HBERTv1_48_L10_H768_A12 / trainer_state.json
gokuls's picture
End of training
8deb113
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.1529425258791255,
"eval_steps": 1000000,
"global_step": 225243,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 9.9239,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 1.0000000000000002e-06,
"loss": 9.1673,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 8.7549,
"step": 1500
},
{
"epoch": 0.02,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.2851,
"step": 2000
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 7.7885,
"step": 2500
},
{
"epoch": 0.03,
"learning_rate": 3e-06,
"loss": 7.4014,
"step": 3000
},
{
"epoch": 0.03,
"learning_rate": 3.5e-06,
"loss": 7.1544,
"step": 3500
},
{
"epoch": 0.04,
"learning_rate": 4.000000000000001e-06,
"loss": 7.0253,
"step": 4000
},
{
"epoch": 0.04,
"learning_rate": 4.5e-06,
"loss": 6.9305,
"step": 4500
},
{
"epoch": 0.05,
"learning_rate": 5e-06,
"loss": 6.8678,
"step": 5000
},
{
"epoch": 0.05,
"learning_rate": 5.500000000000001e-06,
"loss": 6.814,
"step": 5500
},
{
"epoch": 0.06,
"learning_rate": 6e-06,
"loss": 6.7725,
"step": 6000
},
{
"epoch": 0.06,
"learning_rate": 6.5000000000000004e-06,
"loss": 6.734,
"step": 6500
},
{
"epoch": 0.07,
"learning_rate": 7e-06,
"loss": 6.6882,
"step": 7000
},
{
"epoch": 0.07,
"learning_rate": 7.500000000000001e-06,
"loss": 6.6641,
"step": 7500
},
{
"epoch": 0.08,
"learning_rate": 8.000000000000001e-06,
"loss": 6.6342,
"step": 8000
},
{
"epoch": 0.08,
"learning_rate": 8.5e-06,
"loss": 6.6129,
"step": 8500
},
{
"epoch": 0.09,
"learning_rate": 9e-06,
"loss": 6.5907,
"step": 9000
},
{
"epoch": 0.09,
"learning_rate": 9.5e-06,
"loss": 6.5534,
"step": 9500
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 6.5351,
"step": 10000
},
{
"epoch": 0.1,
"learning_rate": 9.999521627232806e-06,
"loss": 6.5133,
"step": 10500
},
{
"epoch": 0.11,
"learning_rate": 9.99904325446561e-06,
"loss": 6.4921,
"step": 11000
},
{
"epoch": 0.11,
"learning_rate": 9.998564881698415e-06,
"loss": 6.472,
"step": 11500
},
{
"epoch": 0.11,
"learning_rate": 9.99808650893122e-06,
"loss": 6.4614,
"step": 12000
},
{
"epoch": 0.12,
"learning_rate": 9.997608136164025e-06,
"loss": 6.4463,
"step": 12500
},
{
"epoch": 0.12,
"learning_rate": 9.99712976339683e-06,
"loss": 6.4302,
"step": 13000
},
{
"epoch": 0.13,
"learning_rate": 9.996651390629635e-06,
"loss": 6.4184,
"step": 13500
},
{
"epoch": 0.13,
"learning_rate": 9.99617301786244e-06,
"loss": 6.4077,
"step": 14000
},
{
"epoch": 0.14,
"learning_rate": 9.995694645095244e-06,
"loss": 6.3951,
"step": 14500
},
{
"epoch": 0.14,
"learning_rate": 9.99521627232805e-06,
"loss": 6.3849,
"step": 15000
},
{
"epoch": 0.15,
"learning_rate": 9.994737899560854e-06,
"loss": 6.3742,
"step": 15500
},
{
"epoch": 0.15,
"learning_rate": 9.994259526793659e-06,
"loss": 6.3584,
"step": 16000
},
{
"epoch": 0.16,
"learning_rate": 9.993781154026464e-06,
"loss": 6.3541,
"step": 16500
},
{
"epoch": 0.16,
"learning_rate": 9.99330278125927e-06,
"loss": 6.338,
"step": 17000
},
{
"epoch": 0.17,
"learning_rate": 9.992824408492075e-06,
"loss": 6.3329,
"step": 17500
},
{
"epoch": 0.17,
"learning_rate": 9.992346035724878e-06,
"loss": 6.3238,
"step": 18000
},
{
"epoch": 0.18,
"learning_rate": 9.991867662957683e-06,
"loss": 6.3103,
"step": 18500
},
{
"epoch": 0.18,
"learning_rate": 9.991389290190488e-06,
"loss": 6.3042,
"step": 19000
},
{
"epoch": 0.19,
"learning_rate": 9.990910917423293e-06,
"loss": 6.3042,
"step": 19500
},
{
"epoch": 0.19,
"learning_rate": 9.9904325446561e-06,
"loss": 6.2976,
"step": 20000
},
{
"epoch": 0.2,
"learning_rate": 9.989954171888904e-06,
"loss": 6.2935,
"step": 20500
},
{
"epoch": 0.2,
"learning_rate": 9.989475799121709e-06,
"loss": 6.2808,
"step": 21000
},
{
"epoch": 0.21,
"learning_rate": 9.988997426354512e-06,
"loss": 6.2811,
"step": 21500
},
{
"epoch": 0.21,
"learning_rate": 9.988519053587317e-06,
"loss": 6.275,
"step": 22000
},
{
"epoch": 0.22,
"learning_rate": 9.988040680820124e-06,
"loss": 6.2721,
"step": 22500
},
{
"epoch": 0.22,
"learning_rate": 9.987562308052929e-06,
"loss": 6.2596,
"step": 23000
},
{
"epoch": 0.22,
"learning_rate": 9.987083935285733e-06,
"loss": 6.25,
"step": 23500
},
{
"epoch": 0.23,
"learning_rate": 9.986605562518538e-06,
"loss": 6.251,
"step": 24000
},
{
"epoch": 0.23,
"learning_rate": 9.986127189751343e-06,
"loss": 6.2465,
"step": 24500
},
{
"epoch": 0.24,
"learning_rate": 9.985648816984146e-06,
"loss": 6.2406,
"step": 25000
},
{
"epoch": 0.24,
"learning_rate": 9.985170444216953e-06,
"loss": 6.2365,
"step": 25500
},
{
"epoch": 0.25,
"learning_rate": 9.984692071449758e-06,
"loss": 6.2353,
"step": 26000
},
{
"epoch": 0.25,
"learning_rate": 9.984213698682562e-06,
"loss": 6.2313,
"step": 26500
},
{
"epoch": 0.26,
"learning_rate": 9.983735325915367e-06,
"loss": 6.2208,
"step": 27000
},
{
"epoch": 0.26,
"learning_rate": 9.983256953148172e-06,
"loss": 6.2279,
"step": 27500
},
{
"epoch": 0.27,
"learning_rate": 9.982778580380977e-06,
"loss": 6.2163,
"step": 28000
},
{
"epoch": 0.27,
"learning_rate": 9.982300207613782e-06,
"loss": 6.206,
"step": 28500
},
{
"epoch": 0.28,
"learning_rate": 9.981821834846587e-06,
"loss": 6.2043,
"step": 29000
},
{
"epoch": 0.28,
"learning_rate": 9.981343462079391e-06,
"loss": 6.2042,
"step": 29500
},
{
"epoch": 0.29,
"learning_rate": 9.980865089312196e-06,
"loss": 6.2034,
"step": 30000
},
{
"epoch": 0.29,
"learning_rate": 9.980386716545001e-06,
"loss": 6.201,
"step": 30500
},
{
"epoch": 0.3,
"learning_rate": 9.979908343777806e-06,
"loss": 6.1837,
"step": 31000
},
{
"epoch": 0.3,
"learning_rate": 9.979429971010611e-06,
"loss": 6.1866,
"step": 31500
},
{
"epoch": 0.31,
"learning_rate": 9.978951598243416e-06,
"loss": 6.1925,
"step": 32000
},
{
"epoch": 0.31,
"learning_rate": 9.97847322547622e-06,
"loss": 6.1772,
"step": 32500
},
{
"epoch": 0.32,
"learning_rate": 9.977994852709025e-06,
"loss": 6.1805,
"step": 33000
},
{
"epoch": 0.32,
"learning_rate": 9.977516479941832e-06,
"loss": 6.1788,
"step": 33500
},
{
"epoch": 0.32,
"learning_rate": 9.977038107174635e-06,
"loss": 6.1714,
"step": 34000
},
{
"epoch": 0.33,
"learning_rate": 9.97655973440744e-06,
"loss": 6.1686,
"step": 34500
},
{
"epoch": 0.33,
"learning_rate": 9.976081361640245e-06,
"loss": 6.1714,
"step": 35000
},
{
"epoch": 0.34,
"learning_rate": 9.97560298887305e-06,
"loss": 6.1704,
"step": 35500
},
{
"epoch": 0.34,
"learning_rate": 9.975124616105856e-06,
"loss": 6.1579,
"step": 36000
},
{
"epoch": 0.35,
"learning_rate": 9.974646243338661e-06,
"loss": 6.1669,
"step": 36500
},
{
"epoch": 0.35,
"learning_rate": 9.974167870571466e-06,
"loss": 6.1611,
"step": 37000
},
{
"epoch": 0.36,
"learning_rate": 9.973689497804269e-06,
"loss": 6.1548,
"step": 37500
},
{
"epoch": 0.36,
"learning_rate": 9.973211125037074e-06,
"loss": 6.1569,
"step": 38000
},
{
"epoch": 0.37,
"learning_rate": 9.972732752269879e-06,
"loss": 6.1528,
"step": 38500
},
{
"epoch": 0.37,
"learning_rate": 9.972254379502685e-06,
"loss": 6.1402,
"step": 39000
},
{
"epoch": 0.38,
"learning_rate": 9.97177600673549e-06,
"loss": 6.1469,
"step": 39500
},
{
"epoch": 0.38,
"learning_rate": 9.971297633968295e-06,
"loss": 6.1441,
"step": 40000
},
{
"epoch": 0.39,
"learning_rate": 9.9708192612011e-06,
"loss": 6.1391,
"step": 40500
},
{
"epoch": 0.39,
"learning_rate": 9.970340888433903e-06,
"loss": 6.1449,
"step": 41000
},
{
"epoch": 0.4,
"learning_rate": 9.96986251566671e-06,
"loss": 6.1341,
"step": 41500
},
{
"epoch": 0.4,
"learning_rate": 9.969384142899514e-06,
"loss": 6.1357,
"step": 42000
},
{
"epoch": 0.41,
"learning_rate": 9.96890577013232e-06,
"loss": 6.1371,
"step": 42500
},
{
"epoch": 0.41,
"learning_rate": 9.968427397365124e-06,
"loss": 6.1304,
"step": 43000
},
{
"epoch": 0.42,
"learning_rate": 9.967949024597929e-06,
"loss": 6.1308,
"step": 43500
},
{
"epoch": 0.42,
"learning_rate": 9.967470651830734e-06,
"loss": 6.1265,
"step": 44000
},
{
"epoch": 0.43,
"learning_rate": 9.966992279063539e-06,
"loss": 6.1159,
"step": 44500
},
{
"epoch": 0.43,
"learning_rate": 9.966513906296343e-06,
"loss": 6.1206,
"step": 45000
},
{
"epoch": 0.43,
"learning_rate": 9.966035533529148e-06,
"loss": 6.1177,
"step": 45500
},
{
"epoch": 0.44,
"learning_rate": 9.965557160761953e-06,
"loss": 6.1157,
"step": 46000
},
{
"epoch": 0.44,
"learning_rate": 9.965078787994758e-06,
"loss": 6.1145,
"step": 46500
},
{
"epoch": 0.45,
"learning_rate": 9.964600415227563e-06,
"loss": 6.106,
"step": 47000
},
{
"epoch": 0.45,
"learning_rate": 9.964122042460368e-06,
"loss": 6.1095,
"step": 47500
},
{
"epoch": 0.46,
"learning_rate": 9.963643669693172e-06,
"loss": 6.1017,
"step": 48000
},
{
"epoch": 0.46,
"learning_rate": 9.963165296925977e-06,
"loss": 6.0923,
"step": 48500
},
{
"epoch": 0.47,
"learning_rate": 9.962686924158782e-06,
"loss": 6.0763,
"step": 49000
},
{
"epoch": 0.47,
"learning_rate": 9.962208551391587e-06,
"loss": 6.057,
"step": 49500
},
{
"epoch": 0.48,
"learning_rate": 9.961730178624392e-06,
"loss": 6.0377,
"step": 50000
},
{
"epoch": 0.48,
"learning_rate": 9.961251805857197e-06,
"loss": 6.0221,
"step": 50500
},
{
"epoch": 0.49,
"learning_rate": 9.960773433090002e-06,
"loss": 6.0077,
"step": 51000
},
{
"epoch": 0.49,
"learning_rate": 9.960295060322806e-06,
"loss": 5.9924,
"step": 51500
},
{
"epoch": 0.5,
"learning_rate": 9.959816687555611e-06,
"loss": 5.985,
"step": 52000
},
{
"epoch": 0.5,
"learning_rate": 9.959338314788418e-06,
"loss": 5.9684,
"step": 52500
},
{
"epoch": 0.51,
"learning_rate": 9.958859942021221e-06,
"loss": 5.9564,
"step": 53000
},
{
"epoch": 0.51,
"learning_rate": 9.958381569254026e-06,
"loss": 5.9449,
"step": 53500
},
{
"epoch": 0.52,
"learning_rate": 9.95790319648683e-06,
"loss": 5.9338,
"step": 54000
},
{
"epoch": 0.52,
"learning_rate": 9.957424823719635e-06,
"loss": 5.9249,
"step": 54500
},
{
"epoch": 0.53,
"learning_rate": 9.95694645095244e-06,
"loss": 5.9231,
"step": 55000
},
{
"epoch": 0.53,
"learning_rate": 9.956468078185247e-06,
"loss": 5.9075,
"step": 55500
},
{
"epoch": 0.54,
"learning_rate": 9.955989705418052e-06,
"loss": 5.9082,
"step": 56000
},
{
"epoch": 0.54,
"learning_rate": 9.955511332650855e-06,
"loss": 5.899,
"step": 56500
},
{
"epoch": 0.54,
"learning_rate": 9.95503295988366e-06,
"loss": 5.8856,
"step": 57000
},
{
"epoch": 0.55,
"learning_rate": 9.954554587116465e-06,
"loss": 5.8841,
"step": 57500
},
{
"epoch": 0.55,
"learning_rate": 9.954076214349271e-06,
"loss": 5.8765,
"step": 58000
},
{
"epoch": 0.56,
"learning_rate": 9.953597841582076e-06,
"loss": 5.8661,
"step": 58500
},
{
"epoch": 0.56,
"learning_rate": 9.95311946881488e-06,
"loss": 5.8583,
"step": 59000
},
{
"epoch": 0.57,
"learning_rate": 9.952641096047686e-06,
"loss": 5.8525,
"step": 59500
},
{
"epoch": 0.57,
"learning_rate": 9.952162723280489e-06,
"loss": 5.8418,
"step": 60000
},
{
"epoch": 0.58,
"learning_rate": 9.951684350513294e-06,
"loss": 5.8411,
"step": 60500
},
{
"epoch": 0.58,
"learning_rate": 9.9512059777461e-06,
"loss": 5.8394,
"step": 61000
},
{
"epoch": 0.59,
"learning_rate": 9.950727604978905e-06,
"loss": 5.8241,
"step": 61500
},
{
"epoch": 0.59,
"learning_rate": 9.95024923221171e-06,
"loss": 5.8221,
"step": 62000
},
{
"epoch": 0.6,
"learning_rate": 9.949770859444515e-06,
"loss": 5.8117,
"step": 62500
},
{
"epoch": 0.6,
"learning_rate": 9.94929248667732e-06,
"loss": 5.8019,
"step": 63000
},
{
"epoch": 0.61,
"learning_rate": 9.948814113910124e-06,
"loss": 5.798,
"step": 63500
},
{
"epoch": 0.61,
"learning_rate": 9.94833574114293e-06,
"loss": 5.788,
"step": 64000
},
{
"epoch": 0.62,
"learning_rate": 9.947857368375734e-06,
"loss": 5.7772,
"step": 64500
},
{
"epoch": 0.62,
"learning_rate": 9.947378995608539e-06,
"loss": 5.7652,
"step": 65000
},
{
"epoch": 0.63,
"learning_rate": 9.946900622841344e-06,
"loss": 5.7641,
"step": 65500
},
{
"epoch": 0.63,
"learning_rate": 9.946422250074149e-06,
"loss": 5.7417,
"step": 66000
},
{
"epoch": 0.64,
"learning_rate": 9.945943877306953e-06,
"loss": 5.7279,
"step": 66500
},
{
"epoch": 0.64,
"learning_rate": 9.945465504539758e-06,
"loss": 5.7096,
"step": 67000
},
{
"epoch": 0.65,
"learning_rate": 9.944987131772563e-06,
"loss": 5.6962,
"step": 67500
},
{
"epoch": 0.65,
"learning_rate": 9.944508759005368e-06,
"loss": 5.6763,
"step": 68000
},
{
"epoch": 0.65,
"learning_rate": 9.944030386238173e-06,
"loss": 5.6662,
"step": 68500
},
{
"epoch": 0.66,
"learning_rate": 9.943552013470978e-06,
"loss": 5.6343,
"step": 69000
},
{
"epoch": 0.66,
"learning_rate": 9.943073640703783e-06,
"loss": 5.5925,
"step": 69500
},
{
"epoch": 0.67,
"learning_rate": 9.942595267936587e-06,
"loss": 5.5517,
"step": 70000
},
{
"epoch": 0.67,
"learning_rate": 9.942116895169392e-06,
"loss": 5.5147,
"step": 70500
},
{
"epoch": 0.68,
"learning_rate": 9.941638522402197e-06,
"loss": 5.4691,
"step": 71000
},
{
"epoch": 0.68,
"learning_rate": 9.941160149635002e-06,
"loss": 5.4319,
"step": 71500
},
{
"epoch": 0.69,
"learning_rate": 9.940681776867808e-06,
"loss": 5.3928,
"step": 72000
},
{
"epoch": 0.69,
"learning_rate": 9.940203404100612e-06,
"loss": 5.3468,
"step": 72500
},
{
"epoch": 0.7,
"learning_rate": 9.939725031333416e-06,
"loss": 5.3136,
"step": 73000
},
{
"epoch": 0.7,
"learning_rate": 9.939246658566221e-06,
"loss": 5.2761,
"step": 73500
},
{
"epoch": 0.71,
"learning_rate": 9.938768285799026e-06,
"loss": 5.2384,
"step": 74000
},
{
"epoch": 0.71,
"learning_rate": 9.938289913031833e-06,
"loss": 5.2061,
"step": 74500
},
{
"epoch": 0.72,
"learning_rate": 9.937811540264638e-06,
"loss": 5.1755,
"step": 75000
},
{
"epoch": 0.72,
"learning_rate": 9.937333167497442e-06,
"loss": 5.1405,
"step": 75500
},
{
"epoch": 0.73,
"learning_rate": 9.936854794730246e-06,
"loss": 5.11,
"step": 76000
},
{
"epoch": 0.73,
"learning_rate": 9.93637642196305e-06,
"loss": 5.0771,
"step": 76500
},
{
"epoch": 0.74,
"learning_rate": 9.935898049195855e-06,
"loss": 5.0511,
"step": 77000
},
{
"epoch": 0.74,
"learning_rate": 9.935419676428662e-06,
"loss": 5.0296,
"step": 77500
},
{
"epoch": 0.75,
"learning_rate": 9.934941303661467e-06,
"loss": 4.9985,
"step": 78000
},
{
"epoch": 0.75,
"learning_rate": 9.934462930894271e-06,
"loss": 4.9759,
"step": 78500
},
{
"epoch": 0.76,
"learning_rate": 9.933984558127076e-06,
"loss": 4.942,
"step": 79000
},
{
"epoch": 0.76,
"learning_rate": 9.93350618535988e-06,
"loss": 4.9226,
"step": 79500
},
{
"epoch": 0.76,
"learning_rate": 9.933027812592686e-06,
"loss": 4.8993,
"step": 80000
},
{
"epoch": 0.77,
"learning_rate": 9.932549439825491e-06,
"loss": 4.8738,
"step": 80500
},
{
"epoch": 0.77,
"learning_rate": 9.932071067058296e-06,
"loss": 4.8467,
"step": 81000
},
{
"epoch": 0.78,
"learning_rate": 9.9315926942911e-06,
"loss": 4.8251,
"step": 81500
},
{
"epoch": 0.78,
"learning_rate": 9.931114321523905e-06,
"loss": 4.813,
"step": 82000
},
{
"epoch": 0.79,
"learning_rate": 9.93063594875671e-06,
"loss": 4.784,
"step": 82500
},
{
"epoch": 0.79,
"learning_rate": 9.930157575989515e-06,
"loss": 4.7694,
"step": 83000
},
{
"epoch": 0.8,
"learning_rate": 9.92967920322232e-06,
"loss": 4.7434,
"step": 83500
},
{
"epoch": 0.8,
"learning_rate": 9.929200830455125e-06,
"loss": 4.7263,
"step": 84000
},
{
"epoch": 0.81,
"learning_rate": 9.92872245768793e-06,
"loss": 4.7086,
"step": 84500
},
{
"epoch": 0.81,
"learning_rate": 9.928244084920734e-06,
"loss": 4.6852,
"step": 85000
},
{
"epoch": 0.82,
"learning_rate": 9.92776571215354e-06,
"loss": 4.6643,
"step": 85500
},
{
"epoch": 0.82,
"learning_rate": 9.927287339386344e-06,
"loss": 4.6441,
"step": 86000
},
{
"epoch": 0.83,
"learning_rate": 9.926808966619149e-06,
"loss": 4.624,
"step": 86500
},
{
"epoch": 0.83,
"learning_rate": 9.926330593851954e-06,
"loss": 4.5976,
"step": 87000
},
{
"epoch": 0.84,
"learning_rate": 9.925852221084759e-06,
"loss": 4.5814,
"step": 87500
},
{
"epoch": 0.84,
"learning_rate": 9.925373848317564e-06,
"loss": 4.5606,
"step": 88000
},
{
"epoch": 0.85,
"learning_rate": 9.924895475550368e-06,
"loss": 4.5413,
"step": 88500
},
{
"epoch": 0.85,
"learning_rate": 9.924417102783173e-06,
"loss": 4.5017,
"step": 89000
},
{
"epoch": 0.86,
"learning_rate": 9.923938730015978e-06,
"loss": 4.4623,
"step": 89500
},
{
"epoch": 0.86,
"learning_rate": 9.923460357248783e-06,
"loss": 4.4205,
"step": 90000
},
{
"epoch": 0.87,
"learning_rate": 9.922981984481588e-06,
"loss": 4.3811,
"step": 90500
},
{
"epoch": 0.87,
"learning_rate": 9.922503611714394e-06,
"loss": 4.3612,
"step": 91000
},
{
"epoch": 0.87,
"learning_rate": 9.922025238947197e-06,
"loss": 4.3201,
"step": 91500
},
{
"epoch": 0.88,
"learning_rate": 9.921546866180002e-06,
"loss": 4.3,
"step": 92000
},
{
"epoch": 0.88,
"learning_rate": 9.921068493412807e-06,
"loss": 4.2616,
"step": 92500
},
{
"epoch": 0.89,
"learning_rate": 9.920590120645612e-06,
"loss": 4.2337,
"step": 93000
},
{
"epoch": 0.89,
"learning_rate": 9.920111747878419e-06,
"loss": 4.2122,
"step": 93500
},
{
"epoch": 0.9,
"learning_rate": 9.919633375111223e-06,
"loss": 4.185,
"step": 94000
},
{
"epoch": 0.9,
"learning_rate": 9.919155002344028e-06,
"loss": 4.162,
"step": 94500
},
{
"epoch": 0.91,
"learning_rate": 9.918676629576831e-06,
"loss": 4.1374,
"step": 95000
},
{
"epoch": 0.91,
"learning_rate": 9.918198256809636e-06,
"loss": 4.1102,
"step": 95500
},
{
"epoch": 0.92,
"learning_rate": 9.917719884042441e-06,
"loss": 4.0982,
"step": 96000
},
{
"epoch": 0.92,
"learning_rate": 9.917241511275248e-06,
"loss": 4.0628,
"step": 96500
},
{
"epoch": 0.93,
"learning_rate": 9.916763138508052e-06,
"loss": 4.0464,
"step": 97000
},
{
"epoch": 0.93,
"learning_rate": 9.916284765740857e-06,
"loss": 4.0196,
"step": 97500
},
{
"epoch": 0.94,
"learning_rate": 9.915806392973662e-06,
"loss": 4.0049,
"step": 98000
},
{
"epoch": 0.94,
"learning_rate": 9.915328020206465e-06,
"loss": 3.9919,
"step": 98500
},
{
"epoch": 0.95,
"learning_rate": 9.914849647439272e-06,
"loss": 3.9626,
"step": 99000
},
{
"epoch": 0.95,
"learning_rate": 9.914371274672077e-06,
"loss": 3.9469,
"step": 99500
},
{
"epoch": 0.96,
"learning_rate": 9.913892901904882e-06,
"loss": 3.9354,
"step": 100000
},
{
"epoch": 0.96,
"learning_rate": 9.913414529137686e-06,
"loss": 3.9084,
"step": 100500
},
{
"epoch": 0.97,
"learning_rate": 9.912936156370491e-06,
"loss": 3.8966,
"step": 101000
},
{
"epoch": 0.97,
"learning_rate": 9.912457783603296e-06,
"loss": 3.8735,
"step": 101500
},
{
"epoch": 0.97,
"learning_rate": 9.911979410836101e-06,
"loss": 3.8618,
"step": 102000
},
{
"epoch": 0.98,
"learning_rate": 9.911501038068906e-06,
"loss": 3.8407,
"step": 102500
},
{
"epoch": 0.98,
"learning_rate": 9.91102266530171e-06,
"loss": 3.8246,
"step": 103000
},
{
"epoch": 0.99,
"learning_rate": 9.910544292534515e-06,
"loss": 3.8059,
"step": 103500
},
{
"epoch": 0.99,
"learning_rate": 9.91006591976732e-06,
"loss": 3.796,
"step": 104000
},
{
"epoch": 1.0,
"learning_rate": 9.909587547000125e-06,
"loss": 3.7835,
"step": 104500
},
{
"epoch": 1.0,
"learning_rate": 9.90910917423293e-06,
"loss": 3.7657,
"step": 105000
},
{
"epoch": 1.01,
"learning_rate": 9.908630801465735e-06,
"loss": 3.7459,
"step": 105500
},
{
"epoch": 1.01,
"learning_rate": 9.90815242869854e-06,
"loss": 3.7431,
"step": 106000
},
{
"epoch": 1.02,
"learning_rate": 9.907674055931345e-06,
"loss": 3.7274,
"step": 106500
},
{
"epoch": 1.02,
"learning_rate": 9.90719568316415e-06,
"loss": 3.7172,
"step": 107000
},
{
"epoch": 1.03,
"learning_rate": 9.906717310396954e-06,
"loss": 3.7015,
"step": 107500
},
{
"epoch": 1.03,
"learning_rate": 9.906238937629759e-06,
"loss": 3.6916,
"step": 108000
},
{
"epoch": 1.04,
"learning_rate": 9.905760564862564e-06,
"loss": 3.6755,
"step": 108500
},
{
"epoch": 1.04,
"learning_rate": 9.905282192095369e-06,
"loss": 3.6646,
"step": 109000
},
{
"epoch": 1.05,
"learning_rate": 9.904803819328174e-06,
"loss": 3.6548,
"step": 109500
},
{
"epoch": 1.05,
"learning_rate": 9.90432544656098e-06,
"loss": 3.6433,
"step": 110000
},
{
"epoch": 1.06,
"learning_rate": 9.903847073793785e-06,
"loss": 3.6269,
"step": 110500
},
{
"epoch": 1.06,
"learning_rate": 9.903368701026588e-06,
"loss": 3.6216,
"step": 111000
},
{
"epoch": 1.07,
"learning_rate": 9.902890328259393e-06,
"loss": 3.6056,
"step": 111500
},
{
"epoch": 1.07,
"learning_rate": 9.902411955492198e-06,
"loss": 3.5949,
"step": 112000
},
{
"epoch": 1.08,
"learning_rate": 9.901933582725003e-06,
"loss": 3.5931,
"step": 112500
},
{
"epoch": 1.08,
"learning_rate": 9.90145520995781e-06,
"loss": 3.5786,
"step": 113000
},
{
"epoch": 1.08,
"learning_rate": 9.900976837190614e-06,
"loss": 3.5733,
"step": 113500
},
{
"epoch": 1.09,
"learning_rate": 9.900498464423419e-06,
"loss": 3.5628,
"step": 114000
},
{
"epoch": 1.09,
"learning_rate": 9.900020091656222e-06,
"loss": 3.5453,
"step": 114500
},
{
"epoch": 1.1,
"learning_rate": 9.899541718889027e-06,
"loss": 3.5472,
"step": 115000
},
{
"epoch": 1.1,
"learning_rate": 9.899063346121833e-06,
"loss": 3.5334,
"step": 115500
},
{
"epoch": 1.11,
"learning_rate": 9.898584973354638e-06,
"loss": 3.5187,
"step": 116000
},
{
"epoch": 1.11,
"learning_rate": 9.898106600587443e-06,
"loss": 3.5137,
"step": 116500
},
{
"epoch": 1.12,
"learning_rate": 9.897628227820248e-06,
"loss": 3.5029,
"step": 117000
},
{
"epoch": 1.12,
"learning_rate": 9.897149855053053e-06,
"loss": 3.4994,
"step": 117500
},
{
"epoch": 1.13,
"learning_rate": 9.896671482285856e-06,
"loss": 3.4834,
"step": 118000
},
{
"epoch": 1.13,
"learning_rate": 9.896193109518663e-06,
"loss": 3.4748,
"step": 118500
},
{
"epoch": 1.14,
"learning_rate": 9.895714736751467e-06,
"loss": 3.4802,
"step": 119000
},
{
"epoch": 1.14,
"learning_rate": 9.895236363984272e-06,
"loss": 3.4635,
"step": 119500
},
{
"epoch": 1.15,
"learning_rate": 9.894757991217077e-06,
"loss": 3.4572,
"step": 120000
},
{
"epoch": 1.15,
"learning_rate": 9.894279618449882e-06,
"loss": 3.4505,
"step": 120500
},
{
"epoch": 1.16,
"learning_rate": 9.893801245682687e-06,
"loss": 3.4351,
"step": 121000
},
{
"epoch": 1.16,
"learning_rate": 9.893322872915492e-06,
"loss": 3.4333,
"step": 121500
},
{
"epoch": 1.17,
"learning_rate": 9.892844500148296e-06,
"loss": 3.4241,
"step": 122000
},
{
"epoch": 1.17,
"learning_rate": 9.892366127381101e-06,
"loss": 3.4255,
"step": 122500
},
{
"epoch": 1.18,
"learning_rate": 9.891887754613906e-06,
"loss": 3.4108,
"step": 123000
},
{
"epoch": 1.18,
"learning_rate": 9.891409381846711e-06,
"loss": 3.4036,
"step": 123500
},
{
"epoch": 1.19,
"learning_rate": 9.890931009079516e-06,
"loss": 3.3975,
"step": 124000
},
{
"epoch": 1.19,
"learning_rate": 9.89045263631232e-06,
"loss": 3.3904,
"step": 124500
},
{
"epoch": 1.19,
"learning_rate": 9.889974263545126e-06,
"loss": 3.387,
"step": 125000
},
{
"epoch": 1.2,
"learning_rate": 9.88949589077793e-06,
"loss": 3.3716,
"step": 125500
},
{
"epoch": 1.2,
"learning_rate": 9.889017518010735e-06,
"loss": 3.369,
"step": 126000
},
{
"epoch": 1.21,
"learning_rate": 9.88853914524354e-06,
"loss": 3.3587,
"step": 126500
},
{
"epoch": 1.21,
"learning_rate": 9.888060772476345e-06,
"loss": 3.3638,
"step": 127000
},
{
"epoch": 1.22,
"learning_rate": 9.88758239970915e-06,
"loss": 3.3531,
"step": 127500
},
{
"epoch": 1.22,
"learning_rate": 9.887104026941955e-06,
"loss": 3.3412,
"step": 128000
},
{
"epoch": 1.23,
"learning_rate": 9.88662565417476e-06,
"loss": 3.3392,
"step": 128500
},
{
"epoch": 1.23,
"learning_rate": 9.886147281407564e-06,
"loss": 3.327,
"step": 129000
},
{
"epoch": 1.24,
"learning_rate": 9.88566890864037e-06,
"loss": 3.3197,
"step": 129500
},
{
"epoch": 1.24,
"learning_rate": 9.885190535873174e-06,
"loss": 3.3237,
"step": 130000
},
{
"epoch": 1.25,
"learning_rate": 9.884712163105979e-06,
"loss": 3.3081,
"step": 130500
},
{
"epoch": 1.25,
"learning_rate": 9.884233790338784e-06,
"loss": 3.3071,
"step": 131000
},
{
"epoch": 1.26,
"learning_rate": 9.883755417571589e-06,
"loss": 3.301,
"step": 131500
},
{
"epoch": 1.26,
"learning_rate": 9.883277044804395e-06,
"loss": 3.3011,
"step": 132000
},
{
"epoch": 1.27,
"learning_rate": 9.8827986720372e-06,
"loss": 3.2862,
"step": 132500
},
{
"epoch": 1.27,
"learning_rate": 9.882320299270005e-06,
"loss": 3.2838,
"step": 133000
},
{
"epoch": 1.28,
"learning_rate": 9.881841926502808e-06,
"loss": 3.2749,
"step": 133500
},
{
"epoch": 1.28,
"learning_rate": 9.881363553735613e-06,
"loss": 3.2778,
"step": 134000
},
{
"epoch": 1.29,
"learning_rate": 9.880885180968418e-06,
"loss": 3.2691,
"step": 134500
},
{
"epoch": 1.29,
"learning_rate": 9.880406808201224e-06,
"loss": 3.2645,
"step": 135000
},
{
"epoch": 1.3,
"learning_rate": 9.879928435434029e-06,
"loss": 3.2589,
"step": 135500
},
{
"epoch": 1.3,
"learning_rate": 9.879450062666834e-06,
"loss": 3.2441,
"step": 136000
},
{
"epoch": 1.3,
"learning_rate": 9.878971689899639e-06,
"loss": 3.2469,
"step": 136500
},
{
"epoch": 1.31,
"learning_rate": 9.878493317132442e-06,
"loss": 3.2443,
"step": 137000
},
{
"epoch": 1.31,
"learning_rate": 9.878014944365248e-06,
"loss": 3.2431,
"step": 137500
},
{
"epoch": 1.32,
"learning_rate": 9.877536571598053e-06,
"loss": 3.2268,
"step": 138000
},
{
"epoch": 1.32,
"learning_rate": 9.877058198830858e-06,
"loss": 3.219,
"step": 138500
},
{
"epoch": 1.33,
"learning_rate": 9.876579826063663e-06,
"loss": 3.2265,
"step": 139000
},
{
"epoch": 1.33,
"learning_rate": 9.876101453296468e-06,
"loss": 3.2182,
"step": 139500
},
{
"epoch": 1.34,
"learning_rate": 9.875623080529273e-06,
"loss": 3.2138,
"step": 140000
},
{
"epoch": 1.34,
"learning_rate": 9.875144707762077e-06,
"loss": 3.204,
"step": 140500
},
{
"epoch": 1.35,
"learning_rate": 9.874666334994882e-06,
"loss": 3.1989,
"step": 141000
},
{
"epoch": 1.35,
"learning_rate": 9.874187962227687e-06,
"loss": 3.2008,
"step": 141500
},
{
"epoch": 1.36,
"learning_rate": 9.873709589460492e-06,
"loss": 3.1909,
"step": 142000
},
{
"epoch": 1.36,
"learning_rate": 9.873231216693297e-06,
"loss": 3.1902,
"step": 142500
},
{
"epoch": 1.37,
"learning_rate": 9.872752843926102e-06,
"loss": 3.1796,
"step": 143000
},
{
"epoch": 1.37,
"learning_rate": 9.872274471158907e-06,
"loss": 3.1792,
"step": 143500
},
{
"epoch": 1.38,
"learning_rate": 9.871796098391711e-06,
"loss": 3.1798,
"step": 144000
},
{
"epoch": 1.38,
"learning_rate": 9.871317725624516e-06,
"loss": 3.1621,
"step": 144500
},
{
"epoch": 1.39,
"learning_rate": 9.870839352857321e-06,
"loss": 3.168,
"step": 145000
},
{
"epoch": 1.39,
"learning_rate": 9.870360980090128e-06,
"loss": 3.1598,
"step": 145500
},
{
"epoch": 1.4,
"learning_rate": 9.86988260732293e-06,
"loss": 3.155,
"step": 146000
},
{
"epoch": 1.4,
"learning_rate": 9.869404234555736e-06,
"loss": 3.1539,
"step": 146500
},
{
"epoch": 1.41,
"learning_rate": 9.86892586178854e-06,
"loss": 3.1468,
"step": 147000
},
{
"epoch": 1.41,
"learning_rate": 9.868447489021345e-06,
"loss": 3.136,
"step": 147500
},
{
"epoch": 1.41,
"learning_rate": 9.86796911625415e-06,
"loss": 3.1355,
"step": 148000
},
{
"epoch": 1.42,
"learning_rate": 9.867490743486957e-06,
"loss": 3.1361,
"step": 148500
},
{
"epoch": 1.42,
"learning_rate": 9.867012370719761e-06,
"loss": 3.1299,
"step": 149000
},
{
"epoch": 1.43,
"learning_rate": 9.866533997952565e-06,
"loss": 3.1259,
"step": 149500
},
{
"epoch": 1.43,
"learning_rate": 9.86605562518537e-06,
"loss": 3.1176,
"step": 150000
},
{
"epoch": 1.44,
"learning_rate": 9.865577252418174e-06,
"loss": 3.126,
"step": 150500
},
{
"epoch": 1.44,
"learning_rate": 9.865098879650981e-06,
"loss": 3.1132,
"step": 151000
},
{
"epoch": 1.45,
"learning_rate": 9.864620506883786e-06,
"loss": 3.1072,
"step": 151500
},
{
"epoch": 1.45,
"learning_rate": 9.86414213411659e-06,
"loss": 3.1036,
"step": 152000
},
{
"epoch": 1.46,
"learning_rate": 9.863663761349395e-06,
"loss": 3.1007,
"step": 152500
},
{
"epoch": 1.46,
"learning_rate": 9.863185388582199e-06,
"loss": 3.0971,
"step": 153000
},
{
"epoch": 1.47,
"learning_rate": 9.862707015815003e-06,
"loss": 3.0893,
"step": 153500
},
{
"epoch": 1.47,
"learning_rate": 9.86222864304781e-06,
"loss": 3.0835,
"step": 154000
},
{
"epoch": 1.48,
"learning_rate": 9.861750270280615e-06,
"loss": 3.0827,
"step": 154500
},
{
"epoch": 1.48,
"learning_rate": 9.86127189751342e-06,
"loss": 3.0792,
"step": 155000
},
{
"epoch": 1.49,
"learning_rate": 9.860793524746224e-06,
"loss": 3.0726,
"step": 155500
},
{
"epoch": 1.49,
"learning_rate": 9.86031515197903e-06,
"loss": 3.0696,
"step": 156000
},
{
"epoch": 1.5,
"learning_rate": 9.859836779211834e-06,
"loss": 3.0624,
"step": 156500
},
{
"epoch": 1.5,
"learning_rate": 9.859358406444639e-06,
"loss": 3.0654,
"step": 157000
},
{
"epoch": 1.51,
"learning_rate": 9.858880033677444e-06,
"loss": 3.0591,
"step": 157500
},
{
"epoch": 1.51,
"learning_rate": 9.858401660910249e-06,
"loss": 3.0501,
"step": 158000
},
{
"epoch": 1.51,
"learning_rate": 9.857923288143054e-06,
"loss": 3.0534,
"step": 158500
},
{
"epoch": 1.52,
"learning_rate": 9.857444915375858e-06,
"loss": 3.0498,
"step": 159000
},
{
"epoch": 1.52,
"learning_rate": 9.856966542608663e-06,
"loss": 3.0412,
"step": 159500
},
{
"epoch": 1.53,
"learning_rate": 9.856488169841468e-06,
"loss": 3.0357,
"step": 160000
},
{
"epoch": 1.53,
"learning_rate": 9.856009797074273e-06,
"loss": 3.0351,
"step": 160500
},
{
"epoch": 1.54,
"learning_rate": 9.855531424307078e-06,
"loss": 3.034,
"step": 161000
},
{
"epoch": 1.54,
"learning_rate": 9.855053051539883e-06,
"loss": 3.0332,
"step": 161500
},
{
"epoch": 1.55,
"learning_rate": 9.854574678772687e-06,
"loss": 3.0269,
"step": 162000
},
{
"epoch": 1.55,
"learning_rate": 9.854096306005492e-06,
"loss": 3.0232,
"step": 162500
},
{
"epoch": 1.56,
"learning_rate": 9.853617933238297e-06,
"loss": 3.0266,
"step": 163000
},
{
"epoch": 1.56,
"learning_rate": 9.853139560471102e-06,
"loss": 3.0164,
"step": 163500
},
{
"epoch": 1.57,
"learning_rate": 9.852661187703907e-06,
"loss": 3.0115,
"step": 164000
},
{
"epoch": 1.57,
"learning_rate": 9.852182814936712e-06,
"loss": 3.0088,
"step": 164500
},
{
"epoch": 1.58,
"learning_rate": 9.851704442169517e-06,
"loss": 3.0049,
"step": 165000
},
{
"epoch": 1.58,
"learning_rate": 9.851226069402321e-06,
"loss": 2.9978,
"step": 165500
},
{
"epoch": 1.59,
"learning_rate": 9.850747696635126e-06,
"loss": 3.0032,
"step": 166000
},
{
"epoch": 1.59,
"learning_rate": 9.850269323867931e-06,
"loss": 2.993,
"step": 166500
},
{
"epoch": 1.6,
"learning_rate": 9.849790951100736e-06,
"loss": 2.9939,
"step": 167000
},
{
"epoch": 1.6,
"learning_rate": 9.849312578333542e-06,
"loss": 2.9906,
"step": 167500
},
{
"epoch": 1.61,
"learning_rate": 9.848834205566347e-06,
"loss": 2.9855,
"step": 168000
},
{
"epoch": 1.61,
"learning_rate": 9.84835583279915e-06,
"loss": 2.9814,
"step": 168500
},
{
"epoch": 1.62,
"learning_rate": 9.847877460031955e-06,
"loss": 2.9848,
"step": 169000
},
{
"epoch": 1.62,
"learning_rate": 9.84739908726476e-06,
"loss": 2.9744,
"step": 169500
},
{
"epoch": 1.62,
"learning_rate": 9.846920714497565e-06,
"loss": 2.9682,
"step": 170000
},
{
"epoch": 1.63,
"learning_rate": 9.846442341730372e-06,
"loss": 2.9689,
"step": 170500
},
{
"epoch": 1.63,
"learning_rate": 9.845963968963176e-06,
"loss": 2.9649,
"step": 171000
},
{
"epoch": 1.64,
"learning_rate": 9.845485596195981e-06,
"loss": 2.9616,
"step": 171500
},
{
"epoch": 1.64,
"learning_rate": 9.845007223428784e-06,
"loss": 2.9621,
"step": 172000
},
{
"epoch": 1.65,
"learning_rate": 9.84452885066159e-06,
"loss": 2.9569,
"step": 172500
},
{
"epoch": 1.65,
"learning_rate": 9.844050477894396e-06,
"loss": 2.951,
"step": 173000
},
{
"epoch": 1.66,
"learning_rate": 9.8435721051272e-06,
"loss": 2.9469,
"step": 173500
},
{
"epoch": 1.66,
"learning_rate": 9.843093732360005e-06,
"loss": 2.9409,
"step": 174000
},
{
"epoch": 1.67,
"learning_rate": 9.84261535959281e-06,
"loss": 2.9422,
"step": 174500
},
{
"epoch": 1.67,
"learning_rate": 9.842136986825615e-06,
"loss": 2.938,
"step": 175000
},
{
"epoch": 1.68,
"learning_rate": 9.841658614058418e-06,
"loss": 2.9334,
"step": 175500
},
{
"epoch": 1.68,
"learning_rate": 9.841180241291225e-06,
"loss": 2.9355,
"step": 176000
},
{
"epoch": 1.69,
"learning_rate": 9.84070186852403e-06,
"loss": 2.9299,
"step": 176500
},
{
"epoch": 1.69,
"learning_rate": 9.840223495756835e-06,
"loss": 2.9272,
"step": 177000
},
{
"epoch": 1.7,
"learning_rate": 9.83974512298964e-06,
"loss": 2.919,
"step": 177500
},
{
"epoch": 1.7,
"learning_rate": 9.839266750222444e-06,
"loss": 2.928,
"step": 178000
},
{
"epoch": 1.71,
"learning_rate": 9.838788377455249e-06,
"loss": 2.9123,
"step": 178500
},
{
"epoch": 1.71,
"learning_rate": 9.838310004688054e-06,
"loss": 2.9111,
"step": 179000
},
{
"epoch": 1.72,
"learning_rate": 9.837831631920859e-06,
"loss": 2.912,
"step": 179500
},
{
"epoch": 1.72,
"learning_rate": 9.837353259153664e-06,
"loss": 2.906,
"step": 180000
},
{
"epoch": 1.73,
"learning_rate": 9.836874886386468e-06,
"loss": 2.9096,
"step": 180500
},
{
"epoch": 1.73,
"learning_rate": 9.836396513619273e-06,
"loss": 2.9066,
"step": 181000
},
{
"epoch": 1.73,
"learning_rate": 9.835918140852078e-06,
"loss": 2.9049,
"step": 181500
},
{
"epoch": 1.74,
"learning_rate": 9.835439768084883e-06,
"loss": 2.9004,
"step": 182000
},
{
"epoch": 1.74,
"learning_rate": 9.834961395317688e-06,
"loss": 2.8895,
"step": 182500
},
{
"epoch": 1.75,
"learning_rate": 9.834483022550493e-06,
"loss": 2.8974,
"step": 183000
},
{
"epoch": 1.75,
"learning_rate": 9.834004649783298e-06,
"loss": 2.8893,
"step": 183500
},
{
"epoch": 1.76,
"learning_rate": 9.833526277016104e-06,
"loss": 2.8864,
"step": 184000
},
{
"epoch": 1.76,
"learning_rate": 9.833047904248907e-06,
"loss": 2.8876,
"step": 184500
},
{
"epoch": 1.77,
"learning_rate": 9.832569531481712e-06,
"loss": 2.8786,
"step": 185000
},
{
"epoch": 1.77,
"learning_rate": 9.832091158714517e-06,
"loss": 2.8743,
"step": 185500
},
{
"epoch": 1.78,
"learning_rate": 9.831612785947322e-06,
"loss": 2.8711,
"step": 186000
},
{
"epoch": 1.78,
"learning_rate": 9.831134413180127e-06,
"loss": 2.8704,
"step": 186500
},
{
"epoch": 1.79,
"learning_rate": 9.830656040412933e-06,
"loss": 2.8686,
"step": 187000
},
{
"epoch": 1.79,
"learning_rate": 9.830177667645738e-06,
"loss": 2.8641,
"step": 187500
},
{
"epoch": 1.8,
"learning_rate": 9.829699294878541e-06,
"loss": 2.8697,
"step": 188000
},
{
"epoch": 1.8,
"learning_rate": 9.829220922111346e-06,
"loss": 2.8572,
"step": 188500
},
{
"epoch": 1.81,
"learning_rate": 9.828742549344151e-06,
"loss": 2.8619,
"step": 189000
},
{
"epoch": 1.81,
"learning_rate": 9.828264176576957e-06,
"loss": 2.8614,
"step": 189500
},
{
"epoch": 1.82,
"learning_rate": 9.827785803809762e-06,
"loss": 2.855,
"step": 190000
},
{
"epoch": 1.82,
"learning_rate": 9.827307431042567e-06,
"loss": 2.8589,
"step": 190500
},
{
"epoch": 1.83,
"learning_rate": 9.826829058275372e-06,
"loss": 2.8497,
"step": 191000
},
{
"epoch": 1.83,
"learning_rate": 9.826350685508175e-06,
"loss": 2.8471,
"step": 191500
},
{
"epoch": 1.84,
"learning_rate": 9.825872312740982e-06,
"loss": 2.8485,
"step": 192000
},
{
"epoch": 1.84,
"learning_rate": 9.825393939973786e-06,
"loss": 2.8452,
"step": 192500
},
{
"epoch": 1.84,
"learning_rate": 9.824915567206591e-06,
"loss": 2.8429,
"step": 193000
},
{
"epoch": 1.85,
"learning_rate": 9.824437194439396e-06,
"loss": 2.84,
"step": 193500
},
{
"epoch": 1.85,
"learning_rate": 9.823958821672201e-06,
"loss": 2.8344,
"step": 194000
},
{
"epoch": 1.86,
"learning_rate": 9.823480448905006e-06,
"loss": 2.8337,
"step": 194500
},
{
"epoch": 1.86,
"learning_rate": 9.82300207613781e-06,
"loss": 2.8341,
"step": 195000
},
{
"epoch": 1.87,
"learning_rate": 9.822523703370616e-06,
"loss": 2.8372,
"step": 195500
},
{
"epoch": 1.87,
"learning_rate": 9.82204533060342e-06,
"loss": 2.8268,
"step": 196000
},
{
"epoch": 1.88,
"learning_rate": 9.821566957836225e-06,
"loss": 2.8248,
"step": 196500
},
{
"epoch": 1.88,
"learning_rate": 9.82108858506903e-06,
"loss": 2.8233,
"step": 197000
},
{
"epoch": 1.89,
"learning_rate": 9.820610212301835e-06,
"loss": 2.8141,
"step": 197500
},
{
"epoch": 1.89,
"learning_rate": 9.82013183953464e-06,
"loss": 2.818,
"step": 198000
},
{
"epoch": 1.9,
"learning_rate": 9.819653466767445e-06,
"loss": 2.8156,
"step": 198500
},
{
"epoch": 1.9,
"learning_rate": 9.81917509400025e-06,
"loss": 2.8165,
"step": 199000
},
{
"epoch": 1.91,
"learning_rate": 9.818696721233054e-06,
"loss": 2.8092,
"step": 199500
},
{
"epoch": 1.91,
"learning_rate": 9.81821834846586e-06,
"loss": 2.803,
"step": 200000
},
{
"epoch": 1.92,
"learning_rate": 9.817739975698664e-06,
"loss": 2.8103,
"step": 200500
},
{
"epoch": 1.92,
"learning_rate": 9.817261602931469e-06,
"loss": 2.8056,
"step": 201000
},
{
"epoch": 1.93,
"learning_rate": 9.816783230164274e-06,
"loss": 2.8062,
"step": 201500
},
{
"epoch": 1.93,
"learning_rate": 9.816304857397079e-06,
"loss": 2.8035,
"step": 202000
},
{
"epoch": 1.94,
"learning_rate": 9.815826484629883e-06,
"loss": 2.8014,
"step": 202500
},
{
"epoch": 1.94,
"learning_rate": 9.81534811186269e-06,
"loss": 2.7975,
"step": 203000
},
{
"epoch": 1.95,
"learning_rate": 9.814869739095493e-06,
"loss": 2.7922,
"step": 203500
},
{
"epoch": 1.95,
"learning_rate": 9.814391366328298e-06,
"loss": 2.7891,
"step": 204000
},
{
"epoch": 1.95,
"learning_rate": 9.813912993561103e-06,
"loss": 2.7872,
"step": 204500
},
{
"epoch": 1.96,
"learning_rate": 9.813434620793908e-06,
"loss": 2.7839,
"step": 205000
},
{
"epoch": 1.96,
"learning_rate": 9.812956248026712e-06,
"loss": 2.7831,
"step": 205500
},
{
"epoch": 1.97,
"learning_rate": 9.812477875259519e-06,
"loss": 2.7802,
"step": 206000
},
{
"epoch": 1.97,
"learning_rate": 9.811999502492324e-06,
"loss": 2.7764,
"step": 206500
},
{
"epoch": 1.98,
"learning_rate": 9.811521129725127e-06,
"loss": 2.774,
"step": 207000
},
{
"epoch": 1.98,
"learning_rate": 9.811042756957932e-06,
"loss": 2.7793,
"step": 207500
},
{
"epoch": 1.99,
"learning_rate": 9.810564384190737e-06,
"loss": 2.7738,
"step": 208000
},
{
"epoch": 1.99,
"learning_rate": 9.810086011423543e-06,
"loss": 2.7756,
"step": 208500
},
{
"epoch": 2.0,
"learning_rate": 9.809607638656348e-06,
"loss": 2.7736,
"step": 209000
},
{
"epoch": 2.0,
"learning_rate": 9.809129265889153e-06,
"loss": 2.7643,
"step": 209500
},
{
"epoch": 2.01,
"learning_rate": 9.808650893121958e-06,
"loss": 2.7643,
"step": 210000
},
{
"epoch": 2.01,
"learning_rate": 9.808172520354761e-06,
"loss": 2.7615,
"step": 210500
},
{
"epoch": 2.02,
"learning_rate": 9.807694147587566e-06,
"loss": 2.7653,
"step": 211000
},
{
"epoch": 2.02,
"learning_rate": 9.807215774820372e-06,
"loss": 2.757,
"step": 211500
},
{
"epoch": 2.03,
"learning_rate": 9.806737402053177e-06,
"loss": 2.7607,
"step": 212000
},
{
"epoch": 2.03,
"learning_rate": 9.806259029285982e-06,
"loss": 2.7567,
"step": 212500
},
{
"epoch": 2.04,
"learning_rate": 9.805780656518787e-06,
"loss": 2.7563,
"step": 213000
},
{
"epoch": 2.04,
"learning_rate": 9.805302283751592e-06,
"loss": 2.7533,
"step": 213500
},
{
"epoch": 2.05,
"learning_rate": 9.804823910984397e-06,
"loss": 2.7443,
"step": 214000
},
{
"epoch": 2.05,
"learning_rate": 9.804345538217201e-06,
"loss": 2.7415,
"step": 214500
},
{
"epoch": 2.06,
"learning_rate": 9.803867165450006e-06,
"loss": 2.7493,
"step": 215000
},
{
"epoch": 2.06,
"learning_rate": 9.803388792682811e-06,
"loss": 2.741,
"step": 215500
},
{
"epoch": 2.06,
"learning_rate": 9.802910419915616e-06,
"loss": 2.7392,
"step": 216000
},
{
"epoch": 2.07,
"learning_rate": 9.80243204714842e-06,
"loss": 2.734,
"step": 216500
},
{
"epoch": 2.07,
"learning_rate": 9.801953674381226e-06,
"loss": 2.7402,
"step": 217000
},
{
"epoch": 2.08,
"learning_rate": 9.80147530161403e-06,
"loss": 2.7282,
"step": 217500
},
{
"epoch": 2.08,
"learning_rate": 9.800996928846835e-06,
"loss": 2.7278,
"step": 218000
},
{
"epoch": 2.09,
"learning_rate": 9.80051855607964e-06,
"loss": 2.7316,
"step": 218500
},
{
"epoch": 2.09,
"learning_rate": 9.800040183312445e-06,
"loss": 2.7258,
"step": 219000
},
{
"epoch": 2.1,
"learning_rate": 9.79956181054525e-06,
"loss": 2.7267,
"step": 219500
},
{
"epoch": 2.1,
"learning_rate": 9.799083437778055e-06,
"loss": 2.728,
"step": 220000
},
{
"epoch": 2.11,
"learning_rate": 9.79860506501086e-06,
"loss": 2.7308,
"step": 220500
},
{
"epoch": 2.11,
"learning_rate": 9.798126692243664e-06,
"loss": 2.7204,
"step": 221000
},
{
"epoch": 2.12,
"learning_rate": 9.79764831947647e-06,
"loss": 2.7143,
"step": 221500
},
{
"epoch": 2.12,
"learning_rate": 9.797169946709274e-06,
"loss": 2.7151,
"step": 222000
},
{
"epoch": 2.13,
"learning_rate": 9.79669157394208e-06,
"loss": 2.7091,
"step": 222500
},
{
"epoch": 2.13,
"learning_rate": 9.796213201174884e-06,
"loss": 2.7201,
"step": 223000
},
{
"epoch": 2.14,
"learning_rate": 9.795734828407689e-06,
"loss": 2.7186,
"step": 223500
},
{
"epoch": 2.14,
"learning_rate": 9.795256455640493e-06,
"loss": 2.7121,
"step": 224000
},
{
"epoch": 2.15,
"learning_rate": 9.794778082873298e-06,
"loss": 2.7096,
"step": 224500
},
{
"epoch": 2.15,
"learning_rate": 9.794299710106105e-06,
"loss": 2.7105,
"step": 225000
},
{
"epoch": 2.15,
"step": 225243,
"total_flos": 3.118398678566437e+18,
"train_loss": 4.290504575642074,
"train_runtime": 197999.5648,
"train_samples_per_second": 2958.975,
"train_steps_per_second": 52.839
}
],
"logging_steps": 500,
"max_steps": 10462100,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 3.118398678566437e+18,
"trial_name": null,
"trial_params": null
}