joelniklaus's picture
Training in progress, step 200000
6c3ada6
raw
history blame
25.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2,
"global_step": 200000,
"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": 6.9767,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 4.7384,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 3.8208,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 3.525,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 3.3533,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 3.2884,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.9989,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.9357,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 3.0415,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 2.8658,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.6819,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 2.5197,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.4403,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.392,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 2.3863,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.2381,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.2403,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 2.2579,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 2.2505,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.2141,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 2.1328,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.0589,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 2.0857,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 1.9813,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 1.8747,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.7104,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.5456,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.5308,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.5038,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.443,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 1.3552,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.3915,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.4418,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 1.4082,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 1.3474,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 1.2203,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 1.299,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 1.3058,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 1.3016,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.3035,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 1.2701,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 1.3014,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 1.3243,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 1.2947,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 1.2576,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 1.1458,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 1.1338,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 1.2031,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 1.2255,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.1441,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.9408084154129028,
"eval_runtime": 22.8267,
"eval_samples_per_second": 219.042,
"eval_steps_per_second": 1.752,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 1.0268,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 1.1043,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 1.149,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 1.146,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 1.1736,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 1.1482,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 1.1799,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 1.106,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 1.1093,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 1.0887,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 1.0139,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 0.9824,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 1.0224,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 1.0483,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 1.0312,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 1.013,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 1.0084,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 1.0135,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 1.0014,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 1.0374,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 1.0887,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 1.1263,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 1.1247,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 1.0921,
"step": 74000
},
{
"epoch": 0.07,
"learning_rate": 9.98292246503335e-05,
"loss": 1.1035,
"step": 75000
},
{
"epoch": 0.08,
"learning_rate": 9.981529796748134e-05,
"loss": 1.0531,
"step": 76000
},
{
"epoch": 0.08,
"learning_rate": 9.980082651251175e-05,
"loss": 1.0087,
"step": 77000
},
{
"epoch": 0.08,
"learning_rate": 9.97858104436822e-05,
"loss": 1.0188,
"step": 78000
},
{
"epoch": 0.08,
"learning_rate": 9.977024992520602e-05,
"loss": 0.9905,
"step": 79000
},
{
"epoch": 0.08,
"learning_rate": 9.975414512725057e-05,
"loss": 0.8739,
"step": 80000
},
{
"epoch": 0.08,
"learning_rate": 9.973749622593534e-05,
"loss": 0.9195,
"step": 81000
},
{
"epoch": 0.08,
"learning_rate": 9.972030340333001e-05,
"loss": 0.9907,
"step": 82000
},
{
"epoch": 0.08,
"learning_rate": 9.970256684745258e-05,
"loss": 1.0349,
"step": 83000
},
{
"epoch": 0.08,
"learning_rate": 9.968428675226714e-05,
"loss": 1.0336,
"step": 84000
},
{
"epoch": 0.09,
"learning_rate": 9.966546331768191e-05,
"loss": 1.036,
"step": 85000
},
{
"epoch": 0.09,
"learning_rate": 9.964609674954696e-05,
"loss": 1.1217,
"step": 86000
},
{
"epoch": 0.09,
"learning_rate": 9.962618725965196e-05,
"loss": 1.1492,
"step": 87000
},
{
"epoch": 0.09,
"learning_rate": 9.96057350657239e-05,
"loss": 1.1256,
"step": 88000
},
{
"epoch": 0.09,
"learning_rate": 9.95847403914247e-05,
"loss": 1.1145,
"step": 89000
},
{
"epoch": 0.09,
"learning_rate": 9.956320346634876e-05,
"loss": 1.1303,
"step": 90000
},
{
"epoch": 0.09,
"learning_rate": 9.954112452602045e-05,
"loss": 1.0071,
"step": 91000
},
{
"epoch": 0.09,
"learning_rate": 9.95185038118915e-05,
"loss": 1.0056,
"step": 92000
},
{
"epoch": 0.09,
"learning_rate": 9.949534157133844e-05,
"loss": 1.0161,
"step": 93000
},
{
"epoch": 0.09,
"learning_rate": 9.94716380576598e-05,
"loss": 0.9924,
"step": 94000
},
{
"epoch": 0.1,
"learning_rate": 9.944739353007344e-05,
"loss": 0.935,
"step": 95000
},
{
"epoch": 0.1,
"learning_rate": 9.942260825371358e-05,
"loss": 0.9387,
"step": 96000
},
{
"epoch": 0.1,
"learning_rate": 9.939728249962807e-05,
"loss": 0.9691,
"step": 97000
},
{
"epoch": 0.1,
"learning_rate": 9.937141654477528e-05,
"loss": 1.0143,
"step": 98000
},
{
"epoch": 0.1,
"learning_rate": 9.934501067202117e-05,
"loss": 1.0035,
"step": 99000
},
{
"epoch": 0.1,
"learning_rate": 9.931806517013612e-05,
"loss": 0.9625,
"step": 100000
},
{
"epoch": 0.1,
"eval_loss": 0.7926260828971863,
"eval_runtime": 17.2748,
"eval_samples_per_second": 289.439,
"eval_steps_per_second": 2.316,
"step": 100000
},
{
"epoch": 0.1,
"learning_rate": 9.929058033379181e-05,
"loss": 1.0172,
"step": 101000
},
{
"epoch": 0.1,
"learning_rate": 9.926255646355804e-05,
"loss": 1.0431,
"step": 102000
},
{
"epoch": 0.1,
"learning_rate": 9.923399386589933e-05,
"loss": 1.0074,
"step": 103000
},
{
"epoch": 0.1,
"learning_rate": 9.92048928531717e-05,
"loss": 1.0245,
"step": 104000
},
{
"epoch": 0.1,
"learning_rate": 9.917525374361912e-05,
"loss": 1.071,
"step": 105000
},
{
"epoch": 0.11,
"learning_rate": 9.914507686137019e-05,
"loss": 1.0432,
"step": 106000
},
{
"epoch": 0.11,
"learning_rate": 9.911436253643445e-05,
"loss": 0.9955,
"step": 107000
},
{
"epoch": 0.11,
"learning_rate": 9.90831111046988e-05,
"loss": 0.9834,
"step": 108000
},
{
"epoch": 0.11,
"learning_rate": 9.905132290792394e-05,
"loss": 0.9035,
"step": 109000
},
{
"epoch": 0.11,
"learning_rate": 9.901899829374047e-05,
"loss": 0.872,
"step": 110000
},
{
"epoch": 0.11,
"learning_rate": 9.89861376156452e-05,
"loss": 0.835,
"step": 111000
},
{
"epoch": 0.11,
"learning_rate": 9.895274123299723e-05,
"loss": 0.8424,
"step": 112000
},
{
"epoch": 0.11,
"learning_rate": 9.891880951101407e-05,
"loss": 0.8591,
"step": 113000
},
{
"epoch": 0.11,
"learning_rate": 9.888434282076758e-05,
"loss": 0.8903,
"step": 114000
},
{
"epoch": 0.12,
"learning_rate": 9.884934153917997e-05,
"loss": 0.9674,
"step": 115000
},
{
"epoch": 0.12,
"learning_rate": 9.881380604901964e-05,
"loss": 1.0091,
"step": 116000
},
{
"epoch": 0.12,
"learning_rate": 9.877773673889701e-05,
"loss": 0.9964,
"step": 117000
},
{
"epoch": 0.12,
"learning_rate": 9.87411340032603e-05,
"loss": 0.9666,
"step": 118000
},
{
"epoch": 0.12,
"learning_rate": 9.870399824239117e-05,
"loss": 0.9941,
"step": 119000
},
{
"epoch": 0.12,
"learning_rate": 9.86663298624003e-05,
"loss": 1.0679,
"step": 120000
},
{
"epoch": 0.12,
"learning_rate": 9.862812927522309e-05,
"loss": 1.0277,
"step": 121000
},
{
"epoch": 0.12,
"learning_rate": 9.858939689861506e-05,
"loss": 0.9748,
"step": 122000
},
{
"epoch": 0.12,
"learning_rate": 9.855013315614725e-05,
"loss": 0.9998,
"step": 123000
},
{
"epoch": 0.12,
"learning_rate": 9.851033847720166e-05,
"loss": 0.8839,
"step": 124000
},
{
"epoch": 0.12,
"learning_rate": 9.847001329696653e-05,
"loss": 0.8832,
"step": 125000
},
{
"epoch": 0.13,
"learning_rate": 9.842915805643155e-05,
"loss": 0.8488,
"step": 126000
},
{
"epoch": 0.13,
"learning_rate": 9.838777320238312e-05,
"loss": 0.849,
"step": 127000
},
{
"epoch": 0.13,
"learning_rate": 9.834585918739936e-05,
"loss": 0.8826,
"step": 128000
},
{
"epoch": 0.13,
"learning_rate": 9.830341646984521e-05,
"loss": 0.892,
"step": 129000
},
{
"epoch": 0.13,
"learning_rate": 9.826044551386744e-05,
"loss": 0.949,
"step": 130000
},
{
"epoch": 0.13,
"learning_rate": 9.821694678938953e-05,
"loss": 1.0179,
"step": 131000
},
{
"epoch": 0.13,
"learning_rate": 9.817292077210659e-05,
"loss": 1.0254,
"step": 132000
},
{
"epoch": 0.13,
"learning_rate": 9.812836794348004e-05,
"loss": 1.0143,
"step": 133000
},
{
"epoch": 0.13,
"learning_rate": 9.808328879073251e-05,
"loss": 1.0234,
"step": 134000
},
{
"epoch": 0.14,
"learning_rate": 9.803768380684242e-05,
"loss": 1.0669,
"step": 135000
},
{
"epoch": 0.14,
"learning_rate": 9.799155349053851e-05,
"loss": 1.0151,
"step": 136000
},
{
"epoch": 0.14,
"learning_rate": 9.794489834629455e-05,
"loss": 0.9774,
"step": 137000
},
{
"epoch": 0.14,
"learning_rate": 9.789771888432375e-05,
"loss": 0.9581,
"step": 138000
},
{
"epoch": 0.14,
"learning_rate": 9.785001562057309e-05,
"loss": 0.9845,
"step": 139000
},
{
"epoch": 0.14,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9546,
"step": 140000
},
{
"epoch": 0.14,
"learning_rate": 9.775303978015585e-05,
"loss": 0.8778,
"step": 141000
},
{
"epoch": 0.14,
"learning_rate": 9.77037682640015e-05,
"loss": 0.9097,
"step": 142000
},
{
"epoch": 0.14,
"learning_rate": 9.765397506708023e-05,
"loss": 0.9143,
"step": 143000
},
{
"epoch": 0.14,
"learning_rate": 9.760366073392246e-05,
"loss": 0.9544,
"step": 144000
},
{
"epoch": 0.14,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0027,
"step": 145000
},
{
"epoch": 0.15,
"learning_rate": 9.750147086550844e-05,
"loss": 1.0266,
"step": 146000
},
{
"epoch": 0.15,
"learning_rate": 9.744959644778422e-05,
"loss": 0.9872,
"step": 147000
},
{
"epoch": 0.15,
"learning_rate": 9.739720312887535e-05,
"loss": 1.0059,
"step": 148000
},
{
"epoch": 0.15,
"learning_rate": 9.734429148174675e-05,
"loss": 0.9495,
"step": 149000
},
{
"epoch": 0.15,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9713,
"step": 150000
},
{
"epoch": 0.15,
"eval_loss": 0.7478430867195129,
"eval_runtime": 17.3739,
"eval_samples_per_second": 287.787,
"eval_steps_per_second": 2.302,
"step": 150000
},
{
"epoch": 0.15,
"learning_rate": 9.723691552302562e-05,
"loss": 0.938,
"step": 151000
},
{
"epoch": 0.15,
"learning_rate": 9.718245238567939e-05,
"loss": 0.9249,
"step": 152000
},
{
"epoch": 0.15,
"learning_rate": 9.712747326859315e-05,
"loss": 0.9005,
"step": 153000
},
{
"epoch": 0.15,
"learning_rate": 9.707197877300974e-05,
"loss": 0.9413,
"step": 154000
},
{
"epoch": 0.15,
"learning_rate": 9.701596950580806e-05,
"loss": 0.9013,
"step": 155000
},
{
"epoch": 0.16,
"learning_rate": 9.695944607949649e-05,
"loss": 0.8869,
"step": 156000
},
{
"epoch": 0.16,
"learning_rate": 9.690240911220618e-05,
"loss": 0.8786,
"step": 157000
},
{
"epoch": 0.16,
"learning_rate": 9.684485922768422e-05,
"loss": 0.8526,
"step": 158000
},
{
"epoch": 0.16,
"learning_rate": 9.6786797055287e-05,
"loss": 0.8943,
"step": 159000
},
{
"epoch": 0.16,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9101,
"step": 160000
},
{
"epoch": 0.16,
"learning_rate": 9.66691383922964e-05,
"loss": 0.9027,
"step": 161000
},
{
"epoch": 0.16,
"learning_rate": 9.660954318839933e-05,
"loss": 0.9056,
"step": 162000
},
{
"epoch": 0.16,
"learning_rate": 9.654943827000548e-05,
"loss": 0.9082,
"step": 163000
},
{
"epoch": 0.16,
"learning_rate": 9.648882429441257e-05,
"loss": 0.9303,
"step": 164000
},
{
"epoch": 0.17,
"learning_rate": 9.642770192448536e-05,
"loss": 0.9734,
"step": 165000
},
{
"epoch": 0.17,
"learning_rate": 9.636607182864827e-05,
"loss": 0.9205,
"step": 166000
},
{
"epoch": 0.17,
"learning_rate": 9.630393468087818e-05,
"loss": 0.859,
"step": 167000
},
{
"epoch": 0.17,
"learning_rate": 9.624129116069694e-05,
"loss": 0.8709,
"step": 168000
},
{
"epoch": 0.17,
"learning_rate": 9.617814195316411e-05,
"loss": 0.8963,
"step": 169000
},
{
"epoch": 0.17,
"learning_rate": 9.611448774886924e-05,
"loss": 0.893,
"step": 170000
},
{
"epoch": 0.17,
"learning_rate": 9.605032924392457e-05,
"loss": 0.8637,
"step": 171000
},
{
"epoch": 0.17,
"learning_rate": 9.598566713995718e-05,
"loss": 0.865,
"step": 172000
},
{
"epoch": 0.17,
"learning_rate": 9.59205021441015e-05,
"loss": 0.9266,
"step": 173000
},
{
"epoch": 0.17,
"learning_rate": 9.58548349689915e-05,
"loss": 0.945,
"step": 174000
},
{
"epoch": 0.17,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9553,
"step": 175000
},
{
"epoch": 0.18,
"learning_rate": 9.572199695899522e-05,
"loss": 0.93,
"step": 176000
},
{
"epoch": 0.18,
"learning_rate": 9.565482757680415e-05,
"loss": 0.9294,
"step": 177000
},
{
"epoch": 0.18,
"learning_rate": 9.558715892073323e-05,
"loss": 0.9214,
"step": 178000
},
{
"epoch": 0.18,
"learning_rate": 9.551899173079607e-05,
"loss": 0.9232,
"step": 179000
},
{
"epoch": 0.18,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9419,
"step": 180000
},
{
"epoch": 0.18,
"learning_rate": 9.538116473662861e-05,
"loss": 0.9606,
"step": 181000
},
{
"epoch": 0.18,
"learning_rate": 9.531150643965223e-05,
"loss": 0.8498,
"step": 182000
},
{
"epoch": 0.18,
"learning_rate": 9.524135262330098e-05,
"loss": 0.8969,
"step": 183000
},
{
"epoch": 0.18,
"learning_rate": 9.517070405476575e-05,
"loss": 0.8861,
"step": 184000
},
{
"epoch": 0.18,
"learning_rate": 9.509956150664796e-05,
"loss": 0.9049,
"step": 185000
},
{
"epoch": 0.19,
"learning_rate": 9.502792575695112e-05,
"loss": 0.8876,
"step": 186000
},
{
"epoch": 0.19,
"learning_rate": 9.49557975890723e-05,
"loss": 0.8875,
"step": 187000
},
{
"epoch": 0.19,
"learning_rate": 9.488317779179361e-05,
"loss": 0.9751,
"step": 188000
},
{
"epoch": 0.19,
"learning_rate": 9.481006715927351e-05,
"loss": 1.0256,
"step": 189000
},
{
"epoch": 0.19,
"learning_rate": 9.473646649103818e-05,
"loss": 1.0121,
"step": 190000
},
{
"epoch": 0.19,
"learning_rate": 9.46623765919727e-05,
"loss": 0.9544,
"step": 191000
},
{
"epoch": 0.19,
"learning_rate": 9.458779827231237e-05,
"loss": 0.9857,
"step": 192000
},
{
"epoch": 0.19,
"learning_rate": 9.451273234763371e-05,
"loss": 0.9569,
"step": 193000
},
{
"epoch": 0.19,
"learning_rate": 9.443717963884569e-05,
"loss": 0.9694,
"step": 194000
},
{
"epoch": 0.2,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9824,
"step": 195000
},
{
"epoch": 0.2,
"learning_rate": 9.428461717918511e-05,
"loss": 0.9287,
"step": 196000
},
{
"epoch": 0.2,
"learning_rate": 9.420760909671118e-05,
"loss": 0.8156,
"step": 197000
},
{
"epoch": 0.2,
"learning_rate": 9.413011756690685e-05,
"loss": 0.8472,
"step": 198000
},
{
"epoch": 0.2,
"learning_rate": 9.405214343720707e-05,
"loss": 0.8277,
"step": 199000
},
{
"epoch": 0.2,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8152,
"step": 200000
},
{
"epoch": 0.2,
"eval_loss": 0.7049728631973267,
"eval_runtime": 16.5545,
"eval_samples_per_second": 302.032,
"eval_steps_per_second": 2.416,
"step": 200000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 3.3728545947648e+18,
"trial_name": null,
"trial_params": null
}