finetuned-mt5-small-10epoch / trainer_state.json
Lvxue's picture
End of training
71bcc40
raw history blame
No virus
31.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 127150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 4.980338183248132e-05,
"loss": 8.0518,
"step": 500
},
{
"epoch": 0.08,
"learning_rate": 4.9606763664962646e-05,
"loss": 3.358,
"step": 1000
},
{
"epoch": 0.12,
"learning_rate": 4.9410145497443964e-05,
"loss": 2.9014,
"step": 1500
},
{
"epoch": 0.16,
"learning_rate": 4.921352732992528e-05,
"loss": 2.6617,
"step": 2000
},
{
"epoch": 0.2,
"learning_rate": 4.901690916240661e-05,
"loss": 2.4945,
"step": 2500
},
{
"epoch": 0.24,
"learning_rate": 4.882029099488793e-05,
"loss": 2.3686,
"step": 3000
},
{
"epoch": 0.28,
"learning_rate": 4.862367282736925e-05,
"loss": 2.2674,
"step": 3500
},
{
"epoch": 0.31,
"learning_rate": 4.8427054659850575e-05,
"loss": 2.1889,
"step": 4000
},
{
"epoch": 0.35,
"learning_rate": 4.8230436492331893e-05,
"loss": 2.1107,
"step": 4500
},
{
"epoch": 0.39,
"learning_rate": 4.803381832481321e-05,
"loss": 2.0427,
"step": 5000
},
{
"epoch": 0.43,
"learning_rate": 4.783720015729454e-05,
"loss": 1.9907,
"step": 5500
},
{
"epoch": 0.47,
"learning_rate": 4.7640581989775855e-05,
"loss": 1.9401,
"step": 6000
},
{
"epoch": 0.51,
"learning_rate": 4.744396382225718e-05,
"loss": 1.9027,
"step": 6500
},
{
"epoch": 0.55,
"learning_rate": 4.72473456547385e-05,
"loss": 1.8655,
"step": 7000
},
{
"epoch": 0.59,
"learning_rate": 4.705072748721982e-05,
"loss": 1.823,
"step": 7500
},
{
"epoch": 0.63,
"learning_rate": 4.685410931970115e-05,
"loss": 1.7995,
"step": 8000
},
{
"epoch": 0.67,
"learning_rate": 4.6657491152182466e-05,
"loss": 1.7682,
"step": 8500
},
{
"epoch": 0.71,
"learning_rate": 4.6460872984663785e-05,
"loss": 1.7367,
"step": 9000
},
{
"epoch": 0.75,
"learning_rate": 4.626425481714511e-05,
"loss": 1.7111,
"step": 9500
},
{
"epoch": 0.79,
"learning_rate": 4.606763664962643e-05,
"loss": 1.6903,
"step": 10000
},
{
"epoch": 0.83,
"learning_rate": 4.5871018482107746e-05,
"loss": 1.6655,
"step": 10500
},
{
"epoch": 0.87,
"learning_rate": 4.567440031458907e-05,
"loss": 1.6468,
"step": 11000
},
{
"epoch": 0.9,
"learning_rate": 4.547778214707039e-05,
"loss": 1.6196,
"step": 11500
},
{
"epoch": 0.94,
"learning_rate": 4.528116397955171e-05,
"loss": 1.6017,
"step": 12000
},
{
"epoch": 0.98,
"learning_rate": 4.508454581203303e-05,
"loss": 1.5889,
"step": 12500
},
{
"epoch": 1.02,
"learning_rate": 4.488792764451436e-05,
"loss": 1.5679,
"step": 13000
},
{
"epoch": 1.06,
"learning_rate": 4.4691309476995676e-05,
"loss": 1.5419,
"step": 13500
},
{
"epoch": 1.1,
"learning_rate": 4.4494691309477e-05,
"loss": 1.5339,
"step": 14000
},
{
"epoch": 1.14,
"learning_rate": 4.429807314195832e-05,
"loss": 1.5189,
"step": 14500
},
{
"epoch": 1.18,
"learning_rate": 4.410145497443964e-05,
"loss": 1.5071,
"step": 15000
},
{
"epoch": 1.22,
"learning_rate": 4.390483680692096e-05,
"loss": 1.4936,
"step": 15500
},
{
"epoch": 1.26,
"learning_rate": 4.370821863940228e-05,
"loss": 1.4849,
"step": 16000
},
{
"epoch": 1.3,
"learning_rate": 4.3511600471883605e-05,
"loss": 1.4671,
"step": 16500
},
{
"epoch": 1.34,
"learning_rate": 4.3314982304364923e-05,
"loss": 1.4519,
"step": 17000
},
{
"epoch": 1.38,
"learning_rate": 4.311836413684625e-05,
"loss": 1.4411,
"step": 17500
},
{
"epoch": 1.42,
"learning_rate": 4.2921745969327573e-05,
"loss": 1.4355,
"step": 18000
},
{
"epoch": 1.45,
"learning_rate": 4.272512780180889e-05,
"loss": 1.4224,
"step": 18500
},
{
"epoch": 1.49,
"learning_rate": 4.252850963429021e-05,
"loss": 1.4221,
"step": 19000
},
{
"epoch": 1.53,
"learning_rate": 4.2331891466771535e-05,
"loss": 1.4053,
"step": 19500
},
{
"epoch": 1.57,
"learning_rate": 4.213527329925285e-05,
"loss": 1.394,
"step": 20000
},
{
"epoch": 1.61,
"learning_rate": 4.193865513173417e-05,
"loss": 1.3904,
"step": 20500
},
{
"epoch": 1.65,
"learning_rate": 4.1742036964215496e-05,
"loss": 1.377,
"step": 21000
},
{
"epoch": 1.69,
"learning_rate": 4.1545418796696815e-05,
"loss": 1.3735,
"step": 21500
},
{
"epoch": 1.73,
"learning_rate": 4.134880062917813e-05,
"loss": 1.364,
"step": 22000
},
{
"epoch": 1.77,
"learning_rate": 4.115218246165946e-05,
"loss": 1.3605,
"step": 22500
},
{
"epoch": 1.81,
"learning_rate": 4.095556429414078e-05,
"loss": 1.3539,
"step": 23000
},
{
"epoch": 1.85,
"learning_rate": 4.07589461266221e-05,
"loss": 1.3397,
"step": 23500
},
{
"epoch": 1.89,
"learning_rate": 4.0562327959103426e-05,
"loss": 1.3326,
"step": 24000
},
{
"epoch": 1.93,
"learning_rate": 4.0365709791584744e-05,
"loss": 1.3295,
"step": 24500
},
{
"epoch": 1.97,
"learning_rate": 4.016909162406606e-05,
"loss": 1.3297,
"step": 25000
},
{
"epoch": 2.01,
"learning_rate": 3.997247345654739e-05,
"loss": 1.312,
"step": 25500
},
{
"epoch": 2.04,
"learning_rate": 3.9775855289028706e-05,
"loss": 1.2981,
"step": 26000
},
{
"epoch": 2.08,
"learning_rate": 3.957923712151003e-05,
"loss": 1.2988,
"step": 26500
},
{
"epoch": 2.12,
"learning_rate": 3.938261895399135e-05,
"loss": 1.289,
"step": 27000
},
{
"epoch": 2.16,
"learning_rate": 3.9186000786472674e-05,
"loss": 1.2861,
"step": 27500
},
{
"epoch": 2.2,
"learning_rate": 3.8989382618954e-05,
"loss": 1.2823,
"step": 28000
},
{
"epoch": 2.24,
"learning_rate": 3.879276445143532e-05,
"loss": 1.2718,
"step": 28500
},
{
"epoch": 2.28,
"learning_rate": 3.8596146283916635e-05,
"loss": 1.2673,
"step": 29000
},
{
"epoch": 2.32,
"learning_rate": 3.839952811639796e-05,
"loss": 1.2672,
"step": 29500
},
{
"epoch": 2.36,
"learning_rate": 3.820290994887928e-05,
"loss": 1.2538,
"step": 30000
},
{
"epoch": 2.4,
"learning_rate": 3.80062917813606e-05,
"loss": 1.2533,
"step": 30500
},
{
"epoch": 2.44,
"learning_rate": 3.780967361384192e-05,
"loss": 1.2519,
"step": 31000
},
{
"epoch": 2.48,
"learning_rate": 3.761305544632324e-05,
"loss": 1.2437,
"step": 31500
},
{
"epoch": 2.52,
"learning_rate": 3.741643727880456e-05,
"loss": 1.2363,
"step": 32000
},
{
"epoch": 2.56,
"learning_rate": 3.721981911128588e-05,
"loss": 1.2397,
"step": 32500
},
{
"epoch": 2.6,
"learning_rate": 3.702320094376721e-05,
"loss": 1.2328,
"step": 33000
},
{
"epoch": 2.63,
"learning_rate": 3.6826582776248526e-05,
"loss": 1.2336,
"step": 33500
},
{
"epoch": 2.67,
"learning_rate": 3.662996460872985e-05,
"loss": 1.2271,
"step": 34000
},
{
"epoch": 2.71,
"learning_rate": 3.643334644121117e-05,
"loss": 1.2199,
"step": 34500
},
{
"epoch": 2.75,
"learning_rate": 3.623672827369249e-05,
"loss": 1.2167,
"step": 35000
},
{
"epoch": 2.79,
"learning_rate": 3.604011010617381e-05,
"loss": 1.2115,
"step": 35500
},
{
"epoch": 2.83,
"learning_rate": 3.584349193865513e-05,
"loss": 1.2095,
"step": 36000
},
{
"epoch": 2.87,
"learning_rate": 3.564687377113645e-05,
"loss": 1.2043,
"step": 36500
},
{
"epoch": 2.91,
"learning_rate": 3.5450255603617774e-05,
"loss": 1.2029,
"step": 37000
},
{
"epoch": 2.95,
"learning_rate": 3.52536374360991e-05,
"loss": 1.1952,
"step": 37500
},
{
"epoch": 2.99,
"learning_rate": 3.5057019268580424e-05,
"loss": 1.1916,
"step": 38000
},
{
"epoch": 3.03,
"learning_rate": 3.486040110106174e-05,
"loss": 1.183,
"step": 38500
},
{
"epoch": 3.07,
"learning_rate": 3.466378293354306e-05,
"loss": 1.1823,
"step": 39000
},
{
"epoch": 3.11,
"learning_rate": 3.4467164766024386e-05,
"loss": 1.1806,
"step": 39500
},
{
"epoch": 3.15,
"learning_rate": 3.4270546598505704e-05,
"loss": 1.182,
"step": 40000
},
{
"epoch": 3.19,
"learning_rate": 3.407392843098702e-05,
"loss": 1.1705,
"step": 40500
},
{
"epoch": 3.22,
"learning_rate": 3.387731026346835e-05,
"loss": 1.174,
"step": 41000
},
{
"epoch": 3.26,
"learning_rate": 3.3680692095949665e-05,
"loss": 1.1634,
"step": 41500
},
{
"epoch": 3.3,
"learning_rate": 3.3484073928430984e-05,
"loss": 1.1655,
"step": 42000
},
{
"epoch": 3.34,
"learning_rate": 3.328745576091231e-05,
"loss": 1.1622,
"step": 42500
},
{
"epoch": 3.38,
"learning_rate": 3.3090837593393633e-05,
"loss": 1.161,
"step": 43000
},
{
"epoch": 3.42,
"learning_rate": 3.289421942587495e-05,
"loss": 1.1495,
"step": 43500
},
{
"epoch": 3.46,
"learning_rate": 3.269760125835628e-05,
"loss": 1.1522,
"step": 44000
},
{
"epoch": 3.5,
"learning_rate": 3.2500983090837595e-05,
"loss": 1.1483,
"step": 44500
},
{
"epoch": 3.54,
"learning_rate": 3.230436492331891e-05,
"loss": 1.1516,
"step": 45000
},
{
"epoch": 3.58,
"learning_rate": 3.210774675580024e-05,
"loss": 1.1475,
"step": 45500
},
{
"epoch": 3.62,
"learning_rate": 3.1911128588281556e-05,
"loss": 1.1386,
"step": 46000
},
{
"epoch": 3.66,
"learning_rate": 3.1714510420762875e-05,
"loss": 1.142,
"step": 46500
},
{
"epoch": 3.7,
"learning_rate": 3.15178922532442e-05,
"loss": 1.1403,
"step": 47000
},
{
"epoch": 3.74,
"learning_rate": 3.1321274085725525e-05,
"loss": 1.1328,
"step": 47500
},
{
"epoch": 3.78,
"learning_rate": 3.112465591820685e-05,
"loss": 1.1257,
"step": 48000
},
{
"epoch": 3.81,
"learning_rate": 3.092803775068817e-05,
"loss": 1.1259,
"step": 48500
},
{
"epoch": 3.85,
"learning_rate": 3.0731419583169486e-05,
"loss": 1.128,
"step": 49000
},
{
"epoch": 3.89,
"learning_rate": 3.053480141565081e-05,
"loss": 1.1299,
"step": 49500
},
{
"epoch": 3.93,
"learning_rate": 3.033818324813213e-05,
"loss": 1.1285,
"step": 50000
},
{
"epoch": 3.97,
"learning_rate": 3.0141565080613447e-05,
"loss": 1.1224,
"step": 50500
},
{
"epoch": 4.01,
"learning_rate": 2.9944946913094772e-05,
"loss": 1.116,
"step": 51000
},
{
"epoch": 4.05,
"learning_rate": 2.9748328745576094e-05,
"loss": 1.1125,
"step": 51500
},
{
"epoch": 4.09,
"learning_rate": 2.9551710578057412e-05,
"loss": 1.1031,
"step": 52000
},
{
"epoch": 4.13,
"learning_rate": 2.9355092410538737e-05,
"loss": 1.1091,
"step": 52500
},
{
"epoch": 4.17,
"learning_rate": 2.9158474243020055e-05,
"loss": 1.1058,
"step": 53000
},
{
"epoch": 4.21,
"learning_rate": 2.8961856075501377e-05,
"loss": 1.1025,
"step": 53500
},
{
"epoch": 4.25,
"learning_rate": 2.8765237907982702e-05,
"loss": 1.1076,
"step": 54000
},
{
"epoch": 4.29,
"learning_rate": 2.856861974046402e-05,
"loss": 1.1052,
"step": 54500
},
{
"epoch": 4.33,
"learning_rate": 2.837200157294534e-05,
"loss": 1.0995,
"step": 55000
},
{
"epoch": 4.36,
"learning_rate": 2.8175383405426664e-05,
"loss": 1.0948,
"step": 55500
},
{
"epoch": 4.4,
"learning_rate": 2.7978765237907985e-05,
"loss": 1.0985,
"step": 56000
},
{
"epoch": 4.44,
"learning_rate": 2.7782147070389303e-05,
"loss": 1.0969,
"step": 56500
},
{
"epoch": 4.48,
"learning_rate": 2.758552890287063e-05,
"loss": 1.0921,
"step": 57000
},
{
"epoch": 4.52,
"learning_rate": 2.7388910735351947e-05,
"loss": 1.0913,
"step": 57500
},
{
"epoch": 4.56,
"learning_rate": 2.719229256783327e-05,
"loss": 1.0883,
"step": 58000
},
{
"epoch": 4.6,
"learning_rate": 2.699567440031459e-05,
"loss": 1.0859,
"step": 58500
},
{
"epoch": 4.64,
"learning_rate": 2.679905623279591e-05,
"loss": 1.0898,
"step": 59000
},
{
"epoch": 4.68,
"learning_rate": 2.6602438065277236e-05,
"loss": 1.0809,
"step": 59500
},
{
"epoch": 4.72,
"learning_rate": 2.6405819897758555e-05,
"loss": 1.084,
"step": 60000
},
{
"epoch": 4.76,
"learning_rate": 2.6209201730239873e-05,
"loss": 1.0767,
"step": 60500
},
{
"epoch": 4.8,
"learning_rate": 2.6012583562721198e-05,
"loss": 1.0709,
"step": 61000
},
{
"epoch": 4.84,
"learning_rate": 2.581596539520252e-05,
"loss": 1.0789,
"step": 61500
},
{
"epoch": 4.88,
"learning_rate": 2.5619347227683838e-05,
"loss": 1.0779,
"step": 62000
},
{
"epoch": 4.92,
"learning_rate": 2.5422729060165163e-05,
"loss": 1.0732,
"step": 62500
},
{
"epoch": 4.95,
"learning_rate": 2.522611089264648e-05,
"loss": 1.0718,
"step": 63000
},
{
"epoch": 4.99,
"learning_rate": 2.5029492725127802e-05,
"loss": 1.0665,
"step": 63500
},
{
"epoch": 5.03,
"learning_rate": 2.4832874557609124e-05,
"loss": 1.0673,
"step": 64000
},
{
"epoch": 5.07,
"learning_rate": 2.4636256390090446e-05,
"loss": 1.0603,
"step": 64500
},
{
"epoch": 5.11,
"learning_rate": 2.4439638222571767e-05,
"loss": 1.0557,
"step": 65000
},
{
"epoch": 5.15,
"learning_rate": 2.4243020055053085e-05,
"loss": 1.0563,
"step": 65500
},
{
"epoch": 5.19,
"learning_rate": 2.404640188753441e-05,
"loss": 1.0557,
"step": 66000
},
{
"epoch": 5.23,
"learning_rate": 2.3849783720015732e-05,
"loss": 1.0586,
"step": 66500
},
{
"epoch": 5.27,
"learning_rate": 2.3653165552497054e-05,
"loss": 1.0574,
"step": 67000
},
{
"epoch": 5.31,
"learning_rate": 2.3456547384978372e-05,
"loss": 1.0578,
"step": 67500
},
{
"epoch": 5.35,
"learning_rate": 2.3259929217459694e-05,
"loss": 1.0569,
"step": 68000
},
{
"epoch": 5.39,
"learning_rate": 2.3063311049941015e-05,
"loss": 1.0541,
"step": 68500
},
{
"epoch": 5.43,
"learning_rate": 2.2866692882422337e-05,
"loss": 1.0532,
"step": 69000
},
{
"epoch": 5.47,
"learning_rate": 2.267007471490366e-05,
"loss": 1.0538,
"step": 69500
},
{
"epoch": 5.51,
"learning_rate": 2.247345654738498e-05,
"loss": 1.0467,
"step": 70000
},
{
"epoch": 5.54,
"learning_rate": 2.2276838379866298e-05,
"loss": 1.0483,
"step": 70500
},
{
"epoch": 5.58,
"learning_rate": 2.2080220212347623e-05,
"loss": 1.0565,
"step": 71000
},
{
"epoch": 5.62,
"learning_rate": 2.1883602044828945e-05,
"loss": 1.0494,
"step": 71500
},
{
"epoch": 5.66,
"learning_rate": 2.1686983877310266e-05,
"loss": 1.0423,
"step": 72000
},
{
"epoch": 5.7,
"learning_rate": 2.1490365709791585e-05,
"loss": 1.0449,
"step": 72500
},
{
"epoch": 5.74,
"learning_rate": 2.1293747542272906e-05,
"loss": 1.0447,
"step": 73000
},
{
"epoch": 5.78,
"learning_rate": 2.1097129374754228e-05,
"loss": 1.0411,
"step": 73500
},
{
"epoch": 5.82,
"learning_rate": 2.090051120723555e-05,
"loss": 1.0424,
"step": 74000
},
{
"epoch": 5.86,
"learning_rate": 2.070389303971687e-05,
"loss": 1.0394,
"step": 74500
},
{
"epoch": 5.9,
"learning_rate": 2.0507274872198193e-05,
"loss": 1.035,
"step": 75000
},
{
"epoch": 5.94,
"learning_rate": 2.031065670467951e-05,
"loss": 1.0343,
"step": 75500
},
{
"epoch": 5.98,
"learning_rate": 2.0114038537160836e-05,
"loss": 1.0371,
"step": 76000
},
{
"epoch": 6.02,
"learning_rate": 1.9917420369642157e-05,
"loss": 1.0269,
"step": 76500
},
{
"epoch": 6.06,
"learning_rate": 1.972080220212348e-05,
"loss": 1.0361,
"step": 77000
},
{
"epoch": 6.1,
"learning_rate": 1.9524184034604797e-05,
"loss": 1.0291,
"step": 77500
},
{
"epoch": 6.13,
"learning_rate": 1.932756586708612e-05,
"loss": 1.0275,
"step": 78000
},
{
"epoch": 6.17,
"learning_rate": 1.913094769956744e-05,
"loss": 1.0308,
"step": 78500
},
{
"epoch": 6.21,
"learning_rate": 1.8934329532048762e-05,
"loss": 1.0259,
"step": 79000
},
{
"epoch": 6.25,
"learning_rate": 1.8737711364530084e-05,
"loss": 1.0238,
"step": 79500
},
{
"epoch": 6.29,
"learning_rate": 1.8541093197011405e-05,
"loss": 1.0263,
"step": 80000
},
{
"epoch": 6.33,
"learning_rate": 1.8344475029492724e-05,
"loss": 1.024,
"step": 80500
},
{
"epoch": 6.37,
"learning_rate": 1.814785686197405e-05,
"loss": 1.0217,
"step": 81000
},
{
"epoch": 6.41,
"learning_rate": 1.795123869445537e-05,
"loss": 1.0229,
"step": 81500
},
{
"epoch": 6.45,
"learning_rate": 1.7754620526936692e-05,
"loss": 1.0211,
"step": 82000
},
{
"epoch": 6.49,
"learning_rate": 1.755800235941801e-05,
"loss": 1.0143,
"step": 82500
},
{
"epoch": 6.53,
"learning_rate": 1.736138419189933e-05,
"loss": 1.0234,
"step": 83000
},
{
"epoch": 6.57,
"learning_rate": 1.7164766024380653e-05,
"loss": 1.0182,
"step": 83500
},
{
"epoch": 6.61,
"learning_rate": 1.6968147856861975e-05,
"loss": 1.0163,
"step": 84000
},
{
"epoch": 6.65,
"learning_rate": 1.6771529689343296e-05,
"loss": 1.0143,
"step": 84500
},
{
"epoch": 6.69,
"learning_rate": 1.6574911521824618e-05,
"loss": 1.0184,
"step": 85000
},
{
"epoch": 6.72,
"learning_rate": 1.6378293354305936e-05,
"loss": 1.0183,
"step": 85500
},
{
"epoch": 6.76,
"learning_rate": 1.618167518678726e-05,
"loss": 1.0174,
"step": 86000
},
{
"epoch": 6.8,
"learning_rate": 1.5985057019268583e-05,
"loss": 1.0151,
"step": 86500
},
{
"epoch": 6.84,
"learning_rate": 1.5788438851749904e-05,
"loss": 1.0116,
"step": 87000
},
{
"epoch": 6.88,
"learning_rate": 1.5591820684231223e-05,
"loss": 1.0114,
"step": 87500
},
{
"epoch": 6.92,
"learning_rate": 1.5395202516712544e-05,
"loss": 1.0144,
"step": 88000
},
{
"epoch": 6.96,
"learning_rate": 1.5198584349193868e-05,
"loss": 1.0106,
"step": 88500
},
{
"epoch": 7.0,
"learning_rate": 1.5001966181675187e-05,
"loss": 1.0196,
"step": 89000
},
{
"epoch": 7.04,
"learning_rate": 1.4805348014156509e-05,
"loss": 1.0041,
"step": 89500
},
{
"epoch": 7.08,
"learning_rate": 1.460872984663783e-05,
"loss": 1.0061,
"step": 90000
},
{
"epoch": 7.12,
"learning_rate": 1.441211167911915e-05,
"loss": 1.0013,
"step": 90500
},
{
"epoch": 7.16,
"learning_rate": 1.4215493511600472e-05,
"loss": 1.0085,
"step": 91000
},
{
"epoch": 7.2,
"learning_rate": 1.4018875344081794e-05,
"loss": 1.0028,
"step": 91500
},
{
"epoch": 7.24,
"learning_rate": 1.3822257176563117e-05,
"loss": 1.0028,
"step": 92000
},
{
"epoch": 7.27,
"learning_rate": 1.3625639009044435e-05,
"loss": 0.9988,
"step": 92500
},
{
"epoch": 7.31,
"learning_rate": 1.3429020841525759e-05,
"loss": 1.0067,
"step": 93000
},
{
"epoch": 7.35,
"learning_rate": 1.323240267400708e-05,
"loss": 1.0072,
"step": 93500
},
{
"epoch": 7.39,
"learning_rate": 1.30357845064884e-05,
"loss": 1.0001,
"step": 94000
},
{
"epoch": 7.43,
"learning_rate": 1.2839166338969722e-05,
"loss": 1.0012,
"step": 94500
},
{
"epoch": 7.47,
"learning_rate": 1.2642548171451043e-05,
"loss": 1.0003,
"step": 95000
},
{
"epoch": 7.51,
"learning_rate": 1.2445930003932365e-05,
"loss": 0.9877,
"step": 95500
},
{
"epoch": 7.55,
"learning_rate": 1.2249311836413685e-05,
"loss": 1.0001,
"step": 96000
},
{
"epoch": 7.59,
"learning_rate": 1.2052693668895006e-05,
"loss": 0.9954,
"step": 96500
},
{
"epoch": 7.63,
"learning_rate": 1.1856075501376328e-05,
"loss": 0.9963,
"step": 97000
},
{
"epoch": 7.67,
"learning_rate": 1.1659457333857648e-05,
"loss": 0.994,
"step": 97500
},
{
"epoch": 7.71,
"learning_rate": 1.1462839166338971e-05,
"loss": 1.003,
"step": 98000
},
{
"epoch": 7.75,
"learning_rate": 1.1266220998820291e-05,
"loss": 0.9931,
"step": 98500
},
{
"epoch": 7.79,
"learning_rate": 1.1069602831301613e-05,
"loss": 0.9983,
"step": 99000
},
{
"epoch": 7.83,
"learning_rate": 1.0872984663782934e-05,
"loss": 0.9922,
"step": 99500
},
{
"epoch": 7.86,
"learning_rate": 1.0676366496264254e-05,
"loss": 0.9968,
"step": 100000
},
{
"epoch": 7.9,
"learning_rate": 1.0479748328745578e-05,
"loss": 0.9956,
"step": 100500
},
{
"epoch": 7.94,
"learning_rate": 1.0283130161226898e-05,
"loss": 0.991,
"step": 101000
},
{
"epoch": 7.98,
"learning_rate": 1.008651199370822e-05,
"loss": 0.9915,
"step": 101500
},
{
"epoch": 8.02,
"learning_rate": 9.88989382618954e-06,
"loss": 0.9859,
"step": 102000
},
{
"epoch": 8.06,
"learning_rate": 9.69327565867086e-06,
"loss": 0.986,
"step": 102500
},
{
"epoch": 8.1,
"learning_rate": 9.496657491152184e-06,
"loss": 0.9937,
"step": 103000
},
{
"epoch": 8.14,
"learning_rate": 9.300039323633504e-06,
"loss": 0.9863,
"step": 103500
},
{
"epoch": 8.18,
"learning_rate": 9.103421156114826e-06,
"loss": 0.9836,
"step": 104000
},
{
"epoch": 8.22,
"learning_rate": 8.906802988596147e-06,
"loss": 0.9857,
"step": 104500
},
{
"epoch": 8.26,
"learning_rate": 8.710184821077467e-06,
"loss": 0.989,
"step": 105000
},
{
"epoch": 8.3,
"learning_rate": 8.51356665355879e-06,
"loss": 0.9886,
"step": 105500
},
{
"epoch": 8.34,
"learning_rate": 8.31694848604011e-06,
"loss": 0.9885,
"step": 106000
},
{
"epoch": 8.38,
"learning_rate": 8.120330318521432e-06,
"loss": 0.9847,
"step": 106500
},
{
"epoch": 8.42,
"learning_rate": 7.923712151002753e-06,
"loss": 0.9846,
"step": 107000
},
{
"epoch": 8.45,
"learning_rate": 7.727093983484073e-06,
"loss": 0.9882,
"step": 107500
},
{
"epoch": 8.49,
"learning_rate": 7.530475815965396e-06,
"loss": 0.9866,
"step": 108000
},
{
"epoch": 8.53,
"learning_rate": 7.333857648446717e-06,
"loss": 0.9823,
"step": 108500
},
{
"epoch": 8.57,
"learning_rate": 7.137239480928037e-06,
"loss": 0.9841,
"step": 109000
},
{
"epoch": 8.61,
"learning_rate": 6.94062131340936e-06,
"loss": 0.9844,
"step": 109500
},
{
"epoch": 8.65,
"learning_rate": 6.7440031458906806e-06,
"loss": 0.9817,
"step": 110000
},
{
"epoch": 8.69,
"learning_rate": 6.547384978372002e-06,
"loss": 0.9854,
"step": 110500
},
{
"epoch": 8.73,
"learning_rate": 6.350766810853323e-06,
"loss": 0.9845,
"step": 111000
},
{
"epoch": 8.77,
"learning_rate": 6.1541486433346445e-06,
"loss": 0.984,
"step": 111500
},
{
"epoch": 8.81,
"learning_rate": 5.957530475815966e-06,
"loss": 0.9865,
"step": 112000
},
{
"epoch": 8.85,
"learning_rate": 5.760912308297287e-06,
"loss": 0.9765,
"step": 112500
},
{
"epoch": 8.89,
"learning_rate": 5.564294140778608e-06,
"loss": 0.9867,
"step": 113000
},
{
"epoch": 8.93,
"learning_rate": 5.367675973259929e-06,
"loss": 0.986,
"step": 113500
},
{
"epoch": 8.97,
"learning_rate": 5.171057805741251e-06,
"loss": 0.9817,
"step": 114000
},
{
"epoch": 9.01,
"learning_rate": 4.9744396382225725e-06,
"loss": 0.9774,
"step": 114500
},
{
"epoch": 9.04,
"learning_rate": 4.777821470703893e-06,
"loss": 0.9811,
"step": 115000
},
{
"epoch": 9.08,
"learning_rate": 4.581203303185214e-06,
"loss": 0.9759,
"step": 115500
},
{
"epoch": 9.12,
"learning_rate": 4.384585135666536e-06,
"loss": 0.9769,
"step": 116000
},
{
"epoch": 9.16,
"learning_rate": 4.187966968147857e-06,
"loss": 0.9807,
"step": 116500
},
{
"epoch": 9.2,
"learning_rate": 3.991348800629179e-06,
"loss": 0.9822,
"step": 117000
},
{
"epoch": 9.24,
"learning_rate": 3.794730633110499e-06,
"loss": 0.9843,
"step": 117500
},
{
"epoch": 9.28,
"learning_rate": 3.5981124655918208e-06,
"loss": 0.9777,
"step": 118000
},
{
"epoch": 9.32,
"learning_rate": 3.401494298073142e-06,
"loss": 0.977,
"step": 118500
},
{
"epoch": 9.36,
"learning_rate": 3.2048761305544636e-06,
"loss": 0.9785,
"step": 119000
},
{
"epoch": 9.4,
"learning_rate": 3.0082579630357847e-06,
"loss": 0.9756,
"step": 119500
},
{
"epoch": 9.44,
"learning_rate": 2.811639795517106e-06,
"loss": 0.9803,
"step": 120000
},
{
"epoch": 9.48,
"learning_rate": 2.615021627998427e-06,
"loss": 0.9774,
"step": 120500
},
{
"epoch": 9.52,
"learning_rate": 2.4184034604797483e-06,
"loss": 0.984,
"step": 121000
},
{
"epoch": 9.56,
"learning_rate": 2.22178529296107e-06,
"loss": 0.9753,
"step": 121500
},
{
"epoch": 9.59,
"learning_rate": 2.025167125442391e-06,
"loss": 0.9764,
"step": 122000
},
{
"epoch": 9.63,
"learning_rate": 1.8285489579237123e-06,
"loss": 0.9756,
"step": 122500
},
{
"epoch": 9.67,
"learning_rate": 1.6319307904050335e-06,
"loss": 0.9733,
"step": 123000
},
{
"epoch": 9.71,
"learning_rate": 1.4353126228863549e-06,
"loss": 0.9726,
"step": 123500
},
{
"epoch": 9.75,
"learning_rate": 1.238694455367676e-06,
"loss": 0.9783,
"step": 124000
},
{
"epoch": 9.79,
"learning_rate": 1.0420762878489972e-06,
"loss": 0.9786,
"step": 124500
},
{
"epoch": 9.83,
"learning_rate": 8.454581203303186e-07,
"loss": 0.9802,
"step": 125000
},
{
"epoch": 9.87,
"learning_rate": 6.488399528116398e-07,
"loss": 0.979,
"step": 125500
},
{
"epoch": 9.91,
"learning_rate": 4.522217852929611e-07,
"loss": 0.978,
"step": 126000
},
{
"epoch": 9.95,
"learning_rate": 2.556036177742823e-07,
"loss": 0.9718,
"step": 126500
},
{
"epoch": 9.99,
"learning_rate": 5.898545025560362e-08,
"loss": 0.9811,
"step": 127000
},
{
"epoch": 10.0,
"step": 127150,
"total_flos": 5.807966088205763e+17,
"train_loss": 1.219492632603017,
"train_runtime": 160361.9384,
"train_samples_per_second": 38.059,
"train_steps_per_second": 0.793
}
],
"max_steps": 127150,
"num_train_epochs": 10,
"total_flos": 5.807966088205763e+17,
"trial_name": null,
"trial_params": null
}