joelniklaus's picture
Training in progress, step 300000
2f9df8a
raw history blame
No virus
37.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3,
"global_step": 300000,
"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": 4.7524,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 3.5548,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 2.9636,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 2.7618,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 2.6257,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 2.5517,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.4628,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.4338,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 2.3362,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 2.2746,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.1795,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 2.2309,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.8605,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.7232,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.6872,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.1581,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.0653,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 2.049,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 2.0773,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 1.9397,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 1.8899,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.8474,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 1.8034,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 1.7666,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 1.7899,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.4265,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.3535,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.1703,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.129,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.2811,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 1.2189,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.4371,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.3551,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3616,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 1.2483,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 1.2174,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 1.1861,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 1.1465,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 1.1957,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.136,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 1.1122,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 1.0905,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 1.0996,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 1.0632,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 1.1387,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 1.2049,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 1.1783,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 1.1043,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 1.0633,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.1331,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.753776490688324,
"eval_runtime": 33.8225,
"eval_samples_per_second": 147.83,
"eval_steps_per_second": 2.336,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 1.0509,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 1.2048,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 1.2837,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 1.1458,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 1.0255,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 1.2046,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 0.9363,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 0.6931,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 0.7802,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 1.0542,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 1.1069,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 1.0202,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 1.0179,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 1.0872,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0288,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 1.0054,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 1.0455,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 0.9996,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 1.0668,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 0.993,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 1.0315,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 1.0934,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 0.9016,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 1.0367,
"step": 74000
},
{
"epoch": 0.07,
"learning_rate": 9.98292246503335e-05,
"loss": 0.9656,
"step": 75000
},
{
"epoch": 0.08,
"learning_rate": 9.981529796748134e-05,
"loss": 1.1794,
"step": 76000
},
{
"epoch": 0.08,
"learning_rate": 9.980082651251175e-05,
"loss": 1.0076,
"step": 77000
},
{
"epoch": 0.08,
"learning_rate": 9.97858104436822e-05,
"loss": 1.038,
"step": 78000
},
{
"epoch": 0.08,
"learning_rate": 9.977024992520602e-05,
"loss": 1.1324,
"step": 79000
},
{
"epoch": 0.08,
"learning_rate": 9.975414512725057e-05,
"loss": 0.9674,
"step": 80000
},
{
"epoch": 0.08,
"learning_rate": 9.973749622593534e-05,
"loss": 0.9536,
"step": 81000
},
{
"epoch": 0.08,
"learning_rate": 9.972030340333001e-05,
"loss": 0.9515,
"step": 82000
},
{
"epoch": 0.08,
"learning_rate": 9.970256684745258e-05,
"loss": 1.0164,
"step": 83000
},
{
"epoch": 0.08,
"learning_rate": 9.968428675226714e-05,
"loss": 0.9569,
"step": 84000
},
{
"epoch": 0.09,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9485,
"step": 85000
},
{
"epoch": 0.09,
"learning_rate": 9.964609674954696e-05,
"loss": 0.9676,
"step": 86000
},
{
"epoch": 0.09,
"learning_rate": 9.962618725965196e-05,
"loss": 0.9634,
"step": 87000
},
{
"epoch": 0.09,
"learning_rate": 9.96057350657239e-05,
"loss": 0.9789,
"step": 88000
},
{
"epoch": 0.09,
"learning_rate": 9.95847403914247e-05,
"loss": 1.011,
"step": 89000
},
{
"epoch": 0.09,
"learning_rate": 9.956320346634876e-05,
"loss": 1.081,
"step": 90000
},
{
"epoch": 0.09,
"learning_rate": 9.954112452602045e-05,
"loss": 1.1758,
"step": 91000
},
{
"epoch": 0.09,
"learning_rate": 9.95185038118915e-05,
"loss": 1.1315,
"step": 92000
},
{
"epoch": 0.09,
"learning_rate": 9.949534157133844e-05,
"loss": 1.0568,
"step": 93000
},
{
"epoch": 0.09,
"learning_rate": 9.94716380576598e-05,
"loss": 1.0164,
"step": 94000
},
{
"epoch": 0.1,
"learning_rate": 9.944739353007344e-05,
"loss": 0.9761,
"step": 95000
},
{
"epoch": 0.1,
"learning_rate": 9.942260825371358e-05,
"loss": 1.0452,
"step": 96000
},
{
"epoch": 0.1,
"learning_rate": 9.939728249962807e-05,
"loss": 1.0411,
"step": 97000
},
{
"epoch": 0.1,
"learning_rate": 9.937141654477528e-05,
"loss": 1.003,
"step": 98000
},
{
"epoch": 0.1,
"learning_rate": 9.934501067202117e-05,
"loss": 0.9932,
"step": 99000
},
{
"epoch": 0.1,
"learning_rate": 9.931806517013612e-05,
"loss": 0.9302,
"step": 100000
},
{
"epoch": 0.1,
"eval_loss": 0.6663409471511841,
"eval_runtime": 34.9654,
"eval_samples_per_second": 142.999,
"eval_steps_per_second": 2.259,
"step": 100000
},
{
"epoch": 0.1,
"learning_rate": 9.929058033379181e-05,
"loss": 0.9777,
"step": 101000
},
{
"epoch": 0.1,
"learning_rate": 9.926255646355804e-05,
"loss": 0.6898,
"step": 102000
},
{
"epoch": 0.1,
"learning_rate": 9.923399386589933e-05,
"loss": 0.6548,
"step": 103000
},
{
"epoch": 0.1,
"learning_rate": 9.92048928531717e-05,
"loss": 0.8245,
"step": 104000
},
{
"epoch": 0.1,
"learning_rate": 9.917525374361912e-05,
"loss": 1.0507,
"step": 105000
},
{
"epoch": 0.11,
"learning_rate": 9.914507686137019e-05,
"loss": 0.956,
"step": 106000
},
{
"epoch": 0.11,
"learning_rate": 9.911436253643445e-05,
"loss": 0.936,
"step": 107000
},
{
"epoch": 0.11,
"learning_rate": 9.90831111046988e-05,
"loss": 1.0589,
"step": 108000
},
{
"epoch": 0.11,
"learning_rate": 9.905132290792394e-05,
"loss": 1.029,
"step": 109000
},
{
"epoch": 0.11,
"learning_rate": 9.901899829374047e-05,
"loss": 0.9992,
"step": 110000
},
{
"epoch": 0.11,
"learning_rate": 9.89861376156452e-05,
"loss": 1.0624,
"step": 111000
},
{
"epoch": 0.11,
"learning_rate": 9.895274123299723e-05,
"loss": 1.0827,
"step": 112000
},
{
"epoch": 0.11,
"learning_rate": 9.891880951101407e-05,
"loss": 1.0869,
"step": 113000
},
{
"epoch": 0.11,
"learning_rate": 9.888434282076758e-05,
"loss": 0.9603,
"step": 114000
},
{
"epoch": 0.12,
"learning_rate": 9.884934153917997e-05,
"loss": 1.0249,
"step": 115000
},
{
"epoch": 0.12,
"learning_rate": 9.881380604901964e-05,
"loss": 0.9934,
"step": 116000
},
{
"epoch": 0.12,
"learning_rate": 9.877773673889701e-05,
"loss": 0.7718,
"step": 117000
},
{
"epoch": 0.12,
"learning_rate": 9.87411340032603e-05,
"loss": 0.9071,
"step": 118000
},
{
"epoch": 0.12,
"learning_rate": 9.870399824239117e-05,
"loss": 0.9566,
"step": 119000
},
{
"epoch": 0.12,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9122,
"step": 120000
},
{
"epoch": 0.12,
"learning_rate": 9.862812927522309e-05,
"loss": 1.0316,
"step": 121000
},
{
"epoch": 0.12,
"learning_rate": 9.858939689861506e-05,
"loss": 1.0056,
"step": 122000
},
{
"epoch": 0.12,
"learning_rate": 9.855013315614725e-05,
"loss": 0.9951,
"step": 123000
},
{
"epoch": 0.12,
"learning_rate": 9.851033847720166e-05,
"loss": 0.9995,
"step": 124000
},
{
"epoch": 0.12,
"learning_rate": 9.847001329696653e-05,
"loss": 0.9108,
"step": 125000
},
{
"epoch": 0.13,
"learning_rate": 9.842915805643155e-05,
"loss": 0.9289,
"step": 126000
},
{
"epoch": 0.13,
"learning_rate": 9.838777320238312e-05,
"loss": 0.9776,
"step": 127000
},
{
"epoch": 0.13,
"learning_rate": 9.834585918739936e-05,
"loss": 1.0039,
"step": 128000
},
{
"epoch": 0.13,
"learning_rate": 9.830341646984521e-05,
"loss": 0.9274,
"step": 129000
},
{
"epoch": 0.13,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9803,
"step": 130000
},
{
"epoch": 0.13,
"learning_rate": 9.821694678938953e-05,
"loss": 1.0113,
"step": 131000
},
{
"epoch": 0.13,
"learning_rate": 9.817292077210659e-05,
"loss": 1.0792,
"step": 132000
},
{
"epoch": 0.13,
"learning_rate": 9.812836794348004e-05,
"loss": 0.9982,
"step": 133000
},
{
"epoch": 0.13,
"learning_rate": 9.808328879073251e-05,
"loss": 1.0073,
"step": 134000
},
{
"epoch": 0.14,
"learning_rate": 9.803768380684242e-05,
"loss": 1.227,
"step": 135000
},
{
"epoch": 0.14,
"learning_rate": 9.799155349053851e-05,
"loss": 1.0423,
"step": 136000
},
{
"epoch": 0.14,
"learning_rate": 9.794489834629455e-05,
"loss": 0.8962,
"step": 137000
},
{
"epoch": 0.14,
"learning_rate": 9.789771888432375e-05,
"loss": 0.9724,
"step": 138000
},
{
"epoch": 0.14,
"learning_rate": 9.785001562057309e-05,
"loss": 0.9518,
"step": 139000
},
{
"epoch": 0.14,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9236,
"step": 140000
},
{
"epoch": 0.14,
"learning_rate": 9.775303978015585e-05,
"loss": 0.9958,
"step": 141000
},
{
"epoch": 0.14,
"learning_rate": 9.77037682640015e-05,
"loss": 0.9957,
"step": 142000
},
{
"epoch": 0.14,
"learning_rate": 9.765397506708023e-05,
"loss": 0.9146,
"step": 143000
},
{
"epoch": 0.14,
"learning_rate": 9.760366073392246e-05,
"loss": 0.9139,
"step": 144000
},
{
"epoch": 0.14,
"learning_rate": 9.755282581475769e-05,
"loss": 0.953,
"step": 145000
},
{
"epoch": 0.15,
"learning_rate": 9.750147086550844e-05,
"loss": 0.7912,
"step": 146000
},
{
"epoch": 0.15,
"learning_rate": 9.744959644778422e-05,
"loss": 0.6733,
"step": 147000
},
{
"epoch": 0.15,
"learning_rate": 9.739720312887535e-05,
"loss": 0.6821,
"step": 148000
},
{
"epoch": 0.15,
"learning_rate": 9.734429148174675e-05,
"loss": 1.0371,
"step": 149000
},
{
"epoch": 0.15,
"learning_rate": 9.729086208503174e-05,
"loss": 1.0203,
"step": 150000
},
{
"epoch": 0.15,
"eval_loss": 0.6467772722244263,
"eval_runtime": 24.4207,
"eval_samples_per_second": 204.744,
"eval_steps_per_second": 3.235,
"step": 150000
},
{
"epoch": 0.15,
"learning_rate": 9.723691552302562e-05,
"loss": 1.0099,
"step": 151000
},
{
"epoch": 0.15,
"learning_rate": 9.718245238567939e-05,
"loss": 1.0822,
"step": 152000
},
{
"epoch": 0.15,
"learning_rate": 9.712747326859315e-05,
"loss": 1.0352,
"step": 153000
},
{
"epoch": 0.15,
"learning_rate": 9.707197877300974e-05,
"loss": 0.9671,
"step": 154000
},
{
"epoch": 0.15,
"learning_rate": 9.701596950580806e-05,
"loss": 1.0521,
"step": 155000
},
{
"epoch": 0.16,
"learning_rate": 9.695944607949649e-05,
"loss": 0.9215,
"step": 156000
},
{
"epoch": 0.16,
"learning_rate": 9.690240911220618e-05,
"loss": 0.9033,
"step": 157000
},
{
"epoch": 0.16,
"learning_rate": 9.684485922768422e-05,
"loss": 1.0112,
"step": 158000
},
{
"epoch": 0.16,
"learning_rate": 9.6786797055287e-05,
"loss": 0.843,
"step": 159000
},
{
"epoch": 0.16,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9084,
"step": 160000
},
{
"epoch": 0.16,
"learning_rate": 9.66691383922964e-05,
"loss": 0.8648,
"step": 161000
},
{
"epoch": 0.16,
"learning_rate": 9.660954318839933e-05,
"loss": 0.7183,
"step": 162000
},
{
"epoch": 0.16,
"learning_rate": 9.654943827000548e-05,
"loss": 0.8846,
"step": 163000
},
{
"epoch": 0.16,
"learning_rate": 9.648882429441257e-05,
"loss": 0.8588,
"step": 164000
},
{
"epoch": 0.17,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9902,
"step": 165000
},
{
"epoch": 0.17,
"learning_rate": 9.636607182864827e-05,
"loss": 0.937,
"step": 166000
},
{
"epoch": 0.17,
"learning_rate": 9.630393468087818e-05,
"loss": 0.9826,
"step": 167000
},
{
"epoch": 0.17,
"learning_rate": 9.624129116069694e-05,
"loss": 1.037,
"step": 168000
},
{
"epoch": 0.17,
"learning_rate": 9.617814195316411e-05,
"loss": 0.9159,
"step": 169000
},
{
"epoch": 0.17,
"learning_rate": 9.611448774886924e-05,
"loss": 0.9548,
"step": 170000
},
{
"epoch": 0.17,
"learning_rate": 9.605032924392457e-05,
"loss": 0.9936,
"step": 171000
},
{
"epoch": 0.17,
"learning_rate": 9.598566713995718e-05,
"loss": 1.0708,
"step": 172000
},
{
"epoch": 0.17,
"learning_rate": 9.59205021441015e-05,
"loss": 0.9153,
"step": 173000
},
{
"epoch": 0.17,
"learning_rate": 9.58548349689915e-05,
"loss": 0.9598,
"step": 174000
},
{
"epoch": 0.17,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9642,
"step": 175000
},
{
"epoch": 0.18,
"learning_rate": 9.572199695899522e-05,
"loss": 0.8771,
"step": 176000
},
{
"epoch": 0.18,
"learning_rate": 9.565482757680415e-05,
"loss": 0.9064,
"step": 177000
},
{
"epoch": 0.18,
"learning_rate": 9.558715892073323e-05,
"loss": 0.9757,
"step": 178000
},
{
"epoch": 0.18,
"learning_rate": 9.551899173079607e-05,
"loss": 0.9963,
"step": 179000
},
{
"epoch": 0.18,
"learning_rate": 9.545032675245813e-05,
"loss": 1.0155,
"step": 180000
},
{
"epoch": 0.18,
"learning_rate": 9.538116473662861e-05,
"loss": 0.9509,
"step": 181000
},
{
"epoch": 0.18,
"learning_rate": 9.531150643965223e-05,
"loss": 0.8333,
"step": 182000
},
{
"epoch": 0.18,
"learning_rate": 9.524135262330098e-05,
"loss": 0.9373,
"step": 183000
},
{
"epoch": 0.18,
"learning_rate": 9.517070405476575e-05,
"loss": 0.852,
"step": 184000
},
{
"epoch": 0.18,
"learning_rate": 9.509956150664796e-05,
"loss": 0.9335,
"step": 185000
},
{
"epoch": 0.19,
"learning_rate": 9.502792575695112e-05,
"loss": 0.9773,
"step": 186000
},
{
"epoch": 0.19,
"learning_rate": 9.49557975890723e-05,
"loss": 0.9384,
"step": 187000
},
{
"epoch": 0.19,
"learning_rate": 9.488317779179361e-05,
"loss": 0.9105,
"step": 188000
},
{
"epoch": 0.19,
"learning_rate": 9.481006715927351e-05,
"loss": 0.9118,
"step": 189000
},
{
"epoch": 0.19,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9584,
"step": 190000
},
{
"epoch": 0.19,
"learning_rate": 9.46623765919727e-05,
"loss": 0.7601,
"step": 191000
},
{
"epoch": 0.19,
"learning_rate": 9.458779827231237e-05,
"loss": 0.7258,
"step": 192000
},
{
"epoch": 0.19,
"learning_rate": 9.451273234763371e-05,
"loss": 0.8387,
"step": 193000
},
{
"epoch": 0.19,
"learning_rate": 9.443717963884569e-05,
"loss": 1.1209,
"step": 194000
},
{
"epoch": 0.2,
"learning_rate": 9.43611409721806e-05,
"loss": 0.8961,
"step": 195000
},
{
"epoch": 0.2,
"learning_rate": 9.428461717918511e-05,
"loss": 0.8493,
"step": 196000
},
{
"epoch": 0.2,
"learning_rate": 9.420760909671118e-05,
"loss": 1.0333,
"step": 197000
},
{
"epoch": 0.2,
"learning_rate": 9.413011756690685e-05,
"loss": 0.928,
"step": 198000
},
{
"epoch": 0.2,
"learning_rate": 9.405214343720707e-05,
"loss": 0.9016,
"step": 199000
},
{
"epoch": 0.2,
"learning_rate": 9.397368756032445e-05,
"loss": 0.9039,
"step": 200000
},
{
"epoch": 0.2,
"eval_loss": 0.6195229291915894,
"eval_runtime": 24.1688,
"eval_samples_per_second": 206.878,
"eval_steps_per_second": 3.269,
"step": 200000
},
{
"epoch": 0.2,
"learning_rate": 9.389475079423988e-05,
"loss": 0.8939,
"step": 201000
},
{
"epoch": 0.2,
"learning_rate": 9.381533400219318e-05,
"loss": 0.9112,
"step": 202000
},
{
"epoch": 0.2,
"learning_rate": 9.373543805267368e-05,
"loss": 0.8656,
"step": 203000
},
{
"epoch": 0.2,
"learning_rate": 9.365506381941066e-05,
"loss": 0.852,
"step": 204000
},
{
"epoch": 0.2,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8976,
"step": 205000
},
{
"epoch": 0.21,
"learning_rate": 9.349288402271388e-05,
"loss": 0.6997,
"step": 206000
},
{
"epoch": 0.21,
"learning_rate": 9.341108023285238e-05,
"loss": 0.8927,
"step": 207000
},
{
"epoch": 0.21,
"learning_rate": 9.332880170637252e-05,
"loss": 0.8809,
"step": 208000
},
{
"epoch": 0.21,
"learning_rate": 9.32460493430591e-05,
"loss": 0.9284,
"step": 209000
},
{
"epoch": 0.21,
"learning_rate": 9.316282404787871e-05,
"loss": 1.0261,
"step": 210000
},
{
"epoch": 0.21,
"learning_rate": 9.30791267309698e-05,
"loss": 1.1077,
"step": 211000
},
{
"epoch": 0.21,
"learning_rate": 9.299495830763286e-05,
"loss": 1.0381,
"step": 212000
},
{
"epoch": 0.21,
"learning_rate": 9.291031969832026e-05,
"loss": 0.9225,
"step": 213000
},
{
"epoch": 0.21,
"learning_rate": 9.282521182862629e-05,
"loss": 1.0013,
"step": 214000
},
{
"epoch": 0.21,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8487,
"step": 215000
},
{
"epoch": 0.22,
"learning_rate": 9.265359203611987e-05,
"loss": 0.9014,
"step": 216000
},
{
"epoch": 0.22,
"learning_rate": 9.256708199011401e-05,
"loss": 0.9586,
"step": 217000
},
{
"epoch": 0.22,
"learning_rate": 9.248010643731935e-05,
"loss": 0.8322,
"step": 218000
},
{
"epoch": 0.22,
"learning_rate": 9.239266632888659e-05,
"loss": 0.8878,
"step": 219000
},
{
"epoch": 0.22,
"learning_rate": 9.230476262104677e-05,
"loss": 0.8508,
"step": 220000
},
{
"epoch": 0.22,
"learning_rate": 9.221639627510076e-05,
"loss": 0.8793,
"step": 221000
},
{
"epoch": 0.22,
"learning_rate": 9.212756825740873e-05,
"loss": 0.8577,
"step": 222000
},
{
"epoch": 0.22,
"learning_rate": 9.20382795393797e-05,
"loss": 0.9545,
"step": 223000
},
{
"epoch": 0.22,
"learning_rate": 9.194853109746074e-05,
"loss": 1.0083,
"step": 224000
},
{
"epoch": 0.23,
"learning_rate": 9.185832391312644e-05,
"loss": 1.0004,
"step": 225000
},
{
"epoch": 0.23,
"learning_rate": 9.176765897286813e-05,
"loss": 0.8553,
"step": 226000
},
{
"epoch": 0.23,
"learning_rate": 9.167653726818305e-05,
"loss": 0.9164,
"step": 227000
},
{
"epoch": 0.23,
"learning_rate": 9.158495979556358e-05,
"loss": 0.8879,
"step": 228000
},
{
"epoch": 0.23,
"learning_rate": 9.14929275564863e-05,
"loss": 0.9265,
"step": 229000
},
{
"epoch": 0.23,
"learning_rate": 9.140044155740101e-05,
"loss": 1.0602,
"step": 230000
},
{
"epoch": 0.23,
"learning_rate": 9.130750280971978e-05,
"loss": 1.0829,
"step": 231000
},
{
"epoch": 0.23,
"learning_rate": 9.121411232980588e-05,
"loss": 0.9123,
"step": 232000
},
{
"epoch": 0.23,
"learning_rate": 9.112027113896262e-05,
"loss": 0.8953,
"step": 233000
},
{
"epoch": 0.23,
"learning_rate": 9.102598026342222e-05,
"loss": 1.0354,
"step": 234000
},
{
"epoch": 0.23,
"learning_rate": 9.093124073433463e-05,
"loss": 0.6453,
"step": 235000
},
{
"epoch": 0.24,
"learning_rate": 9.083605358775612e-05,
"loss": 0.6108,
"step": 236000
},
{
"epoch": 0.24,
"learning_rate": 9.074041986463808e-05,
"loss": 0.7116,
"step": 237000
},
{
"epoch": 0.24,
"learning_rate": 9.064434061081562e-05,
"loss": 0.9821,
"step": 238000
},
{
"epoch": 0.24,
"learning_rate": 9.0547816876996e-05,
"loss": 0.8962,
"step": 239000
},
{
"epoch": 0.24,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8552,
"step": 240000
},
{
"epoch": 0.24,
"learning_rate": 9.035344019648702e-05,
"loss": 0.9197,
"step": 241000
},
{
"epoch": 0.24,
"learning_rate": 9.025558937546988e-05,
"loss": 0.9253,
"step": 242000
},
{
"epoch": 0.24,
"learning_rate": 9.015729832577681e-05,
"loss": 0.8837,
"step": 243000
},
{
"epoch": 0.24,
"learning_rate": 9.005856812230304e-05,
"loss": 0.8883,
"step": 244000
},
{
"epoch": 0.24,
"learning_rate": 8.995939984474624e-05,
"loss": 0.9024,
"step": 245000
},
{
"epoch": 0.25,
"learning_rate": 8.98597945775948e-05,
"loss": 0.899,
"step": 246000
},
{
"epoch": 0.25,
"learning_rate": 8.975975341011596e-05,
"loss": 0.9336,
"step": 247000
},
{
"epoch": 0.25,
"learning_rate": 8.965927743634391e-05,
"loss": 0.8503,
"step": 248000
},
{
"epoch": 0.25,
"learning_rate": 8.955836775506776e-05,
"loss": 0.9448,
"step": 249000
},
{
"epoch": 0.25,
"learning_rate": 8.945702546981969e-05,
"loss": 0.8713,
"step": 250000
},
{
"epoch": 0.25,
"eval_loss": 0.6120243072509766,
"eval_runtime": 24.3453,
"eval_samples_per_second": 205.378,
"eval_steps_per_second": 3.245,
"step": 250000
},
{
"epoch": 0.25,
"learning_rate": 8.935525168886262e-05,
"loss": 0.8729,
"step": 251000
},
{
"epoch": 0.25,
"learning_rate": 8.92530475251784e-05,
"loss": 0.8731,
"step": 252000
},
{
"epoch": 0.25,
"learning_rate": 8.91504140964553e-05,
"loss": 0.8978,
"step": 253000
},
{
"epoch": 0.25,
"learning_rate": 8.90473525250761e-05,
"loss": 1.0355,
"step": 254000
},
{
"epoch": 0.26,
"learning_rate": 8.894386393810563e-05,
"loss": 0.8987,
"step": 255000
},
{
"epoch": 0.26,
"learning_rate": 8.883994946727849e-05,
"loss": 0.9422,
"step": 256000
},
{
"epoch": 0.26,
"learning_rate": 8.873561024898668e-05,
"loss": 0.9875,
"step": 257000
},
{
"epoch": 0.26,
"learning_rate": 8.863084742426719e-05,
"loss": 0.8255,
"step": 258000
},
{
"epoch": 0.26,
"learning_rate": 8.852566213878947e-05,
"loss": 0.847,
"step": 259000
},
{
"epoch": 0.26,
"learning_rate": 8.842005554284296e-05,
"loss": 0.8732,
"step": 260000
},
{
"epoch": 0.26,
"learning_rate": 8.831402879132446e-05,
"loss": 0.8759,
"step": 261000
},
{
"epoch": 0.26,
"learning_rate": 8.820758304372557e-05,
"loss": 0.841,
"step": 262000
},
{
"epoch": 0.26,
"learning_rate": 8.810071946411989e-05,
"loss": 0.8556,
"step": 263000
},
{
"epoch": 0.26,
"learning_rate": 8.799343922115044e-05,
"loss": 0.8639,
"step": 264000
},
{
"epoch": 0.27,
"learning_rate": 8.788574348801675e-05,
"loss": 0.851,
"step": 265000
},
{
"epoch": 0.27,
"learning_rate": 8.77776334424621e-05,
"loss": 0.8877,
"step": 266000
},
{
"epoch": 0.27,
"learning_rate": 8.766911026676064e-05,
"loss": 0.933,
"step": 267000
},
{
"epoch": 0.27,
"learning_rate": 8.756017514770443e-05,
"loss": 1.0089,
"step": 268000
},
{
"epoch": 0.27,
"learning_rate": 8.745082927659047e-05,
"loss": 1.0651,
"step": 269000
},
{
"epoch": 0.27,
"learning_rate": 8.73410738492077e-05,
"loss": 1.0143,
"step": 270000
},
{
"epoch": 0.27,
"learning_rate": 8.723091006582389e-05,
"loss": 0.9269,
"step": 271000
},
{
"epoch": 0.27,
"learning_rate": 8.71203391311725e-05,
"loss": 0.9089,
"step": 272000
},
{
"epoch": 0.27,
"learning_rate": 8.700936225443959e-05,
"loss": 0.9593,
"step": 273000
},
{
"epoch": 0.27,
"learning_rate": 8.689798064925049e-05,
"loss": 0.9285,
"step": 274000
},
{
"epoch": 0.28,
"learning_rate": 8.678619553365659e-05,
"loss": 0.9185,
"step": 275000
},
{
"epoch": 0.28,
"learning_rate": 8.6674008130122e-05,
"loss": 0.9223,
"step": 276000
},
{
"epoch": 0.28,
"learning_rate": 8.656141966551019e-05,
"loss": 0.8536,
"step": 277000
},
{
"epoch": 0.28,
"learning_rate": 8.644843137107059e-05,
"loss": 0.8694,
"step": 278000
},
{
"epoch": 0.28,
"learning_rate": 8.633504448242505e-05,
"loss": 0.76,
"step": 279000
},
{
"epoch": 0.28,
"learning_rate": 8.622126023955446e-05,
"loss": 0.6139,
"step": 280000
},
{
"epoch": 0.28,
"learning_rate": 8.610707988678503e-05,
"loss": 0.5841,
"step": 281000
},
{
"epoch": 0.28,
"learning_rate": 8.599250467277483e-05,
"loss": 0.8604,
"step": 282000
},
{
"epoch": 0.28,
"learning_rate": 8.587753585050004e-05,
"loss": 0.9247,
"step": 283000
},
{
"epoch": 0.28,
"learning_rate": 8.576217467724128e-05,
"loss": 0.8514,
"step": 284000
},
{
"epoch": 0.28,
"learning_rate": 8.564642241456986e-05,
"loss": 0.8482,
"step": 285000
},
{
"epoch": 0.29,
"learning_rate": 8.553028032833397e-05,
"loss": 0.9728,
"step": 286000
},
{
"epoch": 0.29,
"learning_rate": 8.541374968864487e-05,
"loss": 0.8998,
"step": 287000
},
{
"epoch": 0.29,
"learning_rate": 8.529683176986295e-05,
"loss": 0.8923,
"step": 288000
},
{
"epoch": 0.29,
"learning_rate": 8.517952785058385e-05,
"loss": 0.9404,
"step": 289000
},
{
"epoch": 0.29,
"learning_rate": 8.506183921362443e-05,
"loss": 0.9988,
"step": 290000
},
{
"epoch": 0.29,
"learning_rate": 8.494376714600878e-05,
"loss": 0.953,
"step": 291000
},
{
"epoch": 0.29,
"learning_rate": 8.482531293895412e-05,
"loss": 0.8338,
"step": 292000
},
{
"epoch": 0.29,
"learning_rate": 8.470647788785665e-05,
"loss": 0.9674,
"step": 293000
},
{
"epoch": 0.29,
"learning_rate": 8.458726329227747e-05,
"loss": 0.8512,
"step": 294000
},
{
"epoch": 0.29,
"learning_rate": 8.44676704559283e-05,
"loss": 0.6064,
"step": 295000
},
{
"epoch": 0.3,
"learning_rate": 8.434770068665723e-05,
"loss": 0.9205,
"step": 296000
},
{
"epoch": 0.3,
"learning_rate": 8.422735529643444e-05,
"loss": 0.8043,
"step": 297000
},
{
"epoch": 0.3,
"learning_rate": 8.410663560133784e-05,
"loss": 0.8971,
"step": 298000
},
{
"epoch": 0.3,
"learning_rate": 8.398554292153866e-05,
"loss": 0.883,
"step": 299000
},
{
"epoch": 0.3,
"learning_rate": 8.386407858128706e-05,
"loss": 0.9223,
"step": 300000
},
{
"epoch": 0.3,
"eval_loss": 0.5713072419166565,
"eval_runtime": 22.7311,
"eval_samples_per_second": 219.963,
"eval_steps_per_second": 3.475,
"step": 300000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.78949694947328e+19,
"trial_name": null,
"trial_params": null
}