joelniklaus's picture
Training in progress, step 500000
76b4997
raw
history blame
No virus
63.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5,
"global_step": 500000,
"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": 6.7042,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 5.1179,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 4.5505,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 4.3111,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.0888,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 3.9555,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 3.8349,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 3.8199,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 3.6237,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 3.7137,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 3.5308,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 3.3471,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 3.2095,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 3.1049,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 2.9958,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.8518,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.7929,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 2.6958,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 2.7341,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.6605,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 2.5796,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.499,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 2.4217,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 2.285,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 2.2433,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.8565,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.6906,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.6053,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.5208,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.4884,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 1.4536,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.4163,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.3619,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3432,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 1.3435,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 1.3395,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 1.3372,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 1.3257,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 1.2969,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.2716,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 1.2637,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 1.2254,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 1.257,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 1.2555,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 1.258,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 1.2429,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 1.2297,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 1.2281,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 1.1976,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.193,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.6851979494094849,
"eval_runtime": 114.3167,
"eval_samples_per_second": 43.738,
"eval_steps_per_second": 0.691,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 1.2195,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 1.1675,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 1.1804,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 1.1654,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 1.1731,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 1.1482,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 1.136,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 1.1142,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 1.1169,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 1.105,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 1.106,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 1.1023,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 1.0824,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 1.088,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 1.1121,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 1.1019,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 1.1244,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 1.0794,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 1.0748,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 1.0954,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 1.0871,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 1.086,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 1.0842,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 1.0924,
"step": 74000
},
{
"epoch": 0.07,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0783,
"step": 75000
},
{
"epoch": 0.08,
"learning_rate": 9.981529796748134e-05,
"loss": 1.0547,
"step": 76000
},
{
"epoch": 0.08,
"learning_rate": 9.980082651251175e-05,
"loss": 1.0725,
"step": 77000
},
{
"epoch": 0.08,
"learning_rate": 9.97858104436822e-05,
"loss": 1.0847,
"step": 78000
},
{
"epoch": 0.08,
"learning_rate": 9.977024992520602e-05,
"loss": 1.0695,
"step": 79000
},
{
"epoch": 0.08,
"learning_rate": 9.975414512725057e-05,
"loss": 1.0657,
"step": 80000
},
{
"epoch": 0.08,
"learning_rate": 9.973749622593534e-05,
"loss": 1.0415,
"step": 81000
},
{
"epoch": 0.08,
"learning_rate": 9.972030340333001e-05,
"loss": 1.047,
"step": 82000
},
{
"epoch": 0.08,
"learning_rate": 9.970256684745258e-05,
"loss": 1.0437,
"step": 83000
},
{
"epoch": 0.08,
"learning_rate": 9.968428675226714e-05,
"loss": 1.0484,
"step": 84000
},
{
"epoch": 0.09,
"learning_rate": 9.966546331768191e-05,
"loss": 1.0601,
"step": 85000
},
{
"epoch": 0.09,
"learning_rate": 9.964609674954696e-05,
"loss": 1.0666,
"step": 86000
},
{
"epoch": 0.09,
"learning_rate": 9.962618725965196e-05,
"loss": 1.0594,
"step": 87000
},
{
"epoch": 0.09,
"learning_rate": 9.96057350657239e-05,
"loss": 1.0493,
"step": 88000
},
{
"epoch": 0.09,
"learning_rate": 9.95847403914247e-05,
"loss": 1.0604,
"step": 89000
},
{
"epoch": 0.09,
"learning_rate": 9.956320346634876e-05,
"loss": 1.0533,
"step": 90000
},
{
"epoch": 0.09,
"learning_rate": 9.954112452602045e-05,
"loss": 1.0552,
"step": 91000
},
{
"epoch": 0.09,
"learning_rate": 9.95185038118915e-05,
"loss": 1.0535,
"step": 92000
},
{
"epoch": 0.09,
"learning_rate": 9.949534157133844e-05,
"loss": 1.0618,
"step": 93000
},
{
"epoch": 0.09,
"learning_rate": 9.94716380576598e-05,
"loss": 1.0459,
"step": 94000
},
{
"epoch": 0.1,
"learning_rate": 9.944739353007344e-05,
"loss": 1.0431,
"step": 95000
},
{
"epoch": 0.1,
"learning_rate": 9.942260825371358e-05,
"loss": 1.0274,
"step": 96000
},
{
"epoch": 0.1,
"learning_rate": 9.939728249962807e-05,
"loss": 1.0104,
"step": 97000
},
{
"epoch": 0.1,
"learning_rate": 9.937141654477528e-05,
"loss": 1.0039,
"step": 98000
},
{
"epoch": 0.1,
"learning_rate": 9.934501067202117e-05,
"loss": 1.0206,
"step": 99000
},
{
"epoch": 0.1,
"learning_rate": 9.931806517013612e-05,
"loss": 1.0214,
"step": 100000
},
{
"epoch": 0.1,
"eval_loss": 0.5695434808731079,
"eval_runtime": 114.0507,
"eval_samples_per_second": 43.84,
"eval_steps_per_second": 0.693,
"step": 100000
},
{
"epoch": 0.1,
"learning_rate": 9.929058033379181e-05,
"loss": 1.0319,
"step": 101000
},
{
"epoch": 0.1,
"learning_rate": 9.926255646355804e-05,
"loss": 1.0237,
"step": 102000
},
{
"epoch": 0.1,
"learning_rate": 9.923399386589933e-05,
"loss": 1.0235,
"step": 103000
},
{
"epoch": 0.1,
"learning_rate": 9.92048928531717e-05,
"loss": 1.0082,
"step": 104000
},
{
"epoch": 0.1,
"learning_rate": 9.917525374361912e-05,
"loss": 1.0308,
"step": 105000
},
{
"epoch": 0.11,
"learning_rate": 9.914507686137019e-05,
"loss": 1.0448,
"step": 106000
},
{
"epoch": 0.11,
"learning_rate": 9.911436253643445e-05,
"loss": 1.0277,
"step": 107000
},
{
"epoch": 0.11,
"learning_rate": 9.90831111046988e-05,
"loss": 1.0076,
"step": 108000
},
{
"epoch": 0.11,
"learning_rate": 9.905132290792394e-05,
"loss": 1.0161,
"step": 109000
},
{
"epoch": 0.11,
"learning_rate": 9.901899829374047e-05,
"loss": 0.986,
"step": 110000
},
{
"epoch": 0.11,
"learning_rate": 9.89861376156452e-05,
"loss": 0.944,
"step": 111000
},
{
"epoch": 0.11,
"learning_rate": 9.895274123299723e-05,
"loss": 1.0054,
"step": 112000
},
{
"epoch": 0.11,
"learning_rate": 9.891880951101407e-05,
"loss": 1.0082,
"step": 113000
},
{
"epoch": 0.11,
"learning_rate": 9.888434282076758e-05,
"loss": 1.0296,
"step": 114000
},
{
"epoch": 0.12,
"learning_rate": 9.884934153917997e-05,
"loss": 0.9877,
"step": 115000
},
{
"epoch": 0.12,
"learning_rate": 9.881380604901964e-05,
"loss": 1.0095,
"step": 116000
},
{
"epoch": 0.12,
"learning_rate": 9.877773673889701e-05,
"loss": 0.9812,
"step": 117000
},
{
"epoch": 0.12,
"learning_rate": 9.87411340032603e-05,
"loss": 0.9829,
"step": 118000
},
{
"epoch": 0.12,
"learning_rate": 9.870399824239117e-05,
"loss": 0.9751,
"step": 119000
},
{
"epoch": 0.12,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9376,
"step": 120000
},
{
"epoch": 0.12,
"learning_rate": 9.862812927522309e-05,
"loss": 0.9635,
"step": 121000
},
{
"epoch": 0.12,
"learning_rate": 9.858939689861506e-05,
"loss": 0.9636,
"step": 122000
},
{
"epoch": 0.12,
"learning_rate": 9.855013315614725e-05,
"loss": 0.9879,
"step": 123000
},
{
"epoch": 0.12,
"learning_rate": 9.851033847720166e-05,
"loss": 0.9704,
"step": 124000
},
{
"epoch": 0.12,
"learning_rate": 9.847001329696653e-05,
"loss": 1.005,
"step": 125000
},
{
"epoch": 0.13,
"learning_rate": 9.842915805643155e-05,
"loss": 0.9819,
"step": 126000
},
{
"epoch": 0.13,
"learning_rate": 9.838777320238312e-05,
"loss": 0.9765,
"step": 127000
},
{
"epoch": 0.13,
"learning_rate": 9.834585918739936e-05,
"loss": 0.9876,
"step": 128000
},
{
"epoch": 0.13,
"learning_rate": 9.830341646984521e-05,
"loss": 0.9878,
"step": 129000
},
{
"epoch": 0.13,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9992,
"step": 130000
},
{
"epoch": 0.13,
"learning_rate": 9.821694678938953e-05,
"loss": 0.9955,
"step": 131000
},
{
"epoch": 0.13,
"learning_rate": 9.817292077210659e-05,
"loss": 0.9978,
"step": 132000
},
{
"epoch": 0.13,
"learning_rate": 9.812836794348004e-05,
"loss": 0.9749,
"step": 133000
},
{
"epoch": 0.13,
"learning_rate": 9.808328879073251e-05,
"loss": 0.9934,
"step": 134000
},
{
"epoch": 0.14,
"learning_rate": 9.803768380684242e-05,
"loss": 1.0019,
"step": 135000
},
{
"epoch": 0.14,
"learning_rate": 9.799155349053851e-05,
"loss": 1.0112,
"step": 136000
},
{
"epoch": 0.14,
"learning_rate": 9.794489834629455e-05,
"loss": 1.0159,
"step": 137000
},
{
"epoch": 0.14,
"learning_rate": 9.789771888432375e-05,
"loss": 1.014,
"step": 138000
},
{
"epoch": 0.14,
"learning_rate": 9.785001562057309e-05,
"loss": 1.0078,
"step": 139000
},
{
"epoch": 0.14,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9941,
"step": 140000
},
{
"epoch": 0.14,
"learning_rate": 9.775303978015585e-05,
"loss": 0.9938,
"step": 141000
},
{
"epoch": 0.14,
"learning_rate": 9.77037682640015e-05,
"loss": 1.0001,
"step": 142000
},
{
"epoch": 0.14,
"learning_rate": 9.765397506708023e-05,
"loss": 0.9662,
"step": 143000
},
{
"epoch": 0.14,
"learning_rate": 9.760366073392246e-05,
"loss": 0.9678,
"step": 144000
},
{
"epoch": 0.14,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9225,
"step": 145000
},
{
"epoch": 0.15,
"learning_rate": 9.750147086550844e-05,
"loss": 0.9329,
"step": 146000
},
{
"epoch": 0.15,
"learning_rate": 9.744959644778422e-05,
"loss": 0.9361,
"step": 147000
},
{
"epoch": 0.15,
"learning_rate": 9.739720312887535e-05,
"loss": 0.9639,
"step": 148000
},
{
"epoch": 0.15,
"learning_rate": 9.734429148174675e-05,
"loss": 0.9647,
"step": 149000
},
{
"epoch": 0.15,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9401,
"step": 150000
},
{
"epoch": 0.15,
"eval_loss": 0.5351489782333374,
"eval_runtime": 114.2656,
"eval_samples_per_second": 43.758,
"eval_steps_per_second": 0.691,
"step": 150000
},
{
"epoch": 0.15,
"learning_rate": 9.723691552302562e-05,
"loss": 0.9502,
"step": 151000
},
{
"epoch": 0.15,
"learning_rate": 9.718245238567939e-05,
"loss": 0.9362,
"step": 152000
},
{
"epoch": 0.15,
"learning_rate": 9.712747326859315e-05,
"loss": 0.9531,
"step": 153000
},
{
"epoch": 0.15,
"learning_rate": 9.707197877300974e-05,
"loss": 0.9626,
"step": 154000
},
{
"epoch": 0.15,
"learning_rate": 9.701596950580806e-05,
"loss": 0.955,
"step": 155000
},
{
"epoch": 0.16,
"learning_rate": 9.695944607949649e-05,
"loss": 0.9344,
"step": 156000
},
{
"epoch": 0.16,
"learning_rate": 9.690240911220618e-05,
"loss": 0.9267,
"step": 157000
},
{
"epoch": 0.16,
"learning_rate": 9.684485922768422e-05,
"loss": 0.9607,
"step": 158000
},
{
"epoch": 0.16,
"learning_rate": 9.6786797055287e-05,
"loss": 0.9479,
"step": 159000
},
{
"epoch": 0.16,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9602,
"step": 160000
},
{
"epoch": 0.16,
"learning_rate": 9.66691383922964e-05,
"loss": 0.9737,
"step": 161000
},
{
"epoch": 0.16,
"learning_rate": 9.660954318839933e-05,
"loss": 0.9637,
"step": 162000
},
{
"epoch": 0.16,
"learning_rate": 9.654943827000548e-05,
"loss": 0.9698,
"step": 163000
},
{
"epoch": 0.16,
"learning_rate": 9.648882429441257e-05,
"loss": 0.9835,
"step": 164000
},
{
"epoch": 0.17,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9854,
"step": 165000
},
{
"epoch": 0.17,
"learning_rate": 9.636607182864827e-05,
"loss": 0.9767,
"step": 166000
},
{
"epoch": 0.17,
"learning_rate": 9.630393468087818e-05,
"loss": 0.9598,
"step": 167000
},
{
"epoch": 0.17,
"learning_rate": 9.624129116069694e-05,
"loss": 0.9528,
"step": 168000
},
{
"epoch": 0.17,
"learning_rate": 9.617814195316411e-05,
"loss": 0.9699,
"step": 169000
},
{
"epoch": 0.17,
"learning_rate": 9.611448774886924e-05,
"loss": 0.9765,
"step": 170000
},
{
"epoch": 0.17,
"learning_rate": 9.605032924392457e-05,
"loss": 0.9888,
"step": 171000
},
{
"epoch": 0.17,
"learning_rate": 9.598566713995718e-05,
"loss": 0.9903,
"step": 172000
},
{
"epoch": 0.17,
"learning_rate": 9.59205021441015e-05,
"loss": 0.9632,
"step": 173000
},
{
"epoch": 0.17,
"learning_rate": 9.58548349689915e-05,
"loss": 0.9534,
"step": 174000
},
{
"epoch": 0.17,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9648,
"step": 175000
},
{
"epoch": 0.18,
"learning_rate": 9.572199695899522e-05,
"loss": 0.9894,
"step": 176000
},
{
"epoch": 0.18,
"learning_rate": 9.565482757680415e-05,
"loss": 0.9711,
"step": 177000
},
{
"epoch": 0.18,
"learning_rate": 9.558715892073323e-05,
"loss": 0.9669,
"step": 178000
},
{
"epoch": 0.18,
"learning_rate": 9.551899173079607e-05,
"loss": 0.9216,
"step": 179000
},
{
"epoch": 0.18,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9517,
"step": 180000
},
{
"epoch": 0.18,
"learning_rate": 9.538116473662861e-05,
"loss": 0.9516,
"step": 181000
},
{
"epoch": 0.18,
"learning_rate": 9.531150643965223e-05,
"loss": 0.9794,
"step": 182000
},
{
"epoch": 0.18,
"learning_rate": 9.524135262330098e-05,
"loss": 0.9548,
"step": 183000
},
{
"epoch": 0.18,
"learning_rate": 9.517070405476575e-05,
"loss": 0.9328,
"step": 184000
},
{
"epoch": 0.18,
"learning_rate": 9.509956150664796e-05,
"loss": 0.9571,
"step": 185000
},
{
"epoch": 0.19,
"learning_rate": 9.502792575695112e-05,
"loss": 0.9703,
"step": 186000
},
{
"epoch": 0.19,
"learning_rate": 9.49557975890723e-05,
"loss": 0.9609,
"step": 187000
},
{
"epoch": 0.19,
"learning_rate": 9.488317779179361e-05,
"loss": 0.9635,
"step": 188000
},
{
"epoch": 0.19,
"learning_rate": 9.481006715927351e-05,
"loss": 0.9671,
"step": 189000
},
{
"epoch": 0.19,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9598,
"step": 190000
},
{
"epoch": 0.19,
"learning_rate": 9.46623765919727e-05,
"loss": 0.9272,
"step": 191000
},
{
"epoch": 0.19,
"learning_rate": 9.458779827231237e-05,
"loss": 0.9502,
"step": 192000
},
{
"epoch": 0.19,
"learning_rate": 9.451273234763371e-05,
"loss": 0.9504,
"step": 193000
},
{
"epoch": 0.19,
"learning_rate": 9.443717963884569e-05,
"loss": 0.9693,
"step": 194000
},
{
"epoch": 0.2,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9599,
"step": 195000
},
{
"epoch": 0.2,
"learning_rate": 9.428461717918511e-05,
"loss": 0.9589,
"step": 196000
},
{
"epoch": 0.2,
"learning_rate": 9.420760909671118e-05,
"loss": 0.9624,
"step": 197000
},
{
"epoch": 0.2,
"learning_rate": 9.413011756690685e-05,
"loss": 0.9649,
"step": 198000
},
{
"epoch": 0.2,
"learning_rate": 9.405214343720707e-05,
"loss": 0.9596,
"step": 199000
},
{
"epoch": 0.2,
"learning_rate": 9.397368756032445e-05,
"loss": 0.9602,
"step": 200000
},
{
"epoch": 0.2,
"eval_loss": 0.5083469748497009,
"eval_runtime": 94.1262,
"eval_samples_per_second": 53.12,
"eval_steps_per_second": 0.839,
"step": 200000
},
{
"epoch": 0.2,
"learning_rate": 9.389475079423988e-05,
"loss": 0.9702,
"step": 201000
},
{
"epoch": 0.2,
"learning_rate": 9.381533400219318e-05,
"loss": 0.9585,
"step": 202000
},
{
"epoch": 0.2,
"learning_rate": 9.373543805267368e-05,
"loss": 0.9457,
"step": 203000
},
{
"epoch": 0.2,
"learning_rate": 9.365506381941066e-05,
"loss": 0.9351,
"step": 204000
},
{
"epoch": 0.2,
"learning_rate": 9.357421218136386e-05,
"loss": 0.9504,
"step": 205000
},
{
"epoch": 0.21,
"learning_rate": 9.349288402271388e-05,
"loss": 0.9256,
"step": 206000
},
{
"epoch": 0.21,
"learning_rate": 9.341108023285238e-05,
"loss": 0.9405,
"step": 207000
},
{
"epoch": 0.21,
"learning_rate": 9.332880170637252e-05,
"loss": 0.9389,
"step": 208000
},
{
"epoch": 0.21,
"learning_rate": 9.32460493430591e-05,
"loss": 0.9298,
"step": 209000
},
{
"epoch": 0.21,
"learning_rate": 9.316282404787871e-05,
"loss": 0.9273,
"step": 210000
},
{
"epoch": 0.21,
"learning_rate": 9.30791267309698e-05,
"loss": 0.9418,
"step": 211000
},
{
"epoch": 0.21,
"learning_rate": 9.299495830763286e-05,
"loss": 0.9566,
"step": 212000
},
{
"epoch": 0.21,
"learning_rate": 9.291031969832026e-05,
"loss": 0.9473,
"step": 213000
},
{
"epoch": 0.21,
"learning_rate": 9.282521182862629e-05,
"loss": 0.9439,
"step": 214000
},
{
"epoch": 0.21,
"learning_rate": 9.273963562927695e-05,
"loss": 0.9234,
"step": 215000
},
{
"epoch": 0.22,
"learning_rate": 9.265359203611987e-05,
"loss": 0.9408,
"step": 216000
},
{
"epoch": 0.22,
"learning_rate": 9.256708199011401e-05,
"loss": 0.9456,
"step": 217000
},
{
"epoch": 0.22,
"learning_rate": 9.248010643731935e-05,
"loss": 0.9313,
"step": 218000
},
{
"epoch": 0.22,
"learning_rate": 9.239266632888659e-05,
"loss": 0.9471,
"step": 219000
},
{
"epoch": 0.22,
"learning_rate": 9.230476262104677e-05,
"loss": 0.9556,
"step": 220000
},
{
"epoch": 0.22,
"learning_rate": 9.221639627510076e-05,
"loss": 0.9346,
"step": 221000
},
{
"epoch": 0.22,
"learning_rate": 9.212756825740873e-05,
"loss": 0.935,
"step": 222000
},
{
"epoch": 0.22,
"learning_rate": 9.20382795393797e-05,
"loss": 0.9133,
"step": 223000
},
{
"epoch": 0.22,
"learning_rate": 9.194853109746074e-05,
"loss": 0.9247,
"step": 224000
},
{
"epoch": 0.23,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9093,
"step": 225000
},
{
"epoch": 0.23,
"learning_rate": 9.176765897286813e-05,
"loss": 0.8778,
"step": 226000
},
{
"epoch": 0.23,
"learning_rate": 9.167653726818305e-05,
"loss": 0.8794,
"step": 227000
},
{
"epoch": 0.23,
"learning_rate": 9.158495979556358e-05,
"loss": 0.9238,
"step": 228000
},
{
"epoch": 0.23,
"learning_rate": 9.14929275564863e-05,
"loss": 0.9351,
"step": 229000
},
{
"epoch": 0.23,
"learning_rate": 9.140044155740101e-05,
"loss": 0.9133,
"step": 230000
},
{
"epoch": 0.23,
"learning_rate": 9.130750280971978e-05,
"loss": 0.9197,
"step": 231000
},
{
"epoch": 0.23,
"learning_rate": 9.121411232980588e-05,
"loss": 0.9007,
"step": 232000
},
{
"epoch": 0.23,
"learning_rate": 9.112027113896262e-05,
"loss": 0.9314,
"step": 233000
},
{
"epoch": 0.23,
"learning_rate": 9.102598026342222e-05,
"loss": 0.9063,
"step": 234000
},
{
"epoch": 0.23,
"learning_rate": 9.093124073433463e-05,
"loss": 0.9354,
"step": 235000
},
{
"epoch": 0.24,
"learning_rate": 9.083605358775612e-05,
"loss": 0.9117,
"step": 236000
},
{
"epoch": 0.24,
"learning_rate": 9.074041986463808e-05,
"loss": 0.9286,
"step": 237000
},
{
"epoch": 0.24,
"learning_rate": 9.064434061081562e-05,
"loss": 0.9249,
"step": 238000
},
{
"epoch": 0.24,
"learning_rate": 9.0547816876996e-05,
"loss": 0.9108,
"step": 239000
},
{
"epoch": 0.24,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9427,
"step": 240000
},
{
"epoch": 0.24,
"learning_rate": 9.035344019648702e-05,
"loss": 0.9355,
"step": 241000
},
{
"epoch": 0.24,
"learning_rate": 9.025558937546988e-05,
"loss": 0.9375,
"step": 242000
},
{
"epoch": 0.24,
"learning_rate": 9.015729832577681e-05,
"loss": 0.9352,
"step": 243000
},
{
"epoch": 0.24,
"learning_rate": 9.005856812230304e-05,
"loss": 0.9345,
"step": 244000
},
{
"epoch": 0.24,
"learning_rate": 8.995939984474624e-05,
"loss": 0.9316,
"step": 245000
},
{
"epoch": 0.25,
"learning_rate": 8.98597945775948e-05,
"loss": 0.926,
"step": 246000
},
{
"epoch": 0.25,
"learning_rate": 8.975975341011596e-05,
"loss": 0.9067,
"step": 247000
},
{
"epoch": 0.25,
"learning_rate": 8.965927743634391e-05,
"loss": 0.8969,
"step": 248000
},
{
"epoch": 0.25,
"learning_rate": 8.955836775506776e-05,
"loss": 0.905,
"step": 249000
},
{
"epoch": 0.25,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8909,
"step": 250000
},
{
"epoch": 0.25,
"eval_loss": 0.4992561936378479,
"eval_runtime": 109.4818,
"eval_samples_per_second": 45.67,
"eval_steps_per_second": 0.722,
"step": 250000
},
{
"epoch": 0.25,
"learning_rate": 8.935525168886262e-05,
"loss": 0.9224,
"step": 251000
},
{
"epoch": 0.25,
"learning_rate": 8.92530475251784e-05,
"loss": 0.9001,
"step": 252000
},
{
"epoch": 0.25,
"learning_rate": 8.91504140964553e-05,
"loss": 0.9038,
"step": 253000
},
{
"epoch": 0.25,
"learning_rate": 8.90473525250761e-05,
"loss": 0.9049,
"step": 254000
},
{
"epoch": 0.26,
"learning_rate": 8.894386393810563e-05,
"loss": 0.9038,
"step": 255000
},
{
"epoch": 0.26,
"learning_rate": 8.883994946727849e-05,
"loss": 0.9287,
"step": 256000
},
{
"epoch": 0.26,
"learning_rate": 8.873561024898668e-05,
"loss": 0.936,
"step": 257000
},
{
"epoch": 0.26,
"learning_rate": 8.863084742426719e-05,
"loss": 0.9456,
"step": 258000
},
{
"epoch": 0.26,
"learning_rate": 8.852566213878947e-05,
"loss": 0.9164,
"step": 259000
},
{
"epoch": 0.26,
"learning_rate": 8.842005554284296e-05,
"loss": 0.9266,
"step": 260000
},
{
"epoch": 0.26,
"learning_rate": 8.831402879132446e-05,
"loss": 0.8984,
"step": 261000
},
{
"epoch": 0.26,
"learning_rate": 8.820758304372557e-05,
"loss": 0.9258,
"step": 262000
},
{
"epoch": 0.26,
"learning_rate": 8.810071946411989e-05,
"loss": 0.9244,
"step": 263000
},
{
"epoch": 0.26,
"learning_rate": 8.799343922115044e-05,
"loss": 0.9394,
"step": 264000
},
{
"epoch": 0.27,
"learning_rate": 8.788574348801675e-05,
"loss": 0.9374,
"step": 265000
},
{
"epoch": 0.27,
"learning_rate": 8.77776334424621e-05,
"loss": 0.9406,
"step": 266000
},
{
"epoch": 0.27,
"learning_rate": 8.766911026676064e-05,
"loss": 0.939,
"step": 267000
},
{
"epoch": 0.27,
"learning_rate": 8.756017514770443e-05,
"loss": 0.9367,
"step": 268000
},
{
"epoch": 0.27,
"learning_rate": 8.745082927659047e-05,
"loss": 0.9334,
"step": 269000
},
{
"epoch": 0.27,
"learning_rate": 8.73410738492077e-05,
"loss": 0.9112,
"step": 270000
},
{
"epoch": 0.27,
"learning_rate": 8.723091006582389e-05,
"loss": 0.9138,
"step": 271000
},
{
"epoch": 0.27,
"learning_rate": 8.71203391311725e-05,
"loss": 0.9107,
"step": 272000
},
{
"epoch": 0.27,
"learning_rate": 8.700936225443959e-05,
"loss": 0.8952,
"step": 273000
},
{
"epoch": 0.27,
"learning_rate": 8.689798064925049e-05,
"loss": 0.9094,
"step": 274000
},
{
"epoch": 0.28,
"learning_rate": 8.678619553365659e-05,
"loss": 0.9174,
"step": 275000
},
{
"epoch": 0.28,
"learning_rate": 8.6674008130122e-05,
"loss": 0.9266,
"step": 276000
},
{
"epoch": 0.28,
"learning_rate": 8.656141966551019e-05,
"loss": 0.8974,
"step": 277000
},
{
"epoch": 0.28,
"learning_rate": 8.644843137107059e-05,
"loss": 0.906,
"step": 278000
},
{
"epoch": 0.28,
"learning_rate": 8.633504448242505e-05,
"loss": 0.8943,
"step": 279000
},
{
"epoch": 0.28,
"learning_rate": 8.622126023955446e-05,
"loss": 0.8919,
"step": 280000
},
{
"epoch": 0.28,
"learning_rate": 8.610707988678503e-05,
"loss": 0.9139,
"step": 281000
},
{
"epoch": 0.28,
"learning_rate": 8.599250467277483e-05,
"loss": 0.9123,
"step": 282000
},
{
"epoch": 0.28,
"learning_rate": 8.587753585050004e-05,
"loss": 0.9071,
"step": 283000
},
{
"epoch": 0.28,
"learning_rate": 8.576217467724128e-05,
"loss": 0.8988,
"step": 284000
},
{
"epoch": 0.28,
"learning_rate": 8.564642241456986e-05,
"loss": 0.8992,
"step": 285000
},
{
"epoch": 0.29,
"learning_rate": 8.553028032833397e-05,
"loss": 0.8935,
"step": 286000
},
{
"epoch": 0.29,
"learning_rate": 8.541374968864487e-05,
"loss": 0.8905,
"step": 287000
},
{
"epoch": 0.29,
"learning_rate": 8.529683176986295e-05,
"loss": 0.8939,
"step": 288000
},
{
"epoch": 0.29,
"learning_rate": 8.517952785058385e-05,
"loss": 0.887,
"step": 289000
},
{
"epoch": 0.29,
"learning_rate": 8.506183921362443e-05,
"loss": 0.9061,
"step": 290000
},
{
"epoch": 0.29,
"learning_rate": 8.494376714600878e-05,
"loss": 0.9229,
"step": 291000
},
{
"epoch": 0.29,
"learning_rate": 8.482531293895412e-05,
"loss": 0.9109,
"step": 292000
},
{
"epoch": 0.29,
"learning_rate": 8.470647788785665e-05,
"loss": 0.9066,
"step": 293000
},
{
"epoch": 0.29,
"learning_rate": 8.458726329227747e-05,
"loss": 0.9235,
"step": 294000
},
{
"epoch": 0.29,
"learning_rate": 8.44676704559283e-05,
"loss": 0.9373,
"step": 295000
},
{
"epoch": 0.3,
"learning_rate": 8.434770068665723e-05,
"loss": 0.9142,
"step": 296000
},
{
"epoch": 0.3,
"learning_rate": 8.422735529643444e-05,
"loss": 0.9029,
"step": 297000
},
{
"epoch": 0.3,
"learning_rate": 8.410663560133784e-05,
"loss": 0.9235,
"step": 298000
},
{
"epoch": 0.3,
"learning_rate": 8.398554292153866e-05,
"loss": 0.9367,
"step": 299000
},
{
"epoch": 0.3,
"learning_rate": 8.386407858128706e-05,
"loss": 0.9122,
"step": 300000
},
{
"epoch": 0.3,
"eval_loss": 0.4920811951160431,
"eval_runtime": 74.5828,
"eval_samples_per_second": 67.04,
"eval_steps_per_second": 1.059,
"step": 300000
},
{
"epoch": 0.3,
"learning_rate": 8.37422439088976e-05,
"loss": 0.8926,
"step": 301000
},
{
"epoch": 0.3,
"learning_rate": 8.362004023673474e-05,
"loss": 0.8974,
"step": 302000
},
{
"epoch": 0.3,
"learning_rate": 8.349746890119826e-05,
"loss": 0.915,
"step": 303000
},
{
"epoch": 0.3,
"learning_rate": 8.337453124270863e-05,
"loss": 0.9294,
"step": 304000
},
{
"epoch": 0.3,
"learning_rate": 8.32512286056924e-05,
"loss": 0.9211,
"step": 305000
},
{
"epoch": 0.31,
"learning_rate": 8.31275623385675e-05,
"loss": 0.9044,
"step": 306000
},
{
"epoch": 0.31,
"learning_rate": 8.300353379372834e-05,
"loss": 0.8952,
"step": 307000
},
{
"epoch": 0.31,
"learning_rate": 8.287914432753123e-05,
"loss": 0.8818,
"step": 308000
},
{
"epoch": 0.31,
"learning_rate": 8.275439530027948e-05,
"loss": 0.869,
"step": 309000
},
{
"epoch": 0.31,
"learning_rate": 8.262928807620843e-05,
"loss": 0.891,
"step": 310000
},
{
"epoch": 0.31,
"learning_rate": 8.250382402347065e-05,
"loss": 0.8834,
"step": 311000
},
{
"epoch": 0.31,
"learning_rate": 8.237800451412095e-05,
"loss": 0.8918,
"step": 312000
},
{
"epoch": 0.31,
"learning_rate": 8.225183092410128e-05,
"loss": 0.8745,
"step": 313000
},
{
"epoch": 0.31,
"learning_rate": 8.212530463322583e-05,
"loss": 0.8662,
"step": 314000
},
{
"epoch": 0.32,
"learning_rate": 8.199842702516583e-05,
"loss": 0.8949,
"step": 315000
},
{
"epoch": 0.32,
"learning_rate": 8.18711994874345e-05,
"loss": 0.866,
"step": 316000
},
{
"epoch": 0.32,
"learning_rate": 8.174362341137177e-05,
"loss": 0.8971,
"step": 317000
},
{
"epoch": 0.32,
"learning_rate": 8.161570019212921e-05,
"loss": 0.8932,
"step": 318000
},
{
"epoch": 0.32,
"learning_rate": 8.148743122865463e-05,
"loss": 0.8679,
"step": 319000
},
{
"epoch": 0.32,
"learning_rate": 8.135881792367686e-05,
"loss": 0.8766,
"step": 320000
},
{
"epoch": 0.32,
"learning_rate": 8.12298616836904e-05,
"loss": 0.8815,
"step": 321000
},
{
"epoch": 0.32,
"learning_rate": 8.110056391894005e-05,
"loss": 0.8995,
"step": 322000
},
{
"epoch": 0.32,
"learning_rate": 8.097092604340542e-05,
"loss": 0.8812,
"step": 323000
},
{
"epoch": 0.32,
"learning_rate": 8.084094947478556e-05,
"loss": 0.8872,
"step": 324000
},
{
"epoch": 0.33,
"learning_rate": 8.07106356344834e-05,
"loss": 0.8947,
"step": 325000
},
{
"epoch": 0.33,
"learning_rate": 8.057998594759022e-05,
"loss": 0.911,
"step": 326000
},
{
"epoch": 0.33,
"learning_rate": 8.044900184287007e-05,
"loss": 0.8999,
"step": 327000
},
{
"epoch": 0.33,
"learning_rate": 8.031768475274413e-05,
"loss": 0.9137,
"step": 328000
},
{
"epoch": 0.33,
"learning_rate": 8.018603611327504e-05,
"loss": 0.9123,
"step": 329000
},
{
"epoch": 0.33,
"learning_rate": 8.005405736415126e-05,
"loss": 0.9004,
"step": 330000
},
{
"epoch": 0.33,
"learning_rate": 7.992174994867123e-05,
"loss": 0.8825,
"step": 331000
},
{
"epoch": 0.33,
"learning_rate": 7.978911531372765e-05,
"loss": 0.8701,
"step": 332000
},
{
"epoch": 0.33,
"learning_rate": 7.965615490979163e-05,
"loss": 0.8749,
"step": 333000
},
{
"epoch": 0.33,
"learning_rate": 7.952287019089685e-05,
"loss": 0.9012,
"step": 334000
},
{
"epoch": 0.34,
"learning_rate": 7.938926261462366e-05,
"loss": 0.8906,
"step": 335000
},
{
"epoch": 0.34,
"learning_rate": 7.925533364208309e-05,
"loss": 0.871,
"step": 336000
},
{
"epoch": 0.34,
"learning_rate": 7.912108473790092e-05,
"loss": 0.8837,
"step": 337000
},
{
"epoch": 0.34,
"learning_rate": 7.898651737020166e-05,
"loss": 0.8889,
"step": 338000
},
{
"epoch": 0.34,
"learning_rate": 7.88516330105925e-05,
"loss": 0.9053,
"step": 339000
},
{
"epoch": 0.34,
"learning_rate": 7.871643313414718e-05,
"loss": 0.9101,
"step": 340000
},
{
"epoch": 0.34,
"learning_rate": 7.858091921938988e-05,
"loss": 0.8979,
"step": 341000
},
{
"epoch": 0.34,
"learning_rate": 7.844509274827907e-05,
"loss": 0.8884,
"step": 342000
},
{
"epoch": 0.34,
"learning_rate": 7.830895520619128e-05,
"loss": 0.8808,
"step": 343000
},
{
"epoch": 0.34,
"learning_rate": 7.817250808190483e-05,
"loss": 0.873,
"step": 344000
},
{
"epoch": 0.34,
"learning_rate": 7.803575286758364e-05,
"loss": 0.8673,
"step": 345000
},
{
"epoch": 0.35,
"learning_rate": 7.789869105876083e-05,
"loss": 0.8555,
"step": 346000
},
{
"epoch": 0.35,
"learning_rate": 7.776132415432234e-05,
"loss": 0.8382,
"step": 347000
},
{
"epoch": 0.35,
"learning_rate": 7.762365365649067e-05,
"loss": 0.8518,
"step": 348000
},
{
"epoch": 0.35,
"learning_rate": 7.748568107080832e-05,
"loss": 0.8367,
"step": 349000
},
{
"epoch": 0.35,
"learning_rate": 7.734740790612136e-05,
"loss": 0.8172,
"step": 350000
},
{
"epoch": 0.35,
"eval_loss": 0.4771507680416107,
"eval_runtime": 58.0784,
"eval_samples_per_second": 86.09,
"eval_steps_per_second": 1.36,
"step": 350000
},
{
"epoch": 0.35,
"learning_rate": 7.720883567456298e-05,
"loss": 0.8479,
"step": 351000
},
{
"epoch": 0.35,
"learning_rate": 7.70699658915369e-05,
"loss": 0.8582,
"step": 352000
},
{
"epoch": 0.35,
"learning_rate": 7.693080007570084e-05,
"loss": 0.8729,
"step": 353000
},
{
"epoch": 0.35,
"learning_rate": 7.679133974894983e-05,
"loss": 0.8367,
"step": 354000
},
{
"epoch": 0.35,
"learning_rate": 7.66515864363997e-05,
"loss": 0.8272,
"step": 355000
},
{
"epoch": 0.36,
"learning_rate": 7.651154166637025e-05,
"loss": 0.8526,
"step": 356000
},
{
"epoch": 0.36,
"learning_rate": 7.637120697036866e-05,
"loss": 0.8495,
"step": 357000
},
{
"epoch": 0.36,
"learning_rate": 7.623058388307269e-05,
"loss": 0.8268,
"step": 358000
},
{
"epoch": 0.36,
"learning_rate": 7.608967394231387e-05,
"loss": 0.8643,
"step": 359000
},
{
"epoch": 0.36,
"learning_rate": 7.594847868906076e-05,
"loss": 0.8786,
"step": 360000
},
{
"epoch": 0.36,
"learning_rate": 7.580699966740201e-05,
"loss": 0.8769,
"step": 361000
},
{
"epoch": 0.36,
"learning_rate": 7.566523842452958e-05,
"loss": 0.8755,
"step": 362000
},
{
"epoch": 0.36,
"learning_rate": 7.552319651072164e-05,
"loss": 0.8843,
"step": 363000
},
{
"epoch": 0.36,
"learning_rate": 7.538087547932585e-05,
"loss": 0.8797,
"step": 364000
},
{
"epoch": 0.36,
"learning_rate": 7.52382768867422e-05,
"loss": 0.8719,
"step": 365000
},
{
"epoch": 0.37,
"learning_rate": 7.509540229240601e-05,
"loss": 0.8725,
"step": 366000
},
{
"epoch": 0.37,
"learning_rate": 7.495225325877103e-05,
"loss": 0.874,
"step": 367000
},
{
"epoch": 0.37,
"learning_rate": 7.480883135129211e-05,
"loss": 0.8795,
"step": 368000
},
{
"epoch": 0.37,
"learning_rate": 7.466513813840825e-05,
"loss": 0.8986,
"step": 369000
},
{
"epoch": 0.37,
"learning_rate": 7.452117519152542e-05,
"loss": 0.8921,
"step": 370000
},
{
"epoch": 0.37,
"learning_rate": 7.437694408499933e-05,
"loss": 0.8985,
"step": 371000
},
{
"epoch": 0.37,
"learning_rate": 7.423244639611826e-05,
"loss": 0.8932,
"step": 372000
},
{
"epoch": 0.37,
"learning_rate": 7.408768370508576e-05,
"loss": 0.9084,
"step": 373000
},
{
"epoch": 0.37,
"learning_rate": 7.394265759500348e-05,
"loss": 0.891,
"step": 374000
},
{
"epoch": 0.38,
"learning_rate": 7.379736965185368e-05,
"loss": 0.8804,
"step": 375000
},
{
"epoch": 0.38,
"learning_rate": 7.365182146448205e-05,
"loss": 0.8703,
"step": 376000
},
{
"epoch": 0.38,
"learning_rate": 7.350601462458024e-05,
"loss": 0.8582,
"step": 377000
},
{
"epoch": 0.38,
"learning_rate": 7.335995072666848e-05,
"loss": 0.8407,
"step": 378000
},
{
"epoch": 0.38,
"learning_rate": 7.32136313680782e-05,
"loss": 0.854,
"step": 379000
},
{
"epoch": 0.38,
"learning_rate": 7.30670581489344e-05,
"loss": 0.8649,
"step": 380000
},
{
"epoch": 0.38,
"learning_rate": 7.292023267213835e-05,
"loss": 0.854,
"step": 381000
},
{
"epoch": 0.38,
"learning_rate": 7.277315654334997e-05,
"loss": 0.8608,
"step": 382000
},
{
"epoch": 0.38,
"learning_rate": 7.262583137097018e-05,
"loss": 0.8471,
"step": 383000
},
{
"epoch": 0.38,
"learning_rate": 7.247825876612353e-05,
"loss": 0.8422,
"step": 384000
},
{
"epoch": 0.39,
"learning_rate": 7.233044034264034e-05,
"loss": 0.8405,
"step": 385000
},
{
"epoch": 0.39,
"learning_rate": 7.218237771703921e-05,
"loss": 0.8088,
"step": 386000
},
{
"epoch": 0.39,
"learning_rate": 7.203407250850928e-05,
"loss": 0.825,
"step": 387000
},
{
"epoch": 0.39,
"learning_rate": 7.188552633889259e-05,
"loss": 0.8299,
"step": 388000
},
{
"epoch": 0.39,
"learning_rate": 7.173674083266624e-05,
"loss": 0.8264,
"step": 389000
},
{
"epoch": 0.39,
"learning_rate": 7.158771761692464e-05,
"loss": 0.8145,
"step": 390000
},
{
"epoch": 0.39,
"learning_rate": 7.143845832136188e-05,
"loss": 0.8398,
"step": 391000
},
{
"epoch": 0.39,
"learning_rate": 7.128896457825364e-05,
"loss": 0.8496,
"step": 392000
},
{
"epoch": 0.39,
"learning_rate": 7.113923802243957e-05,
"loss": 0.8582,
"step": 393000
},
{
"epoch": 0.39,
"learning_rate": 7.09892802913053e-05,
"loss": 0.8667,
"step": 394000
},
{
"epoch": 0.4,
"learning_rate": 7.083909302476453e-05,
"loss": 0.8591,
"step": 395000
},
{
"epoch": 0.4,
"learning_rate": 7.068867786524116e-05,
"loss": 0.8623,
"step": 396000
},
{
"epoch": 0.4,
"learning_rate": 7.053803645765128e-05,
"loss": 0.8359,
"step": 397000
},
{
"epoch": 0.4,
"learning_rate": 7.038717044938519e-05,
"loss": 0.8499,
"step": 398000
},
{
"epoch": 0.4,
"learning_rate": 7.023608149028937e-05,
"loss": 0.8445,
"step": 399000
},
{
"epoch": 0.4,
"learning_rate": 7.008477123264848e-05,
"loss": 0.8213,
"step": 400000
},
{
"epoch": 0.4,
"eval_loss": 0.45939022302627563,
"eval_runtime": 195.195,
"eval_samples_per_second": 25.615,
"eval_steps_per_second": 0.405,
"step": 400000
},
{
"epoch": 0.4,
"learning_rate": 6.993324133116726e-05,
"loss": 0.8436,
"step": 401000
},
{
"epoch": 0.4,
"learning_rate": 6.978149344295242e-05,
"loss": 0.837,
"step": 402000
},
{
"epoch": 0.4,
"learning_rate": 6.962952922749457e-05,
"loss": 0.846,
"step": 403000
},
{
"epoch": 0.4,
"learning_rate": 6.947735034665002e-05,
"loss": 0.8244,
"step": 404000
},
{
"epoch": 0.41,
"learning_rate": 6.932495846462261e-05,
"loss": 0.8232,
"step": 405000
},
{
"epoch": 0.41,
"learning_rate": 6.917235524794558e-05,
"loss": 0.8376,
"step": 406000
},
{
"epoch": 0.41,
"learning_rate": 6.901954236546323e-05,
"loss": 0.8296,
"step": 407000
},
{
"epoch": 0.41,
"learning_rate": 6.886652148831279e-05,
"loss": 0.839,
"step": 408000
},
{
"epoch": 0.41,
"learning_rate": 6.871329428990602e-05,
"loss": 0.8564,
"step": 409000
},
{
"epoch": 0.41,
"learning_rate": 6.855986244591104e-05,
"loss": 0.8704,
"step": 410000
},
{
"epoch": 0.41,
"learning_rate": 6.840622763423391e-05,
"loss": 0.847,
"step": 411000
},
{
"epoch": 0.41,
"learning_rate": 6.825239153500029e-05,
"loss": 0.8419,
"step": 412000
},
{
"epoch": 0.41,
"learning_rate": 6.809835583053715e-05,
"loss": 0.8467,
"step": 413000
},
{
"epoch": 0.41,
"learning_rate": 6.794412220535426e-05,
"loss": 0.8624,
"step": 414000
},
{
"epoch": 0.41,
"learning_rate": 6.778969234612584e-05,
"loss": 0.8592,
"step": 415000
},
{
"epoch": 0.42,
"learning_rate": 6.763506794167208e-05,
"loss": 0.8656,
"step": 416000
},
{
"epoch": 0.42,
"learning_rate": 6.748025068294067e-05,
"loss": 0.8455,
"step": 417000
},
{
"epoch": 0.42,
"learning_rate": 6.732524226298841e-05,
"loss": 0.8579,
"step": 418000
},
{
"epoch": 0.42,
"learning_rate": 6.71700443769625e-05,
"loss": 0.8402,
"step": 419000
},
{
"epoch": 0.42,
"learning_rate": 6.701465872208216e-05,
"loss": 0.8468,
"step": 420000
},
{
"epoch": 0.42,
"learning_rate": 6.685908699762002e-05,
"loss": 0.8411,
"step": 421000
},
{
"epoch": 0.42,
"learning_rate": 6.670333090488356e-05,
"loss": 0.8521,
"step": 422000
},
{
"epoch": 0.42,
"learning_rate": 6.654739214719641e-05,
"loss": 0.843,
"step": 423000
},
{
"epoch": 0.42,
"learning_rate": 6.639127242987988e-05,
"loss": 0.8347,
"step": 424000
},
{
"epoch": 0.42,
"learning_rate": 6.623497346023418e-05,
"loss": 0.8391,
"step": 425000
},
{
"epoch": 0.43,
"learning_rate": 6.607849694751977e-05,
"loss": 0.8606,
"step": 426000
},
{
"epoch": 0.43,
"learning_rate": 6.592184460293877e-05,
"loss": 0.8756,
"step": 427000
},
{
"epoch": 0.43,
"learning_rate": 6.576501813961609e-05,
"loss": 0.89,
"step": 428000
},
{
"epoch": 0.43,
"learning_rate": 6.56080192725808e-05,
"loss": 0.8687,
"step": 429000
},
{
"epoch": 0.43,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8715,
"step": 430000
},
{
"epoch": 0.43,
"learning_rate": 6.529351119689688e-05,
"loss": 0.8797,
"step": 431000
},
{
"epoch": 0.43,
"learning_rate": 6.513600542765817e-05,
"loss": 0.8833,
"step": 432000
},
{
"epoch": 0.43,
"learning_rate": 6.497833413348909e-05,
"loss": 0.8757,
"step": 433000
},
{
"epoch": 0.43,
"learning_rate": 6.48204990386577e-05,
"loss": 0.8763,
"step": 434000
},
{
"epoch": 0.43,
"learning_rate": 6.466250186922325e-05,
"loss": 0.8587,
"step": 435000
},
{
"epoch": 0.44,
"learning_rate": 6.450434435301751e-05,
"loss": 0.8364,
"step": 436000
},
{
"epoch": 0.44,
"learning_rate": 6.43460282196257e-05,
"loss": 0.8597,
"step": 437000
},
{
"epoch": 0.44,
"learning_rate": 6.418755520036775e-05,
"loss": 0.8276,
"step": 438000
},
{
"epoch": 0.44,
"learning_rate": 6.402892702827916e-05,
"loss": 0.844,
"step": 439000
},
{
"epoch": 0.44,
"learning_rate": 6.387014543809223e-05,
"loss": 0.8257,
"step": 440000
},
{
"epoch": 0.44,
"learning_rate": 6.371121216621698e-05,
"loss": 0.8268,
"step": 441000
},
{
"epoch": 0.44,
"learning_rate": 6.355212895072223e-05,
"loss": 0.8533,
"step": 442000
},
{
"epoch": 0.44,
"learning_rate": 6.339289753131649e-05,
"loss": 0.8188,
"step": 443000
},
{
"epoch": 0.44,
"learning_rate": 6.323351964932908e-05,
"loss": 0.8319,
"step": 444000
},
{
"epoch": 0.45,
"learning_rate": 6.307399704769099e-05,
"loss": 0.8183,
"step": 445000
},
{
"epoch": 0.45,
"learning_rate": 6.291433147091583e-05,
"loss": 0.8307,
"step": 446000
},
{
"epoch": 0.45,
"learning_rate": 6.275452466508077e-05,
"loss": 0.8195,
"step": 447000
},
{
"epoch": 0.45,
"learning_rate": 6.259457837780742e-05,
"loss": 0.8038,
"step": 448000
},
{
"epoch": 0.45,
"learning_rate": 6.243449435824276e-05,
"loss": 0.8302,
"step": 449000
},
{
"epoch": 0.45,
"learning_rate": 6.227427435703997e-05,
"loss": 0.7914,
"step": 450000
},
{
"epoch": 0.45,
"eval_loss": 0.4447863698005676,
"eval_runtime": 172.7185,
"eval_samples_per_second": 28.949,
"eval_steps_per_second": 0.457,
"step": 450000
},
{
"epoch": 0.45,
"learning_rate": 6.211392012633932e-05,
"loss": 0.7888,
"step": 451000
},
{
"epoch": 0.45,
"learning_rate": 6.195343341974899e-05,
"loss": 0.8002,
"step": 452000
},
{
"epoch": 0.45,
"learning_rate": 6.179281599232591e-05,
"loss": 0.7938,
"step": 453000
},
{
"epoch": 0.45,
"learning_rate": 6.163206960055651e-05,
"loss": 0.7864,
"step": 454000
},
{
"epoch": 0.46,
"learning_rate": 6.147119600233758e-05,
"loss": 0.8025,
"step": 455000
},
{
"epoch": 0.46,
"learning_rate": 6.131019695695702e-05,
"loss": 0.8224,
"step": 456000
},
{
"epoch": 0.46,
"learning_rate": 6.11490742250746e-05,
"loss": 0.8384,
"step": 457000
},
{
"epoch": 0.46,
"learning_rate": 6.0987829568702656e-05,
"loss": 0.807,
"step": 458000
},
{
"epoch": 0.46,
"learning_rate": 6.0826464751186994e-05,
"loss": 0.8323,
"step": 459000
},
{
"epoch": 0.46,
"learning_rate": 6.066498153718735e-05,
"loss": 0.845,
"step": 460000
},
{
"epoch": 0.46,
"learning_rate": 6.05033816926583e-05,
"loss": 0.8375,
"step": 461000
},
{
"epoch": 0.46,
"learning_rate": 6.034166698482984e-05,
"loss": 0.8422,
"step": 462000
},
{
"epoch": 0.46,
"learning_rate": 6.017983918218812e-05,
"loss": 0.8198,
"step": 463000
},
{
"epoch": 0.46,
"learning_rate": 6.001790005445607e-05,
"loss": 0.8176,
"step": 464000
},
{
"epoch": 0.47,
"learning_rate": 5.985585137257401e-05,
"loss": 0.8111,
"step": 465000
},
{
"epoch": 0.47,
"learning_rate": 5.969369490868042e-05,
"loss": 0.8123,
"step": 466000
},
{
"epoch": 0.47,
"learning_rate": 5.953143243609235e-05,
"loss": 0.8316,
"step": 467000
},
{
"epoch": 0.47,
"learning_rate": 5.9369065729286245e-05,
"loss": 0.8368,
"step": 468000
},
{
"epoch": 0.47,
"learning_rate": 5.9206596563878357e-05,
"loss": 0.8285,
"step": 469000
},
{
"epoch": 0.47,
"learning_rate": 5.90440267166055e-05,
"loss": 0.8192,
"step": 470000
},
{
"epoch": 0.47,
"learning_rate": 5.888135796530544e-05,
"loss": 0.8198,
"step": 471000
},
{
"epoch": 0.47,
"learning_rate": 5.871859208889759e-05,
"loss": 0.8311,
"step": 472000
},
{
"epoch": 0.47,
"learning_rate": 5.85557308673635e-05,
"loss": 0.8473,
"step": 473000
},
{
"epoch": 0.47,
"learning_rate": 5.8392776081727385e-05,
"loss": 0.8549,
"step": 474000
},
{
"epoch": 0.47,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.8519,
"step": 475000
},
{
"epoch": 0.48,
"learning_rate": 5.8066592947342555e-05,
"loss": 0.8408,
"step": 476000
},
{
"epoch": 0.48,
"learning_rate": 5.7903368165680327e-05,
"loss": 0.8472,
"step": 477000
},
{
"epoch": 0.48,
"learning_rate": 5.7740056954050084e-05,
"loss": 0.8396,
"step": 478000
},
{
"epoch": 0.48,
"learning_rate": 5.757666109839702e-05,
"loss": 0.8495,
"step": 479000
},
{
"epoch": 0.48,
"learning_rate": 5.74131823855921e-05,
"loss": 0.8564,
"step": 480000
},
{
"epoch": 0.48,
"learning_rate": 5.72496226034123e-05,
"loss": 0.8477,
"step": 481000
},
{
"epoch": 0.48,
"learning_rate": 5.7085983540521216e-05,
"loss": 0.8278,
"step": 482000
},
{
"epoch": 0.48,
"learning_rate": 5.692226698644938e-05,
"loss": 0.8158,
"step": 483000
},
{
"epoch": 0.48,
"learning_rate": 5.675847473157485e-05,
"loss": 0.8341,
"step": 484000
},
{
"epoch": 0.48,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.8221,
"step": 485000
},
{
"epoch": 0.49,
"learning_rate": 5.6430670285049314e-05,
"loss": 0.8198,
"step": 486000
},
{
"epoch": 0.49,
"learning_rate": 5.6266661678215216e-05,
"loss": 0.8179,
"step": 487000
},
{
"epoch": 0.49,
"learning_rate": 5.6102584540173006e-05,
"loss": 0.819,
"step": 488000
},
{
"epoch": 0.49,
"learning_rate": 5.5938440665244006e-05,
"loss": 0.8216,
"step": 489000
},
{
"epoch": 0.49,
"learning_rate": 5.577423184847932e-05,
"loss": 0.8255,
"step": 490000
},
{
"epoch": 0.49,
"learning_rate": 5.560995988564023e-05,
"loss": 0.7989,
"step": 491000
},
{
"epoch": 0.49,
"learning_rate": 5.544562657317863e-05,
"loss": 0.7775,
"step": 492000
},
{
"epoch": 0.49,
"learning_rate": 5.52812337082173e-05,
"loss": 0.7598,
"step": 493000
},
{
"epoch": 0.49,
"learning_rate": 5.511678308853026e-05,
"loss": 0.7806,
"step": 494000
},
{
"epoch": 0.49,
"learning_rate": 5.495227651252315e-05,
"loss": 0.7533,
"step": 495000
},
{
"epoch": 0.5,
"learning_rate": 5.478771577921351e-05,
"loss": 0.8046,
"step": 496000
},
{
"epoch": 0.5,
"learning_rate": 5.462310268821118e-05,
"loss": 0.7926,
"step": 497000
},
{
"epoch": 0.5,
"learning_rate": 5.445843903969854e-05,
"loss": 0.7922,
"step": 498000
},
{
"epoch": 0.5,
"learning_rate": 5.4293726634410855e-05,
"loss": 0.8191,
"step": 499000
},
{
"epoch": 0.5,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.791,
"step": 500000
},
{
"epoch": 0.5,
"eval_loss": 0.4306029677391052,
"eval_runtime": 170.2109,
"eval_samples_per_second": 29.375,
"eval_steps_per_second": 0.464,
"step": 500000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 2.9834386341888e+19,
"trial_name": null,
"trial_params": null
}