},
{
"epoch": 11.03,
"learning_rate": 7.005041692367154e-06,
"loss": 0.5161,
"step": 838000
},
{
"epoch": 11.03,
"learning_rate": 6.92087326903022e-06,
"loss": 0.5477,
"step": 839000
},
{
"epoch": 11.03,
"learning_rate": 6.837175952121306e-06,
"loss": 0.5151,
"step": 840000
},
{
"epoch": 11.04,
"learning_rate": 6.753950656940905e-06,
"loss": 0.4753,
"step": 841000
},
{
"epoch": 11.04,
"learning_rate": 6.671198293627479e-06,
"loss": 0.5034,
"step": 842000
},
{
"epoch": 11.04,
"learning_rate": 6.588919767147639e-06,
"loss": 0.5449,
"step": 843000
},
{
"epoch": 11.04,
"learning_rate": 6.5071159772861436e-06,
"loss": 0.5154,
"step": 844000
},
{
"epoch": 11.04,
"learning_rate": 6.425787818636131e-06,
"loss": 0.4756,
"step": 845000
},
{
"epoch": 11.04,
"learning_rate": 6.344936180589351e-06,
"loss": 0.5057,
"step": 846000
},
{
"epoch": 11.04,
"learning_rate": 6.264561947326331e-06,
"loss": 0.5353,
"step": 847000
},
{
"epoch": 11.04,
"learning_rate": 6.184665997806832e-06,
"loss": 0.5077,
"step": 848000
},
{
"epoch": 11.04,
"learning_rate": 6.1052492057601275e-06,
"loss": 0.4977,
"step": 849000
},
{
"epoch": 11.04,
"learning_rate": 6.026312439675552e-06,
"loss": 0.5011,
"step": 850000
},
{
"epoch": 11.04,
"eval_loss": 0.4203606843948364,
"eval_runtime": 69.9698,
"eval_samples_per_second": 71.459,
"eval_steps_per_second": 0.572,
"step": 850000
},
{
"epoch": 11.05,
"learning_rate": 5.947856562792925e-06,
"loss": 0.5579,
"step": 851000
},
{
"epoch": 11.05,
"learning_rate": 5.869882433093155e-06,
"loss": 0.5342,
"step": 852000
},
{
"epoch": 11.05,
"learning_rate": 5.79239090328883e-06,
"loss": 0.4915,
"step": 853000
},
{
"epoch": 11.05,
"learning_rate": 5.715382820814885e-06,
"loss": 0.5185,
"step": 854000
},
{
"epoch": 11.05,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.5439,
"step": 855000
},
{
"epoch": 11.05,
"learning_rate": 5.562820361154314e-06,
"loss": 0.5144,
"step": 856000
},
{
"epoch": 11.05,
"learning_rate": 5.48726765236629e-06,
"loss": 0.4734,
"step": 857000
},
{
"epoch": 11.05,
"learning_rate": 5.412201727687644e-06,
"loss": 0.491,
"step": 858000
},
{
"epoch": 11.05,
"learning_rate": 5.337623408027293e-06,
"loss": 0.5233,
"step": 859000
},
{
"epoch": 11.05,
"learning_rate": 5.263533508961827e-06,
"loss": 0.4936,
"step": 860000
},
{
"epoch": 11.06,
"learning_rate": 5.1899328407264855e-06,
"loss": 0.4585,
"step": 861000
},
{
"epoch": 11.06,
"learning_rate": 5.116822208206396e-06,
"loss": 0.5104,
"step": 862000
},
{
"epoch": 11.06,
"learning_rate": 5.044202410927706e-06,
"loss": 0.5342,
"step": 863000
},
{
"epoch": 11.06,
"learning_rate": 4.972074243048897e-06,
"loss": 0.4968,
"step": 864000
},
{
"epoch": 11.06,
"learning_rate": 4.900438493352055e-06,
"loss": 0.4527,
"step": 865000
},
{
"epoch": 11.06,
"learning_rate": 4.829295945234258e-06,
"loss": 0.5301,
"step": 866000
},
{
"epoch": 11.06,
"learning_rate": 4.758647376699032e-06,
"loss": 0.5213,
"step": 867000
},
{
"epoch": 11.06,
"learning_rate": 4.688493560347773e-06,
"loss": 0.5033,
"step": 868000
},
{
"epoch": 11.06,
"learning_rate": 4.618835263371396e-06,
"loss": 0.4709,
"step": 869000
},
{
"epoch": 11.06,
"learning_rate": 4.549673247541875e-06,
"loss": 0.4998,
"step": 870000
},
{
"epoch": 11.07,
"learning_rate": 4.48100826920394e-06,
"loss": 0.5318,
"step": 871000
},
{
"epoch": 11.07,
"learning_rate": 4.412841079266777e-06,
"loss": 0.4929,
"step": 872000
},
{
"epoch": 11.07,
"learning_rate": 4.3451724231958644e-06,
"loss": 0.4505,
"step": 873000
},
{
"epoch": 11.07,
"learning_rate": 4.27800304100478e-06,
"loss": 0.4804,
"step": 874000
},
{
"epoch": 11.07,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.5057,
"step": 875000
},
{
"epoch": 11.07,
"learning_rate": 4.145165031008508e-06,
"loss": 0.4685,
"step": 876000
},
{
"epoch": 11.07,
"learning_rate": 4.079497855898501e-06,
"loss": 0.4303,
"step": 877000
},
{
"epoch": 11.07,
"learning_rate": 4.01433286004283e-06,
"loss": 0.46,
"step": 878000
},
{
"epoch": 11.07,
"learning_rate": 3.949670756075447e-06,
"loss": 0.5197,
"step": 879000
},
{
"epoch": 11.07,
"learning_rate": 3.885512251130763e-06,
"loss": 0.4886,
"step": 880000
},
{
"epoch": 12.0,
"learning_rate": 3.821858046835913e-06,
"loss": 0.4545,
"step": 881000
},
{
"epoch": 12.0,
"learning_rate": 3.75870883930306e-06,
"loss": 0.4543,
"step": 882000
},
{
"epoch": 12.0,
"learning_rate": 3.696065319121833e-06,
"loss": 0.4902,
"step": 883000
},
{
"epoch": 12.0,
"learning_rate": 3.6339281713517303e-06,
"loss": 0.5127,
"step": 884000
},
{
"epoch": 12.0,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.4717,
"step": 885000
},
{
"epoch": 12.01,
"learning_rate": 3.511175705587433e-06,
"loss": 0.4767,
"step": 886000
},
{
"epoch": 12.01,
"learning_rate": 3.4505617299945336e-06,
"loss": 0.5242,
"step": 887000
},
{
"epoch": 12.01,
"learning_rate": 3.390456811600673e-06,
"loss": 0.5297,
"step": 888000
},
{
"epoch": 12.01,
"learning_rate": 3.3308616077036115e-06,
"loss": 0.4846,
"step": 889000
},
{
"epoch": 12.01,
"learning_rate": 3.271776770026963e-06,
"loss": 0.4763,
"step": 890000
},
{
"epoch": 12.01,
"learning_rate": 3.213202944713023e-06,
"loss": 0.5236,
"step": 891000
},
{
"epoch": 12.01,
"learning_rate": 3.155140772315773e-06,
"loss": 0.537,
"step": 892000
},
{
"epoch": 12.01,
"learning_rate": 3.0975908877938277e-06,
"loss": 0.4858,
"step": 893000
},
{
"epoch": 12.01,
"learning_rate": 3.040553920503503e-06,
"loss": 0.4746,
"step": 894000
},
{
"epoch": 12.01,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.523,
"step": 895000
},
{
"epoch": 12.02,
"learning_rate": 2.928021226990263e-06,
"loss": 0.5302,
"step": 896000
},
{
"epoch": 12.02,
"learning_rate": 2.8725267314068495e-06,
"loss": 0.4774,
"step": 897000
},
{
"epoch": 12.02,
"learning_rate": 2.817547614320615e-06,
"loss": 0.4829,
"step": 898000
},
{
"epoch": 12.02,
"learning_rate": 2.7630844769743757e-06,
"loss": 0.506,
"step": 899000
},
{
"epoch": 12.02,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.4766,
"step": 900000
},
{
"epoch": 12.02,
"eval_loss": 0.4155268967151642,
"eval_runtime": 11.4713,
"eval_samples_per_second": 435.87,
"eval_steps_per_second": 3.487,
"step": 900000
},
{
"epoch": 12.02,
"learning_rate": 2.6557085182532582e-06,
"loss": 0.5092,
"step": 901000
},
{
"epoch": 12.02,
"learning_rate": 2.602796871124663e-06,
"loss": 0.5345,
"step": 902000
},
{
"epoch": 12.02,
"learning_rate": 2.5504035522157854e-06,
"loss": 0.505,
"step": 903000
},
{
"epoch": 12.02,
"learning_rate": 2.4985291344915674e-06,
"loss": 0.4708,
"step": 904000
},
{
"epoch": 12.02,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.5031,
"step": 905000
},
{
"epoch": 12.03,
"learning_rate": 2.3963392660775575e-06,
"loss": 0.5311,
"step": 906000
},
{
"epoch": 12.03,
"learning_rate": 2.3460249329197824e-06,
"loss": 0.5038,
"step": 907000
},
{
"epoch": 12.03,
"learning_rate": 2.296231735998511e-06,
"loss": 0.4824,
"step": 908000
},
{
"epoch": 12.03,
"learning_rate": 2.2469602198441573e-06,
"loss": 0.525,
"step": 909000
},
{
"epoch": 12.03,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.5494,
"step": 910000
},
{
"epoch": 12.03,
"learning_rate": 2.149984379426906e-06,
"loss": 0.5128,
"step": 911000
},
{
"epoch": 12.03,
"learning_rate": 2.102281115676258e-06,
"loss": 0.4906,
"step": 912000
},
{
"epoch": 12.03,
"learning_rate": 2.0551016537054493e-06,
"loss": 0.5195,
"step": 913000
},
{
"epoch": 12.03,
"learning_rate": 2.008446509461498e-06,
"loss": 0.5414,
"step": 914000
},
{
"epoch": 12.03,
"learning_rate": 1.962316193157593e-06,
"loss": 0.5017,
"step": 915000
},
{
"epoch": 12.04,
"learning_rate": 1.91671120926748e-06,
"loss": 0.4817,
"step": 916000
},
{
"epoch": 12.04,
"learning_rate": 1.8716320565199618e-06,
"loss": 0.5091,
"step": 917000
},
{
"epoch": 12.04,
"learning_rate": 1.8270792278934302e-06,
"loss": 0.5369,
"step": 918000
},
{
"epoch": 12.04,
"learning_rate": 1.7830532106104747e-06,
"loss": 0.5008,
"step": 919000
},
{
"epoch": 12.04,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.4833,
"step": 920000
},
{
"epoch": 12.04,
"learning_rate": 1.696583530154794e-06,
"loss": 0.5125,
"step": 921000
},
{
"epoch": 12.04,
"learning_rate": 1.6541408126006463e-06,
"loss": 0.5276,
"step": 922000
},
{
"epoch": 12.04,
"learning_rate": 1.6122267976168781e-06,
"loss": 0.4981,
"step": 923000
},
{
"epoch": 12.04,
"learning_rate": 1.5708419435684462e-06,
"loss": 0.503,
"step": 924000
},
{
"epoch": 12.04,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.5057,
"step": 925000
},
{
"epoch": 12.05,
"learning_rate": 1.4896615227983468e-06,
"loss": 0.5574,
"step": 926000
},
{
"epoch": 12.05,
"learning_rate": 1.4498668438527597e-06,
"loss": 0.5185,
"step": 927000
},
{
"epoch": 12.05,
"learning_rate": 1.4106031013849496e-06,
"loss": 0.5015,
"step": 928000
},
{
"epoch": 12.05,
"learning_rate": 1.3718707247769135e-06,
"loss": 0.5219,
"step": 929000
},
{
"epoch": 12.05,
"learning_rate": 1.333670137599713e-06,
"loss": 0.5368,
"step": 930000
},
{
"epoch": 12.05,
"learning_rate": 1.2960017576088446e-06,
"loss": 0.4965,
"step": 931000
},
{
"epoch": 12.05,
"learning_rate": 1.2588659967397e-06,
"loss": 0.4832,
"step": 932000
},
{
"epoch": 12.05,
"learning_rate": 1.222263261102985e-06,
"loss": 0.4951,
"step": 933000
},
{
"epoch": 12.05,
"learning_rate": 1.1861939509803687e-06,
"loss": 0.5181,
"step": 934000
},
{
"epoch": 12.05,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.4736,
"step": 935000
},
{
"epoch": 12.06,
"learning_rate": 1.1156571792324211e-06,
"loss": 0.4763,
"step": 936000
},
{
"epoch": 12.06,
"learning_rate": 1.0811904889859336e-06,
"loss": 0.5135,
"step": 937000
},
{
"epoch": 12.06,
"learning_rate": 1.0472587670027678e-06,
"loss": 0.5277,
"step": 938000
},
{
"epoch": 12.06,
"learning_rate": 1.0138623843548078e-06,
"loss": 0.476,
"step": 939000
},
{
"epoch": 12.06,
"learning_rate": 9.810017062595322e-07,
"loss": 0.4632,
"step": 940000
},
{
"epoch": 12.06,
"learning_rate": 9.486770920760668e-07,
"loss": 0.5357,
"step": 941000
},
{
"epoch": 12.06,
"learning_rate": 9.168888953011989e-07,
"loss": 0.5172,
"step": 942000
},
{
"epoch": 12.06,
"learning_rate": 8.856374635655695e-07,
"loss": 0.4867,
"step": 943000
},
{
"epoch": 12.06,
"learning_rate": 8.549231386298151e-07,
"loss": 0.4824,
"step": 944000
},
{
"epoch": 12.06,
"learning_rate": 8.247462563808817e-07,
"loss": 0.5044,
"step": 945000
},
{
"epoch": 12.07,
"learning_rate": 7.951071468283167e-07,
"loss": 0.5286,
"step": 946000
},
{
"epoch": 12.07,
"learning_rate": 7.66006134100672e-07,
"loss": 0.4702,
"step": 947000
},
{
"epoch": 12.07,
"learning_rate": 7.374435364419674e-07,
"loss": 0.4656,
"step": 948000
},
{
"epoch": 12.07,
"learning_rate": 7.094196662081831e-07,
"loss": 0.4874,
"step": 949000
},
{
"epoch": 12.07,
"learning_rate": 6.819348298638839e-07,
"loss": 0.4981,
"step": 950000
},
{
"epoch": 12.07,
"eval_loss": 0.41201308369636536,
"eval_runtime": 12.2656,
"eval_samples_per_second": 407.643,
"eval_steps_per_second": 3.261,
"step": 950000
},
{
"epoch": 12.07,
"learning_rate": 6.549893279788277e-07,
"loss": 0.4494,
"step": 951000
},
{
"epoch": 12.07,
"learning_rate": 6.285834552247128e-07,
"loss": 0.4465,
"step": 952000
},
{
"epoch": 12.07,
"learning_rate": 6.027175003719354e-07,
"loss": 0.4663,
"step": 953000
},
{
"epoch": 12.07,
"learning_rate": 5.773917462864264e-07,
"loss": 0.5254,
"step": 954000
},
{
"epoch": 12.07,
"learning_rate": 5.526064699265753e-07,
"loss": 0.4647,
"step": 955000
},
{
"epoch": 13.0,
"learning_rate": 5.283619423401998e-07,
"loss": 0.4716,
"step": 956000
},
{
"epoch": 13.0,
"learning_rate": 5.046584286615697e-07,
"loss": 0.4556,
"step": 957000
},
{
"epoch": 13.0,
"learning_rate": 4.814961881085045e-07,
"loss": 0.4911,
"step": 958000
},
{
"epoch": 13.0,
"learning_rate": 4.5887547397955864e-07,
"loss": 0.5024,
"step": 959000
},
{
"epoch": 13.0,
"learning_rate": 4.367965336512403e-07,
"loss": 0.4838,
"step": 960000
},
{
"epoch": 13.01,
"learning_rate": 4.1525960857530243e-07,
"loss": 0.4784,
"step": 961000
},
{
"epoch": 13.01,
"learning_rate": 3.9426493427611177e-07,
"loss": 0.5217,
"step": 962000
},
{
"epoch": 13.01,
"learning_rate": 3.738127403480507e-07,
"loss": 0.5145,
"step": 963000
},
{
"epoch": 13.01,
"learning_rate": 3.5390325045304706e-07,
"loss": 0.493,
"step": 964000
},
{
"epoch": 13.01,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.4808,
"step": 965000
},
{
"epoch": 13.01,
"learning_rate": 3.157132477328628e-07,
"loss": 0.523,
"step": 966000
},
{
"epoch": 13.01,
"learning_rate": 2.9743315254743833e-07,
"loss": 0.5228,
"step": 967000
},
{
"epoch": 13.01,
"learning_rate": 2.796965966699927e-07,
"loss": 0.4934,
"step": 968000
},
{
"epoch": 13.01,
"learning_rate": 2.625037740646763e-07,
"loss": 0.478,
"step": 969000
},
{
"epoch": 13.01,
"learning_rate": 2.458548727494292e-07,
"loss": 0.5233,
"step": 970000
},
{
"epoch": 13.02,
"learning_rate": 2.2975007479397738e-07,
"loss": 0.5158,
"step": 971000
},
{
"epoch": 13.02,
"learning_rate": 2.1418955631781202e-07,
"loss": 0.486,
"step": 972000
},
{
"epoch": 13.02,
"learning_rate": 1.9917348748826335e-07,
"loss": 0.4902,
"step": 973000
},
{
"epoch": 13.02,
"learning_rate": 1.847020325186577e-07,
"loss": 0.4818,
"step": 974000
},
{
"epoch": 13.02,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.4967,
"step": 975000
},
{
"epoch": 13.02,
"learning_rate": 1.5739359123178587e-07,
"loss": 0.5156,
"step": 976000
},
{
"epoch": 13.02,
"learning_rate": 1.4455690355525964e-07,
"loss": 0.5312,
"step": 977000
},
{
"epoch": 13.02,
"learning_rate": 1.3226542701689215e-07,
"loss": 0.4816,
"step": 978000
},
{
"epoch": 13.02,
"learning_rate": 1.2051929603428825e-07,
"loss": 0.4891,
"step": 979000
},
{
"epoch": 13.02,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.5107,
"step": 980000
},
{
"epoch": 13.03,
"learning_rate": 9.866357858642205e-08,
"loss": 0.5282,
"step": 981000
},
{
"epoch": 13.03,
"learning_rate": 8.855423113177664e-08,
"loss": 0.483,
"step": 982000
},
{
"epoch": 13.03,
"learning_rate": 7.899070725153613e-08,
"loss": 0.5034,
"step": 983000
},
{
"epoch": 13.03,
"learning_rate": 6.997311153086883e-08,
"loss": 0.5341,
"step": 984000
},
{
"epoch": 13.03,
"learning_rate": 6.150154258476315e-08,
"loss": 0.5145,
"step": 985000
},
{
"epoch": 13.03,
"learning_rate": 5.3576093056922906e-08,
"loss": 0.4675,
"step": 986000
},
{
"epoch": 13.03,
"learning_rate": 4.619684961881254e-08,
"loss": 0.4735,
"step": 987000
},
{
"epoch": 13.03,
"learning_rate": 3.936389296864129e-08,
"loss": 0.522,
"step": 988000
},
{
"epoch": 13.03,
"learning_rate": 3.3077297830541584e-08,
"loss": 0.5232,
"step": 989000
},
{
"epoch": 13.03,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.473,
"step": 990000
},
{
"epoch": 13.04,
"learning_rate": 2.214346111164556e-08,
"loss": 0.4686,
"step": 991000
},
{
"epoch": 13.04,
"learning_rate": 1.749633910153592e-08,
"loss": 0.5288,
"step": 992000
},
{
"epoch": 13.04,
"learning_rate": 1.3395817743561134e-08,
"loss": 0.5264,
"step": 993000
},
{
"epoch": 13.04,
"learning_rate": 9.841941880361916e-09,
"loss": 0.4746,
"step": 994000
},
{
"epoch": 13.04,
"learning_rate": 6.834750376549792e-09,
"loss": 0.4896,
"step": 995000
},
{
"epoch": 13.04,
"learning_rate": 4.3742761183018784e-09,
"loss": 0.5191,
"step": 996000
},
{
"epoch": 13.04,
"learning_rate": 2.4605460129556445e-09,
"loss": 0.5255,
"step": 997000
},
{
"epoch": 13.04,
"learning_rate": 1.0935809887702154e-09,
"loss": 0.4732,
"step": 998000
},
{
"epoch": 13.04,
"learning_rate": 2.7339599464326627e-10,
"loss": 0.4697,
"step": 999000
},
{
"epoch": 13.04,
"learning_rate": 0.0,
"loss": 0.4974,
"step": 1000000
},
{
"epoch": 13.04,
"eval_loss": 0.4091758728027344,
"eval_runtime": 12.5131,
"eval_samples_per_second": 399.581,
"eval_steps_per_second": 3.197,
"step": 1000000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.6845503889565286e+19,
"trial_name": null,
"trial_params": null
}