atsuki-yamaguchi's picture
Upload folder using huggingface_hub
668a847 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.26000191679001566,
"eval_steps": 500,
"global_step": 6104,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001320455344117052,
"grad_norm": 29.63249969482422,
"learning_rate": 1.0157273918741808e-06,
"loss": 9.114,
"step": 31
},
{
"epoch": 0.002640910688234104,
"grad_norm": 14.638819694519043,
"learning_rate": 2.0314547837483616e-06,
"loss": 7.7274,
"step": 62
},
{
"epoch": 0.003961366032351156,
"grad_norm": 12.396350860595703,
"learning_rate": 3.0471821756225426e-06,
"loss": 6.3242,
"step": 93
},
{
"epoch": 0.005281821376468208,
"grad_norm": 14.456698417663574,
"learning_rate": 4.062909567496723e-06,
"loss": 5.0889,
"step": 124
},
{
"epoch": 0.00660227672058526,
"grad_norm": 22.106542587280273,
"learning_rate": 5.078636959370905e-06,
"loss": 4.5309,
"step": 155
},
{
"epoch": 0.007922732064702311,
"grad_norm": 17.991788864135742,
"learning_rate": 6.094364351245085e-06,
"loss": 4.2146,
"step": 186
},
{
"epoch": 0.009243187408819364,
"grad_norm": 15.457059860229492,
"learning_rate": 7.110091743119267e-06,
"loss": 3.9509,
"step": 217
},
{
"epoch": 0.010563642752936416,
"grad_norm": 16.144941329956055,
"learning_rate": 8.125819134993446e-06,
"loss": 3.7073,
"step": 248
},
{
"epoch": 0.011884098097053469,
"grad_norm": 18.386638641357422,
"learning_rate": 9.141546526867629e-06,
"loss": 3.5325,
"step": 279
},
{
"epoch": 0.01320455344117052,
"grad_norm": 21.711469650268555,
"learning_rate": 1.015727391874181e-05,
"loss": 3.4011,
"step": 310
},
{
"epoch": 0.014525008785287572,
"grad_norm": 14.871952056884766,
"learning_rate": 1.117300131061599e-05,
"loss": 3.2887,
"step": 341
},
{
"epoch": 0.015845464129404623,
"grad_norm": 16.011245727539062,
"learning_rate": 1.218872870249017e-05,
"loss": 3.1892,
"step": 372
},
{
"epoch": 0.017165919473521675,
"grad_norm": 12.8394193649292,
"learning_rate": 1.3204456094364351e-05,
"loss": 3.0572,
"step": 403
},
{
"epoch": 0.018486374817638727,
"grad_norm": 9.7935791015625,
"learning_rate": 1.4220183486238533e-05,
"loss": 2.9882,
"step": 434
},
{
"epoch": 0.01980683016175578,
"grad_norm": 11.32317066192627,
"learning_rate": 1.5235910878112714e-05,
"loss": 2.9312,
"step": 465
},
{
"epoch": 0.021127285505872832,
"grad_norm": 9.307639122009277,
"learning_rate": 1.6251638269986893e-05,
"loss": 2.8479,
"step": 496
},
{
"epoch": 0.022447740849989885,
"grad_norm": 9.315092086791992,
"learning_rate": 1.7267365661861077e-05,
"loss": 2.8021,
"step": 527
},
{
"epoch": 0.023768196194106937,
"grad_norm": 9.456792831420898,
"learning_rate": 1.8283093053735257e-05,
"loss": 2.7374,
"step": 558
},
{
"epoch": 0.025088651538223986,
"grad_norm": 8.998442649841309,
"learning_rate": 1.9298820445609438e-05,
"loss": 2.7135,
"step": 589
},
{
"epoch": 0.02640910688234104,
"grad_norm": 7.467686176300049,
"learning_rate": 2.031454783748362e-05,
"loss": 2.6459,
"step": 620
},
{
"epoch": 0.02772956222645809,
"grad_norm": 7.3969831466674805,
"learning_rate": 2.13302752293578e-05,
"loss": 2.6074,
"step": 651
},
{
"epoch": 0.029050017570575144,
"grad_norm": 7.884100914001465,
"learning_rate": 2.234600262123198e-05,
"loss": 2.5871,
"step": 682
},
{
"epoch": 0.030370472914692196,
"grad_norm": 6.4375224113464355,
"learning_rate": 2.336173001310616e-05,
"loss": 2.5069,
"step": 713
},
{
"epoch": 0.031690928258809245,
"grad_norm": 6.661777973175049,
"learning_rate": 2.437745740498034e-05,
"loss": 2.4812,
"step": 744
},
{
"epoch": 0.0330113836029263,
"grad_norm": 7.4887566566467285,
"learning_rate": 2.5393184796854525e-05,
"loss": 2.4623,
"step": 775
},
{
"epoch": 0.03433183894704335,
"grad_norm": 6.085121154785156,
"learning_rate": 2.6408912188728702e-05,
"loss": 2.4202,
"step": 806
},
{
"epoch": 0.0356522942911604,
"grad_norm": 5.930830478668213,
"learning_rate": 2.7424639580602886e-05,
"loss": 2.3901,
"step": 837
},
{
"epoch": 0.036972749635277455,
"grad_norm": 6.05289363861084,
"learning_rate": 2.8440366972477066e-05,
"loss": 2.3408,
"step": 868
},
{
"epoch": 0.03829320497939451,
"grad_norm": 5.337353229522705,
"learning_rate": 2.9456094364351244e-05,
"loss": 2.335,
"step": 899
},
{
"epoch": 0.03961366032351156,
"grad_norm": 6.452489376068115,
"learning_rate": 3.0471821756225428e-05,
"loss": 2.2955,
"step": 930
},
{
"epoch": 0.04093411566762861,
"grad_norm": 5.795267581939697,
"learning_rate": 3.148754914809961e-05,
"loss": 2.2812,
"step": 961
},
{
"epoch": 0.042254571011745665,
"grad_norm": 5.245680809020996,
"learning_rate": 3.2503276539973785e-05,
"loss": 2.2487,
"step": 992
},
{
"epoch": 0.04357502635586272,
"grad_norm": 4.897157192230225,
"learning_rate": 3.351900393184797e-05,
"loss": 2.2226,
"step": 1023
},
{
"epoch": 0.04489548169997977,
"grad_norm": 4.6457743644714355,
"learning_rate": 3.453473132372215e-05,
"loss": 2.1903,
"step": 1054
},
{
"epoch": 0.04621593704409682,
"grad_norm": 4.918821334838867,
"learning_rate": 3.555045871559633e-05,
"loss": 2.1739,
"step": 1085
},
{
"epoch": 0.047536392388213874,
"grad_norm": 4.948458194732666,
"learning_rate": 3.6566186107470514e-05,
"loss": 2.1354,
"step": 1116
},
{
"epoch": 0.04885684773233092,
"grad_norm": 4.321451663970947,
"learning_rate": 3.7581913499344695e-05,
"loss": 2.1236,
"step": 1147
},
{
"epoch": 0.05017730307644797,
"grad_norm": 4.225420951843262,
"learning_rate": 3.8597640891218876e-05,
"loss": 2.109,
"step": 1178
},
{
"epoch": 0.051497758420565025,
"grad_norm": 3.955733299255371,
"learning_rate": 3.9613368283093056e-05,
"loss": 2.0956,
"step": 1209
},
{
"epoch": 0.05281821376468208,
"grad_norm": 4.185420036315918,
"learning_rate": 4.062909567496724e-05,
"loss": 2.0712,
"step": 1240
},
{
"epoch": 0.05413866910879913,
"grad_norm": 4.096803665161133,
"learning_rate": 4.164482306684142e-05,
"loss": 2.0668,
"step": 1271
},
{
"epoch": 0.05545912445291618,
"grad_norm": 4.0685133934021,
"learning_rate": 4.26605504587156e-05,
"loss": 2.0522,
"step": 1302
},
{
"epoch": 0.056779579797033235,
"grad_norm": 3.7675204277038574,
"learning_rate": 4.367627785058978e-05,
"loss": 2.0196,
"step": 1333
},
{
"epoch": 0.05810003514115029,
"grad_norm": 3.8732528686523438,
"learning_rate": 4.469200524246396e-05,
"loss": 2.008,
"step": 1364
},
{
"epoch": 0.05942049048526734,
"grad_norm": 3.6281332969665527,
"learning_rate": 4.570773263433814e-05,
"loss": 2.0225,
"step": 1395
},
{
"epoch": 0.06074094582938439,
"grad_norm": 3.630474805831909,
"learning_rate": 4.672346002621232e-05,
"loss": 1.9959,
"step": 1426
},
{
"epoch": 0.062061401173501445,
"grad_norm": 3.5610458850860596,
"learning_rate": 4.77391874180865e-05,
"loss": 1.9743,
"step": 1457
},
{
"epoch": 0.06338185651761849,
"grad_norm": 3.3346333503723145,
"learning_rate": 4.875491480996068e-05,
"loss": 1.9779,
"step": 1488
},
{
"epoch": 0.06470231186173554,
"grad_norm": 3.3958165645599365,
"learning_rate": 4.977064220183487e-05,
"loss": 1.9418,
"step": 1519
},
{
"epoch": 0.0660227672058526,
"grad_norm": 3.1751558780670166,
"learning_rate": 4.9999915451558777e-05,
"loss": 1.9516,
"step": 1550
},
{
"epoch": 0.06734322254996965,
"grad_norm": 3.2260396480560303,
"learning_rate": 4.999955597496219e-05,
"loss": 1.9547,
"step": 1581
},
{
"epoch": 0.0686636778940867,
"grad_norm": 3.0978410243988037,
"learning_rate": 4.9998914381774255e-05,
"loss": 1.956,
"step": 1612
},
{
"epoch": 0.06998413323820375,
"grad_norm": 3.0465667247772217,
"learning_rate": 4.999799067923527e-05,
"loss": 1.9154,
"step": 1643
},
{
"epoch": 0.0713045885823208,
"grad_norm": 2.839390277862549,
"learning_rate": 4.999678487776908e-05,
"loss": 1.9295,
"step": 1674
},
{
"epoch": 0.07262504392643786,
"grad_norm": 2.9113218784332275,
"learning_rate": 4.9995296990983006e-05,
"loss": 1.9182,
"step": 1705
},
{
"epoch": 0.07394549927055491,
"grad_norm": 3.088271141052246,
"learning_rate": 4.999352703566763e-05,
"loss": 1.8987,
"step": 1736
},
{
"epoch": 0.07526595461467196,
"grad_norm": 2.7890849113464355,
"learning_rate": 4.999147503179668e-05,
"loss": 1.8665,
"step": 1767
},
{
"epoch": 0.07658640995878901,
"grad_norm": 2.795407295227051,
"learning_rate": 4.998914100252672e-05,
"loss": 1.896,
"step": 1798
},
{
"epoch": 0.07790686530290607,
"grad_norm": 2.7121315002441406,
"learning_rate": 4.998652497419696e-05,
"loss": 1.8766,
"step": 1829
},
{
"epoch": 0.07922732064702312,
"grad_norm": 2.75180983543396,
"learning_rate": 4.9983626976328927e-05,
"loss": 1.8708,
"step": 1860
},
{
"epoch": 0.08054777599114017,
"grad_norm": 2.46042799949646,
"learning_rate": 4.998044704162613e-05,
"loss": 1.8606,
"step": 1891
},
{
"epoch": 0.08186823133525722,
"grad_norm": 2.579169511795044,
"learning_rate": 4.9976985205973705e-05,
"loss": 1.8314,
"step": 1922
},
{
"epoch": 0.08318868667937428,
"grad_norm": 2.867847442626953,
"learning_rate": 4.997324150843799e-05,
"loss": 1.8452,
"step": 1953
},
{
"epoch": 0.08450914202349133,
"grad_norm": 2.783097505569458,
"learning_rate": 4.99692159912661e-05,
"loss": 1.8513,
"step": 1984
},
{
"epoch": 0.08582959736760838,
"grad_norm": 2.689948320388794,
"learning_rate": 4.996490869988546e-05,
"loss": 1.8078,
"step": 2015
},
{
"epoch": 0.08715005271172543,
"grad_norm": 2.5084853172302246,
"learning_rate": 4.996031968290326e-05,
"loss": 1.8036,
"step": 2046
},
{
"epoch": 0.08847050805584249,
"grad_norm": 2.3911800384521484,
"learning_rate": 4.995544899210594e-05,
"loss": 1.8146,
"step": 2077
},
{
"epoch": 0.08979096339995954,
"grad_norm": 2.5737738609313965,
"learning_rate": 4.9950296682458583e-05,
"loss": 1.7868,
"step": 2108
},
{
"epoch": 0.09111141874407659,
"grad_norm": 2.506517171859741,
"learning_rate": 4.994486281210429e-05,
"loss": 1.7947,
"step": 2139
},
{
"epoch": 0.09243187408819364,
"grad_norm": 2.4341087341308594,
"learning_rate": 4.9939147442363566e-05,
"loss": 1.7864,
"step": 2170
},
{
"epoch": 0.0937523294323107,
"grad_norm": 2.530733585357666,
"learning_rate": 4.9933150637733574e-05,
"loss": 1.778,
"step": 2201
},
{
"epoch": 0.09507278477642775,
"grad_norm": 2.351055145263672,
"learning_rate": 4.992687246588743e-05,
"loss": 1.7821,
"step": 2232
},
{
"epoch": 0.09639324012054479,
"grad_norm": 2.3601133823394775,
"learning_rate": 4.992031299767347e-05,
"loss": 1.7765,
"step": 2263
},
{
"epoch": 0.09771369546466184,
"grad_norm": 2.4816064834594727,
"learning_rate": 4.9913472307114386e-05,
"loss": 1.7855,
"step": 2294
},
{
"epoch": 0.09903415080877889,
"grad_norm": 2.3871512413024902,
"learning_rate": 4.9906350471406446e-05,
"loss": 1.7343,
"step": 2325
},
{
"epoch": 0.10035460615289594,
"grad_norm": 2.357987642288208,
"learning_rate": 4.989894757091861e-05,
"loss": 1.7511,
"step": 2356
},
{
"epoch": 0.101675061497013,
"grad_norm": 2.2945756912231445,
"learning_rate": 4.989126368919158e-05,
"loss": 1.7602,
"step": 2387
},
{
"epoch": 0.10299551684113005,
"grad_norm": 2.372497081756592,
"learning_rate": 4.988329891293693e-05,
"loss": 1.7485,
"step": 2418
},
{
"epoch": 0.1043159721852471,
"grad_norm": 2.2850053310394287,
"learning_rate": 4.987505333203608e-05,
"loss": 1.749,
"step": 2449
},
{
"epoch": 0.10563642752936415,
"grad_norm": 2.311553955078125,
"learning_rate": 4.9866527039539276e-05,
"loss": 1.7613,
"step": 2480
},
{
"epoch": 0.10695688287348121,
"grad_norm": 2.346198558807373,
"learning_rate": 4.9857720131664594e-05,
"loss": 1.7412,
"step": 2511
},
{
"epoch": 0.10827733821759826,
"grad_norm": 4.81157112121582,
"learning_rate": 4.9848632707796773e-05,
"loss": 1.7303,
"step": 2542
},
{
"epoch": 0.10959779356171531,
"grad_norm": 2.1670663356781006,
"learning_rate": 4.9839264870486155e-05,
"loss": 1.7273,
"step": 2573
},
{
"epoch": 0.11091824890583236,
"grad_norm": 2.2016870975494385,
"learning_rate": 4.9829616725447526e-05,
"loss": 1.7468,
"step": 2604
},
{
"epoch": 0.11223870424994942,
"grad_norm": 2.3066468238830566,
"learning_rate": 4.981968838155888e-05,
"loss": 1.7506,
"step": 2635
},
{
"epoch": 0.11355915959406647,
"grad_norm": 2.3891100883483887,
"learning_rate": 4.980947995086024e-05,
"loss": 1.7037,
"step": 2666
},
{
"epoch": 0.11487961493818352,
"grad_norm": 2.234248399734497,
"learning_rate": 4.979899154855234e-05,
"loss": 1.74,
"step": 2697
},
{
"epoch": 0.11620007028230057,
"grad_norm": 2.1144893169403076,
"learning_rate": 4.9788223292995386e-05,
"loss": 1.7356,
"step": 2728
},
{
"epoch": 0.11752052562641763,
"grad_norm": 2.2365314960479736,
"learning_rate": 4.977717530570768e-05,
"loss": 1.7121,
"step": 2759
},
{
"epoch": 0.11884098097053468,
"grad_norm": 2.1084237098693848,
"learning_rate": 4.976584771136425e-05,
"loss": 1.7213,
"step": 2790
},
{
"epoch": 0.12016143631465173,
"grad_norm": 2.123991012573242,
"learning_rate": 4.975424063779547e-05,
"loss": 1.7181,
"step": 2821
},
{
"epoch": 0.12148189165876878,
"grad_norm": 2.23928165435791,
"learning_rate": 4.974235421598557e-05,
"loss": 1.6927,
"step": 2852
},
{
"epoch": 0.12280234700288584,
"grad_norm": 2.3638722896575928,
"learning_rate": 4.973018858007122e-05,
"loss": 1.739,
"step": 2883
},
{
"epoch": 0.12412280234700289,
"grad_norm": 2.0232160091400146,
"learning_rate": 4.9717743867339963e-05,
"loss": 1.6869,
"step": 2914
},
{
"epoch": 0.12544325769111994,
"grad_norm": 2.0534439086914062,
"learning_rate": 4.9705020218228695e-05,
"loss": 1.6657,
"step": 2945
},
{
"epoch": 0.12676371303523698,
"grad_norm": 2.1189608573913574,
"learning_rate": 4.969201777632205e-05,
"loss": 1.6935,
"step": 2976
},
{
"epoch": 0.12808416837935405,
"grad_norm": 2.021146535873413,
"learning_rate": 4.9678736688350846e-05,
"loss": 1.6653,
"step": 3007
},
{
"epoch": 0.12940462372347108,
"grad_norm": 2.048736095428467,
"learning_rate": 4.966517710419033e-05,
"loss": 1.6953,
"step": 3038
},
{
"epoch": 0.13072507906758815,
"grad_norm": 2.024050235748291,
"learning_rate": 4.965133917685858e-05,
"loss": 1.6933,
"step": 3069
},
{
"epoch": 0.1320455344117052,
"grad_norm": 2.1064541339874268,
"learning_rate": 4.9637223062514714e-05,
"loss": 1.6801,
"step": 3100
},
{
"epoch": 0.13336598975582226,
"grad_norm": 2.080601692199707,
"learning_rate": 4.962282892045718e-05,
"loss": 1.6789,
"step": 3131
},
{
"epoch": 0.1346864450999393,
"grad_norm": 2.012395143508911,
"learning_rate": 4.9608156913121904e-05,
"loss": 1.6844,
"step": 3162
},
{
"epoch": 0.13600690044405636,
"grad_norm": 3.413083791732788,
"learning_rate": 4.959320720608049e-05,
"loss": 1.6658,
"step": 3193
},
{
"epoch": 0.1373273557881734,
"grad_norm": 1.9258606433868408,
"learning_rate": 4.9577979968038354e-05,
"loss": 1.6467,
"step": 3224
},
{
"epoch": 0.13864781113229047,
"grad_norm": 2.08371901512146,
"learning_rate": 4.956247537083282e-05,
"loss": 1.6623,
"step": 3255
},
{
"epoch": 0.1399682664764075,
"grad_norm": 1.8291853666305542,
"learning_rate": 4.9546693589431145e-05,
"loss": 1.6626,
"step": 3286
},
{
"epoch": 0.14128872182052457,
"grad_norm": 1.8504295349121094,
"learning_rate": 4.9530634801928595e-05,
"loss": 1.6645,
"step": 3317
},
{
"epoch": 0.1426091771646416,
"grad_norm": 1.9732643365859985,
"learning_rate": 4.9514299189546395e-05,
"loss": 1.6608,
"step": 3348
},
{
"epoch": 0.14392963250875868,
"grad_norm": 1.901601791381836,
"learning_rate": 4.949768693662973e-05,
"loss": 1.6644,
"step": 3379
},
{
"epoch": 0.14525008785287571,
"grad_norm": 1.9531694650650024,
"learning_rate": 4.948079823064559e-05,
"loss": 1.6234,
"step": 3410
},
{
"epoch": 0.14657054319699278,
"grad_norm": 1.9135621786117554,
"learning_rate": 4.946363326218074e-05,
"loss": 1.6632,
"step": 3441
},
{
"epoch": 0.14789099854110982,
"grad_norm": 2.0635387897491455,
"learning_rate": 4.9446192224939525e-05,
"loss": 1.6705,
"step": 3472
},
{
"epoch": 0.14921145388522689,
"grad_norm": 2.0968971252441406,
"learning_rate": 4.942847531574167e-05,
"loss": 1.6453,
"step": 3503
},
{
"epoch": 0.15053190922934392,
"grad_norm": 2.050825595855713,
"learning_rate": 4.941048273452008e-05,
"loss": 1.6451,
"step": 3534
},
{
"epoch": 0.151852364573461,
"grad_norm": 2.2845866680145264,
"learning_rate": 4.9392214684318605e-05,
"loss": 1.663,
"step": 3565
},
{
"epoch": 0.15317281991757803,
"grad_norm": 1.8283350467681885,
"learning_rate": 4.93736713712897e-05,
"loss": 1.64,
"step": 3596
},
{
"epoch": 0.15449327526169507,
"grad_norm": 1.9321519136428833,
"learning_rate": 4.9354853004692124e-05,
"loss": 1.6354,
"step": 3627
},
{
"epoch": 0.15581373060581213,
"grad_norm": 1.8610464334487915,
"learning_rate": 4.93357597968886e-05,
"loss": 1.6526,
"step": 3658
},
{
"epoch": 0.15713418594992917,
"grad_norm": 1.8374992609024048,
"learning_rate": 4.931639196334338e-05,
"loss": 1.6223,
"step": 3689
},
{
"epoch": 0.15845464129404624,
"grad_norm": 1.8555856943130493,
"learning_rate": 4.9296749722619826e-05,
"loss": 1.6273,
"step": 3720
},
{
"epoch": 0.15977509663816328,
"grad_norm": 1.8162165880203247,
"learning_rate": 4.9276833296377966e-05,
"loss": 1.6298,
"step": 3751
},
{
"epoch": 0.16109555198228034,
"grad_norm": 2.0659849643707275,
"learning_rate": 4.925664290937196e-05,
"loss": 1.6389,
"step": 3782
},
{
"epoch": 0.16241600732639738,
"grad_norm": 1.9556218385696411,
"learning_rate": 4.9236178789447576e-05,
"loss": 1.6435,
"step": 3813
},
{
"epoch": 0.16373646267051445,
"grad_norm": 1.9478511810302734,
"learning_rate": 4.921544116753962e-05,
"loss": 1.6262,
"step": 3844
},
{
"epoch": 0.1650569180146315,
"grad_norm": 1.8815808296203613,
"learning_rate": 4.919443027766935e-05,
"loss": 1.6319,
"step": 3875
},
{
"epoch": 0.16637737335874855,
"grad_norm": 1.8547437191009521,
"learning_rate": 4.91731463569418e-05,
"loss": 1.6234,
"step": 3906
},
{
"epoch": 0.1676978287028656,
"grad_norm": 1.8541631698608398,
"learning_rate": 4.915158964554312e-05,
"loss": 1.6183,
"step": 3937
},
{
"epoch": 0.16901828404698266,
"grad_norm": 1.837897777557373,
"learning_rate": 4.912976038673786e-05,
"loss": 1.592,
"step": 3968
},
{
"epoch": 0.1703387393910997,
"grad_norm": 1.8930044174194336,
"learning_rate": 4.9107658826866254e-05,
"loss": 1.6191,
"step": 3999
},
{
"epoch": 0.17165919473521676,
"grad_norm": 1.866008996963501,
"learning_rate": 4.908528521534139e-05,
"loss": 1.6197,
"step": 4030
},
{
"epoch": 0.1729796500793338,
"grad_norm": 1.9145745038986206,
"learning_rate": 4.906263980464644e-05,
"loss": 1.6058,
"step": 4061
},
{
"epoch": 0.17430010542345087,
"grad_norm": 1.777824878692627,
"learning_rate": 4.903972285033178e-05,
"loss": 1.6087,
"step": 4092
},
{
"epoch": 0.1756205607675679,
"grad_norm": 1.8439857959747314,
"learning_rate": 4.901653461101213e-05,
"loss": 1.6323,
"step": 4123
},
{
"epoch": 0.17694101611168497,
"grad_norm": 1.7481130361557007,
"learning_rate": 4.8993075348363626e-05,
"loss": 1.6181,
"step": 4154
},
{
"epoch": 0.178261471455802,
"grad_norm": 1.7154821157455444,
"learning_rate": 4.896934532712084e-05,
"loss": 1.6111,
"step": 4185
},
{
"epoch": 0.17958192679991908,
"grad_norm": 1.7249122858047485,
"learning_rate": 4.8945344815073846e-05,
"loss": 1.5984,
"step": 4216
},
{
"epoch": 0.18090238214403612,
"grad_norm": 1.7663273811340332,
"learning_rate": 4.892107408306516e-05,
"loss": 1.6062,
"step": 4247
},
{
"epoch": 0.18222283748815318,
"grad_norm": 1.776564598083496,
"learning_rate": 4.889653340498669e-05,
"loss": 1.5915,
"step": 4278
},
{
"epoch": 0.18354329283227022,
"grad_norm": 1.8661930561065674,
"learning_rate": 4.8871723057776664e-05,
"loss": 1.5929,
"step": 4309
},
{
"epoch": 0.1848637481763873,
"grad_norm": 1.9238152503967285,
"learning_rate": 4.8846643321416476e-05,
"loss": 1.6076,
"step": 4340
},
{
"epoch": 0.18618420352050433,
"grad_norm": 1.8570325374603271,
"learning_rate": 4.882129447892753e-05,
"loss": 1.6095,
"step": 4371
},
{
"epoch": 0.1875046588646214,
"grad_norm": 2.4054951667785645,
"learning_rate": 4.8795676816368076e-05,
"loss": 1.5968,
"step": 4402
},
{
"epoch": 0.18882511420873843,
"grad_norm": 1.845065951347351,
"learning_rate": 4.876979062282995e-05,
"loss": 1.5885,
"step": 4433
},
{
"epoch": 0.1901455695528555,
"grad_norm": 1.797475814819336,
"learning_rate": 4.8743636190435325e-05,
"loss": 1.5794,
"step": 4464
},
{
"epoch": 0.19146602489697254,
"grad_norm": 1.7853962182998657,
"learning_rate": 4.871721381433344e-05,
"loss": 1.5787,
"step": 4495
},
{
"epoch": 0.19278648024108958,
"grad_norm": 1.712103247642517,
"learning_rate": 4.869052379269719e-05,
"loss": 1.5882,
"step": 4526
},
{
"epoch": 0.19410693558520664,
"grad_norm": 1.7332582473754883,
"learning_rate": 4.866356642671985e-05,
"loss": 1.5904,
"step": 4557
},
{
"epoch": 0.19542739092932368,
"grad_norm": 1.699765920639038,
"learning_rate": 4.8636342020611634e-05,
"loss": 1.5711,
"step": 4588
},
{
"epoch": 0.19674784627344075,
"grad_norm": 1.80332612991333,
"learning_rate": 4.860885088159626e-05,
"loss": 1.5885,
"step": 4619
},
{
"epoch": 0.19806830161755778,
"grad_norm": 1.9262676239013672,
"learning_rate": 4.858109331990751e-05,
"loss": 1.5885,
"step": 4650
},
{
"epoch": 0.19938875696167485,
"grad_norm": 1.7199647426605225,
"learning_rate": 4.855306964878567e-05,
"loss": 1.5931,
"step": 4681
},
{
"epoch": 0.2007092123057919,
"grad_norm": 1.769418716430664,
"learning_rate": 4.8524780184474084e-05,
"loss": 1.5833,
"step": 4712
},
{
"epoch": 0.20202966764990896,
"grad_norm": 1.6230579614639282,
"learning_rate": 4.8496225246215496e-05,
"loss": 1.589,
"step": 4743
},
{
"epoch": 0.203350122994026,
"grad_norm": 1.6618564128875732,
"learning_rate": 4.8467405156248505e-05,
"loss": 1.5925,
"step": 4774
},
{
"epoch": 0.20467057833814306,
"grad_norm": 1.7645457983016968,
"learning_rate": 4.843832023980392e-05,
"loss": 1.5733,
"step": 4805
},
{
"epoch": 0.2059910336822601,
"grad_norm": 1.6856187582015991,
"learning_rate": 4.840897082510106e-05,
"loss": 1.5927,
"step": 4836
},
{
"epoch": 0.20731148902637717,
"grad_norm": 1.6648253202438354,
"learning_rate": 4.8379357243344084e-05,
"loss": 1.593,
"step": 4867
},
{
"epoch": 0.2086319443704942,
"grad_norm": 1.7412372827529907,
"learning_rate": 4.8349479828718236e-05,
"loss": 1.5743,
"step": 4898
},
{
"epoch": 0.20995239971461127,
"grad_norm": 1.744364619255066,
"learning_rate": 4.8319338918386075e-05,
"loss": 1.5874,
"step": 4929
},
{
"epoch": 0.2112728550587283,
"grad_norm": 1.6645615100860596,
"learning_rate": 4.828893485248369e-05,
"loss": 1.5756,
"step": 4960
},
{
"epoch": 0.21259331040284538,
"grad_norm": 1.664466381072998,
"learning_rate": 4.825826797411682e-05,
"loss": 1.5756,
"step": 4991
},
{
"epoch": 0.21391376574696241,
"grad_norm": 1.7059963941574097,
"learning_rate": 4.822733862935702e-05,
"loss": 1.5764,
"step": 5022
},
{
"epoch": 0.21523422109107948,
"grad_norm": 1.759968876838684,
"learning_rate": 4.819614716723775e-05,
"loss": 1.5728,
"step": 5053
},
{
"epoch": 0.21655467643519652,
"grad_norm": 1.6804170608520508,
"learning_rate": 4.8164693939750425e-05,
"loss": 1.5612,
"step": 5084
},
{
"epoch": 0.21787513177931359,
"grad_norm": 1.8005627393722534,
"learning_rate": 4.813297930184042e-05,
"loss": 1.5608,
"step": 5115
},
{
"epoch": 0.21919558712343062,
"grad_norm": 1.762055516242981,
"learning_rate": 4.810100361140314e-05,
"loss": 1.5741,
"step": 5146
},
{
"epoch": 0.2205160424675477,
"grad_norm": 1.6809359788894653,
"learning_rate": 4.8068767229279885e-05,
"loss": 1.586,
"step": 5177
},
{
"epoch": 0.22183649781166473,
"grad_norm": 1.6193108558654785,
"learning_rate": 4.8036270519253854e-05,
"loss": 1.595,
"step": 5208
},
{
"epoch": 0.2231569531557818,
"grad_norm": 1.654219150543213,
"learning_rate": 4.8003513848046e-05,
"loss": 1.5897,
"step": 5239
},
{
"epoch": 0.22447740849989883,
"grad_norm": 1.5731104612350464,
"learning_rate": 4.79704975853109e-05,
"loss": 1.5593,
"step": 5270
},
{
"epoch": 0.2257978638440159,
"grad_norm": 1.8123056888580322,
"learning_rate": 4.793722210363262e-05,
"loss": 1.5679,
"step": 5301
},
{
"epoch": 0.22711831918813294,
"grad_norm": 1.6057484149932861,
"learning_rate": 4.7903687778520414e-05,
"loss": 1.5585,
"step": 5332
},
{
"epoch": 0.22843877453225,
"grad_norm": 1.6405997276306152,
"learning_rate": 4.7869894988404593e-05,
"loss": 1.5664,
"step": 5363
},
{
"epoch": 0.22975922987636704,
"grad_norm": 1.6537870168685913,
"learning_rate": 4.783584411463221e-05,
"loss": 1.5465,
"step": 5394
},
{
"epoch": 0.23107968522048408,
"grad_norm": 1.6436322927474976,
"learning_rate": 4.780153554146274e-05,
"loss": 1.5556,
"step": 5425
},
{
"epoch": 0.23240014056460115,
"grad_norm": 1.7310768365859985,
"learning_rate": 4.7766969656063766e-05,
"loss": 1.5615,
"step": 5456
},
{
"epoch": 0.2337205959087182,
"grad_norm": 1.6515048742294312,
"learning_rate": 4.773214684850662e-05,
"loss": 1.5541,
"step": 5487
},
{
"epoch": 0.23504105125283525,
"grad_norm": 1.5832430124282837,
"learning_rate": 4.769706751176193e-05,
"loss": 1.556,
"step": 5518
},
{
"epoch": 0.2363615065969523,
"grad_norm": 1.7008590698242188,
"learning_rate": 4.7661732041695264e-05,
"loss": 1.5571,
"step": 5549
},
{
"epoch": 0.23768196194106936,
"grad_norm": 1.6773130893707275,
"learning_rate": 4.762614083706258e-05,
"loss": 1.5594,
"step": 5580
},
{
"epoch": 0.2390024172851864,
"grad_norm": 1.617154598236084,
"learning_rate": 4.759029429950581e-05,
"loss": 1.5501,
"step": 5611
},
{
"epoch": 0.24032287262930346,
"grad_norm": 1.7171076536178589,
"learning_rate": 4.7554192833548235e-05,
"loss": 1.5504,
"step": 5642
},
{
"epoch": 0.2416433279734205,
"grad_norm": 1.8325423002243042,
"learning_rate": 4.751783684659e-05,
"loss": 1.5606,
"step": 5673
},
{
"epoch": 0.24296378331753757,
"grad_norm": 1.5625604391098022,
"learning_rate": 4.748122674890348e-05,
"loss": 1.5546,
"step": 5704
},
{
"epoch": 0.2442842386616546,
"grad_norm": 1.7324423789978027,
"learning_rate": 4.7444362953628654e-05,
"loss": 1.5519,
"step": 5735
},
{
"epoch": 0.24560469400577167,
"grad_norm": 1.6850440502166748,
"learning_rate": 4.7407245876768424e-05,
"loss": 1.5614,
"step": 5766
},
{
"epoch": 0.2469251493498887,
"grad_norm": 1.624969244003296,
"learning_rate": 4.736987593718397e-05,
"loss": 1.5418,
"step": 5797
},
{
"epoch": 0.24824560469400578,
"grad_norm": 1.6892682313919067,
"learning_rate": 4.733225355658999e-05,
"loss": 1.5323,
"step": 5828
},
{
"epoch": 0.24956606003812282,
"grad_norm": 1.626842737197876,
"learning_rate": 4.7294379159549926e-05,
"loss": 1.5425,
"step": 5859
},
{
"epoch": 0.2508865153822399,
"grad_norm": 1.7167010307312012,
"learning_rate": 4.725625317347119e-05,
"loss": 1.5395,
"step": 5890
},
{
"epoch": 0.25220697072635695,
"grad_norm": 1.6276217699050903,
"learning_rate": 4.7217876028600374e-05,
"loss": 1.5326,
"step": 5921
},
{
"epoch": 0.25352742607047396,
"grad_norm": 1.6535232067108154,
"learning_rate": 4.717924815801832e-05,
"loss": 1.5867,
"step": 5952
},
{
"epoch": 0.254847881414591,
"grad_norm": 1.666059970855713,
"learning_rate": 4.714036999763532e-05,
"loss": 1.5544,
"step": 5983
},
{
"epoch": 0.2561683367587081,
"grad_norm": 1.6418869495391846,
"learning_rate": 4.7101241986186116e-05,
"loss": 1.5506,
"step": 6014
},
{
"epoch": 0.25748879210282516,
"grad_norm": 1.6880836486816406,
"learning_rate": 4.7061864565225e-05,
"loss": 1.5387,
"step": 6045
},
{
"epoch": 0.25880924744694217,
"grad_norm": 1.633300542831421,
"learning_rate": 4.702223817912081e-05,
"loss": 1.5446,
"step": 6076
}
],
"logging_steps": 31,
"max_steps": 30517,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 3052,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.527890108044542e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}