zephyr-7b-sft-full / trainer_state.json
RikkiXu's picture
Model save
759ed41 verified
raw
history blame
36.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1107,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 7.434891346998684,
"learning_rate": 1.801801801801802e-07,
"loss": 1.1387,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 6.054112603313701,
"learning_rate": 9.00900900900901e-07,
"loss": 1.0767,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 2.720345942108079,
"learning_rate": 1.801801801801802e-06,
"loss": 1.0177,
"step": 10
},
{
"epoch": 0.01,
"grad_norm": 3.1804731128565717,
"learning_rate": 2.702702702702703e-06,
"loss": 1.0144,
"step": 15
},
{
"epoch": 0.02,
"grad_norm": 2.301849657938967,
"learning_rate": 3.603603603603604e-06,
"loss": 0.9791,
"step": 20
},
{
"epoch": 0.02,
"grad_norm": 2.4337369010470637,
"learning_rate": 4.504504504504505e-06,
"loss": 0.9802,
"step": 25
},
{
"epoch": 0.03,
"grad_norm": 1.9302145168774039,
"learning_rate": 5.405405405405406e-06,
"loss": 0.986,
"step": 30
},
{
"epoch": 0.03,
"grad_norm": 1.8524872666819012,
"learning_rate": 6.3063063063063065e-06,
"loss": 0.9589,
"step": 35
},
{
"epoch": 0.04,
"grad_norm": 1.8144517560069848,
"learning_rate": 7.207207207207208e-06,
"loss": 0.9633,
"step": 40
},
{
"epoch": 0.04,
"grad_norm": 2.010937969129206,
"learning_rate": 8.108108108108109e-06,
"loss": 0.9687,
"step": 45
},
{
"epoch": 0.05,
"grad_norm": 2.004039674415607,
"learning_rate": 9.00900900900901e-06,
"loss": 0.9419,
"step": 50
},
{
"epoch": 0.05,
"grad_norm": 1.9619351066753616,
"learning_rate": 9.90990990990991e-06,
"loss": 0.9751,
"step": 55
},
{
"epoch": 0.05,
"grad_norm": 2.117833280361577,
"learning_rate": 1.0810810810810812e-05,
"loss": 0.9631,
"step": 60
},
{
"epoch": 0.06,
"grad_norm": 3.1049875306196606,
"learning_rate": 1.1711711711711713e-05,
"loss": 0.9668,
"step": 65
},
{
"epoch": 0.06,
"grad_norm": 2.214128699414308,
"learning_rate": 1.2612612612612613e-05,
"loss": 0.9635,
"step": 70
},
{
"epoch": 0.07,
"grad_norm": 1.737941228120663,
"learning_rate": 1.3513513513513515e-05,
"loss": 0.976,
"step": 75
},
{
"epoch": 0.07,
"grad_norm": 1.8456119696518833,
"learning_rate": 1.4414414414414416e-05,
"loss": 0.9846,
"step": 80
},
{
"epoch": 0.08,
"grad_norm": 1.7815352366071144,
"learning_rate": 1.5315315315315316e-05,
"loss": 0.9783,
"step": 85
},
{
"epoch": 0.08,
"grad_norm": 2.0381827638345844,
"learning_rate": 1.6216216216216218e-05,
"loss": 0.9701,
"step": 90
},
{
"epoch": 0.09,
"grad_norm": 3.8119526094398513,
"learning_rate": 1.711711711711712e-05,
"loss": 0.9867,
"step": 95
},
{
"epoch": 0.09,
"grad_norm": 2.3244802021753816,
"learning_rate": 1.801801801801802e-05,
"loss": 0.9799,
"step": 100
},
{
"epoch": 0.09,
"grad_norm": 2.193951315428562,
"learning_rate": 1.891891891891892e-05,
"loss": 1.0084,
"step": 105
},
{
"epoch": 0.1,
"grad_norm": 2.2121294806446365,
"learning_rate": 1.981981981981982e-05,
"loss": 0.9731,
"step": 110
},
{
"epoch": 0.1,
"grad_norm": 2.105745826240662,
"learning_rate": 1.999920408755684e-05,
"loss": 0.9968,
"step": 115
},
{
"epoch": 0.11,
"grad_norm": 2.0624008245016165,
"learning_rate": 1.9995970910394228e-05,
"loss": 1.0007,
"step": 120
},
{
"epoch": 0.11,
"grad_norm": 1.9216817238638413,
"learning_rate": 1.9990251527524178e-05,
"loss": 0.9864,
"step": 125
},
{
"epoch": 0.12,
"grad_norm": 1.9416400115913934,
"learning_rate": 1.998204736147608e-05,
"loss": 0.982,
"step": 130
},
{
"epoch": 0.12,
"grad_norm": 1.992023353075518,
"learning_rate": 1.9971360452796523e-05,
"loss": 0.9901,
"step": 135
},
{
"epoch": 0.13,
"grad_norm": 2.082117848176388,
"learning_rate": 1.9958193459541804e-05,
"loss": 1.0065,
"step": 140
},
{
"epoch": 0.13,
"grad_norm": 1.9564902575341125,
"learning_rate": 1.994254965661679e-05,
"loss": 1.0058,
"step": 145
},
{
"epoch": 0.14,
"grad_norm": 25.696326656261338,
"learning_rate": 1.9924432934960384e-05,
"loss": 1.1023,
"step": 150
},
{
"epoch": 0.14,
"grad_norm": 15.718602388026698,
"learning_rate": 1.9903847800577777e-05,
"loss": 1.1922,
"step": 155
},
{
"epoch": 0.14,
"grad_norm": 6.361436623798567,
"learning_rate": 1.9880799373419698e-05,
"loss": 1.1022,
"step": 160
},
{
"epoch": 0.15,
"grad_norm": 14.018808638392496,
"learning_rate": 1.9855293386108995e-05,
"loss": 1.0509,
"step": 165
},
{
"epoch": 0.15,
"grad_norm": 2.396996729925699,
"learning_rate": 1.982733618251478e-05,
"loss": 1.0454,
"step": 170
},
{
"epoch": 0.16,
"grad_norm": 2.0783372576733012,
"learning_rate": 1.979693471617462e-05,
"loss": 1.0209,
"step": 175
},
{
"epoch": 0.16,
"grad_norm": 2.3172426926555207,
"learning_rate": 1.976409654856501e-05,
"loss": 1.0314,
"step": 180
},
{
"epoch": 0.17,
"grad_norm": 2.0444492620330186,
"learning_rate": 1.97288298472207e-05,
"loss": 1.003,
"step": 185
},
{
"epoch": 0.17,
"grad_norm": 1.881906410360296,
"learning_rate": 1.969114338370324e-05,
"loss": 1.0024,
"step": 190
},
{
"epoch": 0.18,
"grad_norm": 1.6740200356982151,
"learning_rate": 1.9651046531419335e-05,
"loss": 1.0041,
"step": 195
},
{
"epoch": 0.18,
"grad_norm": 1.744682737538121,
"learning_rate": 1.960854926328946e-05,
"loss": 1.0108,
"step": 200
},
{
"epoch": 0.19,
"grad_norm": 1.7487489845353397,
"learning_rate": 1.9563662149267405e-05,
"loss": 1.0009,
"step": 205
},
{
"epoch": 0.19,
"grad_norm": 1.7482821787721043,
"learning_rate": 1.9516396353711297e-05,
"loss": 1.008,
"step": 210
},
{
"epoch": 0.19,
"grad_norm": 1.7209209399401664,
"learning_rate": 1.946676363260679e-05,
"loss": 0.9967,
"step": 215
},
{
"epoch": 0.2,
"grad_norm": 1.6520280771666889,
"learning_rate": 1.9414776330643126e-05,
"loss": 0.991,
"step": 220
},
{
"epoch": 0.2,
"grad_norm": 1.899715362613167,
"learning_rate": 1.936044737814273e-05,
"loss": 1.0021,
"step": 225
},
{
"epoch": 0.21,
"grad_norm": 1.6989493561259785,
"learning_rate": 1.9303790287845183e-05,
"loss": 0.9902,
"step": 230
},
{
"epoch": 0.21,
"grad_norm": 1.7638925291836884,
"learning_rate": 1.9244819151546325e-05,
"loss": 0.9976,
"step": 235
},
{
"epoch": 0.22,
"grad_norm": 1.564735067537867,
"learning_rate": 1.9183548636593322e-05,
"loss": 0.9787,
"step": 240
},
{
"epoch": 0.22,
"grad_norm": 1.7635286854536336,
"learning_rate": 1.9119993982236608e-05,
"loss": 0.9937,
"step": 245
},
{
"epoch": 0.23,
"grad_norm": 1.5741256061070714,
"learning_rate": 1.9054170995839546e-05,
"loss": 0.9648,
"step": 250
},
{
"epoch": 0.23,
"grad_norm": 1.7091189941765559,
"learning_rate": 1.8986096048946826e-05,
"loss": 0.9818,
"step": 255
},
{
"epoch": 0.23,
"grad_norm": 1.5405427151225155,
"learning_rate": 1.8915786073212508e-05,
"loss": 0.9958,
"step": 260
},
{
"epoch": 0.24,
"grad_norm": 1.5492700267103499,
"learning_rate": 1.8843258556188787e-05,
"loss": 0.9924,
"step": 265
},
{
"epoch": 0.24,
"grad_norm": 1.6206079313144814,
"learning_rate": 1.8768531536976452e-05,
"loss": 0.9804,
"step": 270
},
{
"epoch": 0.25,
"grad_norm": 1.5730537338272383,
"learning_rate": 1.86916236017382e-05,
"loss": 0.9847,
"step": 275
},
{
"epoch": 0.25,
"grad_norm": 1.6501336616437525,
"learning_rate": 1.8612553879075875e-05,
"loss": 0.983,
"step": 280
},
{
"epoch": 0.26,
"grad_norm": 1.5113060463908174,
"learning_rate": 1.8531342035272768e-05,
"loss": 0.981,
"step": 285
},
{
"epoch": 0.26,
"grad_norm": 1.5929173745457115,
"learning_rate": 1.844800826940223e-05,
"loss": 0.9789,
"step": 290
},
{
"epoch": 0.27,
"grad_norm": 1.598141976179977,
"learning_rate": 1.836257330830372e-05,
"loss": 1.0036,
"step": 295
},
{
"epoch": 0.27,
"grad_norm": 1.8798731248860165,
"learning_rate": 1.8275058401427622e-05,
"loss": 0.9704,
"step": 300
},
{
"epoch": 0.28,
"grad_norm": 2.195099845300529,
"learning_rate": 1.8185485315550062e-05,
"loss": 0.968,
"step": 305
},
{
"epoch": 0.28,
"grad_norm": 1.6333370138254395,
"learning_rate": 1.809387632935906e-05,
"loss": 0.9884,
"step": 310
},
{
"epoch": 0.28,
"grad_norm": 1.6383788031138038,
"learning_rate": 1.8000254227913346e-05,
"loss": 0.976,
"step": 315
},
{
"epoch": 0.29,
"grad_norm": 1.59375997270626,
"learning_rate": 1.7904642296975263e-05,
"loss": 0.9752,
"step": 320
},
{
"epoch": 0.29,
"grad_norm": 1.5470092112631526,
"learning_rate": 1.7807064317219096e-05,
"loss": 0.9684,
"step": 325
},
{
"epoch": 0.3,
"grad_norm": 1.5761252347776267,
"learning_rate": 1.7707544558316332e-05,
"loss": 0.983,
"step": 330
},
{
"epoch": 0.3,
"grad_norm": 1.4924968164344596,
"learning_rate": 1.760610777289929e-05,
"loss": 0.9843,
"step": 335
},
{
"epoch": 0.31,
"grad_norm": 1.4359693377296177,
"learning_rate": 1.7502779190404615e-05,
"loss": 0.9634,
"step": 340
},
{
"epoch": 0.31,
"grad_norm": 1.5878997655742073,
"learning_rate": 1.7397584510798208e-05,
"loss": 0.9758,
"step": 345
},
{
"epoch": 0.32,
"grad_norm": 1.6814035465687263,
"learning_rate": 1.7290549898183113e-05,
"loss": 0.967,
"step": 350
},
{
"epoch": 0.32,
"grad_norm": 1.4871838892694749,
"learning_rate": 1.7181701974291927e-05,
"loss": 0.953,
"step": 355
},
{
"epoch": 0.33,
"grad_norm": 1.677903630677117,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.9638,
"step": 360
},
{
"epoch": 0.33,
"grad_norm": 1.7990895100977344,
"learning_rate": 1.6958674927919213e-05,
"loss": 0.9904,
"step": 365
},
{
"epoch": 0.33,
"grad_norm": 1.577389298855143,
"learning_rate": 1.6844551276899184e-05,
"loss": 0.9714,
"step": 370
},
{
"epoch": 0.34,
"grad_norm": 1.6428970048321387,
"learning_rate": 1.672872524372919e-05,
"loss": 0.9925,
"step": 375
},
{
"epoch": 0.34,
"grad_norm": 1.6313220262054722,
"learning_rate": 1.6611225636750838e-05,
"loss": 0.9579,
"step": 380
},
{
"epoch": 0.35,
"grad_norm": 1.4972553968322877,
"learning_rate": 1.649208168055833e-05,
"loss": 0.9747,
"step": 385
},
{
"epoch": 0.35,
"grad_norm": 1.5447739295558658,
"learning_rate": 1.637132300872969e-05,
"loss": 0.9805,
"step": 390
},
{
"epoch": 0.36,
"grad_norm": 1.5876140330526054,
"learning_rate": 1.6248979656456273e-05,
"loss": 0.9684,
"step": 395
},
{
"epoch": 0.36,
"grad_norm": 1.5582777256666884,
"learning_rate": 1.6125082053072408e-05,
"loss": 0.957,
"step": 400
},
{
"epoch": 0.37,
"grad_norm": 1.5476213766084626,
"learning_rate": 1.5999661014486956e-05,
"loss": 0.9861,
"step": 405
},
{
"epoch": 0.37,
"grad_norm": 1.6383105709040227,
"learning_rate": 1.58727477355188e-05,
"loss": 0.9793,
"step": 410
},
{
"epoch": 0.37,
"grad_norm": 1.5270291237304714,
"learning_rate": 1.5744373782137993e-05,
"loss": 0.9608,
"step": 415
},
{
"epoch": 0.38,
"grad_norm": 1.5686224715893557,
"learning_rate": 1.5614571083614683e-05,
"loss": 0.975,
"step": 420
},
{
"epoch": 0.38,
"grad_norm": 1.5293178485058705,
"learning_rate": 1.5483371924577633e-05,
"loss": 0.9632,
"step": 425
},
{
"epoch": 0.39,
"grad_norm": 1.4815279637987373,
"learning_rate": 1.535080893698435e-05,
"loss": 0.9689,
"step": 430
},
{
"epoch": 0.39,
"grad_norm": 1.5169260213036269,
"learning_rate": 1.5216915092004847e-05,
"loss": 0.9809,
"step": 435
},
{
"epoch": 0.4,
"grad_norm": 1.4976729343178568,
"learning_rate": 1.5081723691821029e-05,
"loss": 0.9712,
"step": 440
},
{
"epoch": 0.4,
"grad_norm": 1.4442693064244245,
"learning_rate": 1.4945268361343747e-05,
"loss": 0.9815,
"step": 445
},
{
"epoch": 0.41,
"grad_norm": 1.55780608281581,
"learning_rate": 1.4807583039849589e-05,
"loss": 0.9872,
"step": 450
},
{
"epoch": 0.41,
"grad_norm": 1.454973247549993,
"learning_rate": 1.4668701972539459e-05,
"loss": 0.953,
"step": 455
},
{
"epoch": 0.42,
"grad_norm": 1.5744354457111398,
"learning_rate": 1.4528659702021108e-05,
"loss": 0.9569,
"step": 460
},
{
"epoch": 0.42,
"grad_norm": 1.5374683976132577,
"learning_rate": 1.4387491059717653e-05,
"loss": 0.9544,
"step": 465
},
{
"epoch": 0.42,
"grad_norm": 1.5356499554288368,
"learning_rate": 1.4245231157204282e-05,
"loss": 0.9762,
"step": 470
},
{
"epoch": 0.43,
"grad_norm": 1.451816573803636,
"learning_rate": 1.4101915377475275e-05,
"loss": 0.9484,
"step": 475
},
{
"epoch": 0.43,
"grad_norm": 1.4189149204667209,
"learning_rate": 1.3957579366143521e-05,
"loss": 0.9568,
"step": 480
},
{
"epoch": 0.44,
"grad_norm": 1.4438844550057277,
"learning_rate": 1.3812259022574717e-05,
"loss": 0.9678,
"step": 485
},
{
"epoch": 0.44,
"grad_norm": 1.4944146133812288,
"learning_rate": 1.3665990490958438e-05,
"loss": 0.9684,
"step": 490
},
{
"epoch": 0.45,
"grad_norm": 1.567533543577245,
"learning_rate": 1.351881015131833e-05,
"loss": 0.9523,
"step": 495
},
{
"epoch": 0.45,
"grad_norm": 1.4298833694464113,
"learning_rate": 1.3370754610463655e-05,
"loss": 0.9547,
"step": 500
},
{
"epoch": 0.46,
"grad_norm": 1.586075303116762,
"learning_rate": 1.3221860692884396e-05,
"loss": 0.9621,
"step": 505
},
{
"epoch": 0.46,
"grad_norm": 1.4390997480170529,
"learning_rate": 1.307216543159225e-05,
"loss": 0.9361,
"step": 510
},
{
"epoch": 0.47,
"grad_norm": 1.5962792654589735,
"learning_rate": 1.2921706058909757e-05,
"loss": 0.952,
"step": 515
},
{
"epoch": 0.47,
"grad_norm": 1.5112017838877818,
"learning_rate": 1.2770519997209837e-05,
"loss": 0.9501,
"step": 520
},
{
"epoch": 0.47,
"grad_norm": 1.46430521195488,
"learning_rate": 1.2618644849608068e-05,
"loss": 0.9656,
"step": 525
},
{
"epoch": 0.48,
"grad_norm": 1.472561859950697,
"learning_rate": 1.246611839061002e-05,
"loss": 0.9545,
"step": 530
},
{
"epoch": 0.48,
"grad_norm": 1.5276258975583332,
"learning_rate": 1.2312978556715934e-05,
"loss": 0.9502,
"step": 535
},
{
"epoch": 0.49,
"grad_norm": 1.5767752712595098,
"learning_rate": 1.2159263436985139e-05,
"loss": 0.9497,
"step": 540
},
{
"epoch": 0.49,
"grad_norm": 1.4814084910286585,
"learning_rate": 1.2005011263562514e-05,
"loss": 0.953,
"step": 545
},
{
"epoch": 0.5,
"grad_norm": 1.4811159993074694,
"learning_rate": 1.185026040216934e-05,
"loss": 0.9517,
"step": 550
},
{
"epoch": 0.5,
"grad_norm": 1.5425020495972324,
"learning_rate": 1.1695049342560969e-05,
"loss": 0.9536,
"step": 555
},
{
"epoch": 0.51,
"grad_norm": 1.4813121305496708,
"learning_rate": 1.1539416688953613e-05,
"loss": 0.9566,
"step": 560
},
{
"epoch": 0.51,
"grad_norm": 1.5386521152381667,
"learning_rate": 1.138340115042267e-05,
"loss": 0.968,
"step": 565
},
{
"epoch": 0.51,
"grad_norm": 1.4985329754887164,
"learning_rate": 1.1227041531274978e-05,
"loss": 0.9536,
"step": 570
},
{
"epoch": 0.52,
"grad_norm": 1.7426405055010268,
"learning_rate": 1.1070376721397374e-05,
"loss": 0.9387,
"step": 575
},
{
"epoch": 0.52,
"grad_norm": 1.4876962547232626,
"learning_rate": 1.0913445686583974e-05,
"loss": 0.9479,
"step": 580
},
{
"epoch": 0.53,
"grad_norm": 1.4005947575155968,
"learning_rate": 1.075628745884457e-05,
"loss": 0.94,
"step": 585
},
{
"epoch": 0.53,
"grad_norm": 1.4806276567215155,
"learning_rate": 1.0598941126696545e-05,
"loss": 0.9537,
"step": 590
},
{
"epoch": 0.54,
"grad_norm": 1.3867191265630952,
"learning_rate": 1.0441445825442773e-05,
"loss": 0.9362,
"step": 595
},
{
"epoch": 0.54,
"grad_norm": 1.4082068202931468,
"learning_rate": 1.0283840727437832e-05,
"loss": 0.9391,
"step": 600
},
{
"epoch": 0.55,
"grad_norm": 1.4462569599659194,
"learning_rate": 1.012616503234504e-05,
"loss": 0.9655,
"step": 605
},
{
"epoch": 0.55,
"grad_norm": 1.4280342668958195,
"learning_rate": 9.968457957386663e-06,
"loss": 0.9297,
"step": 610
},
{
"epoch": 0.56,
"grad_norm": 1.4502290522153605,
"learning_rate": 9.810758727589814e-06,
"loss": 0.9486,
"step": 615
},
{
"epoch": 0.56,
"grad_norm": 1.3531947713121897,
"learning_rate": 9.65310656603033e-06,
"loss": 0.9374,
"step": 620
},
{
"epoch": 0.56,
"grad_norm": 1.5003587863241752,
"learning_rate": 9.495540684077215e-06,
"loss": 0.952,
"step": 625
},
{
"epoch": 0.57,
"grad_norm": 1.4085207232358623,
"learning_rate": 9.338100271639932e-06,
"loss": 0.9211,
"step": 630
},
{
"epoch": 0.57,
"grad_norm": 1.4167180963126849,
"learning_rate": 9.180824487421077e-06,
"loss": 0.9291,
"step": 635
},
{
"epoch": 0.58,
"grad_norm": 1.444242534136093,
"learning_rate": 9.023752449176773e-06,
"loss": 0.9338,
"step": 640
},
{
"epoch": 0.58,
"grad_norm": 1.474627058570353,
"learning_rate": 8.866923223987303e-06,
"loss": 0.932,
"step": 645
},
{
"epoch": 0.59,
"grad_norm": 1.3786541919625397,
"learning_rate": 8.71037581854028e-06,
"loss": 0.9287,
"step": 650
},
{
"epoch": 0.59,
"grad_norm": 1.4174870026814845,
"learning_rate": 8.554149169428894e-06,
"loss": 0.9396,
"step": 655
},
{
"epoch": 0.6,
"grad_norm": 1.4346984007547974,
"learning_rate": 8.398282133467579e-06,
"loss": 0.9353,
"step": 660
},
{
"epoch": 0.6,
"grad_norm": 1.3995616959967054,
"learning_rate": 8.242813478027491e-06,
"loss": 0.9451,
"step": 665
},
{
"epoch": 0.61,
"grad_norm": 1.4298853430595138,
"learning_rate": 8.087781871394281e-06,
"loss": 0.9294,
"step": 670
},
{
"epoch": 0.61,
"grad_norm": 4.062626134056569,
"learning_rate": 7.93322587315047e-06,
"loss": 0.9486,
"step": 675
},
{
"epoch": 0.61,
"grad_norm": 2.593063209369072,
"learning_rate": 7.7791839245849e-06,
"loss": 0.9323,
"step": 680
},
{
"epoch": 0.62,
"grad_norm": 1.4402410302679418,
"learning_rate": 7.625694339131564e-06,
"loss": 0.9208,
"step": 685
},
{
"epoch": 0.62,
"grad_norm": 1.427719727713364,
"learning_rate": 7.4727952928402695e-06,
"loss": 0.9432,
"step": 690
},
{
"epoch": 0.63,
"grad_norm": 1.4229770799618295,
"learning_rate": 7.320524814881471e-06,
"loss": 0.926,
"step": 695
},
{
"epoch": 0.63,
"grad_norm": 1.4126909774748309,
"learning_rate": 7.1689207780876026e-06,
"loss": 0.9282,
"step": 700
},
{
"epoch": 0.64,
"grad_norm": 1.4661343172163777,
"learning_rate": 7.018020889533348e-06,
"loss": 0.9245,
"step": 705
},
{
"epoch": 0.64,
"grad_norm": 1.5393466522100154,
"learning_rate": 6.867862681157067e-06,
"loss": 0.9215,
"step": 710
},
{
"epoch": 0.65,
"grad_norm": 1.412508168571422,
"learning_rate": 6.718483500425868e-06,
"loss": 0.9247,
"step": 715
},
{
"epoch": 0.65,
"grad_norm": 1.4776147088210356,
"learning_rate": 6.569920501046474e-06,
"loss": 0.9219,
"step": 720
},
{
"epoch": 0.65,
"grad_norm": 1.3425578015608433,
"learning_rate": 6.42221063372436e-06,
"loss": 0.9258,
"step": 725
},
{
"epoch": 0.66,
"grad_norm": 1.4129522183319783,
"learning_rate": 6.275390636973315e-06,
"loss": 0.9192,
"step": 730
},
{
"epoch": 0.66,
"grad_norm": 1.4289303694831434,
"learning_rate": 6.129497027977829e-06,
"loss": 0.9189,
"step": 735
},
{
"epoch": 0.67,
"grad_norm": 1.3710954157535182,
"learning_rate": 5.9845660935105084e-06,
"loss": 0.9164,
"step": 740
},
{
"epoch": 0.67,
"grad_norm": 1.4387200450753754,
"learning_rate": 5.8406338809067874e-06,
"loss": 0.9369,
"step": 745
},
{
"epoch": 0.68,
"grad_norm": 1.4010474045719385,
"learning_rate": 5.69773618909923e-06,
"loss": 0.9244,
"step": 750
},
{
"epoch": 0.68,
"grad_norm": 1.409153799110607,
"learning_rate": 5.555908559713561e-06,
"loss": 0.9118,
"step": 755
},
{
"epoch": 0.69,
"grad_norm": 1.3657173927666795,
"learning_rate": 5.4151862682287624e-06,
"loss": 0.9142,
"step": 760
},
{
"epoch": 0.69,
"grad_norm": 1.3963533437536293,
"learning_rate": 5.2756043152032934e-06,
"loss": 0.9176,
"step": 765
},
{
"epoch": 0.7,
"grad_norm": 1.3216489386400923,
"learning_rate": 5.137197417569739e-06,
"loss": 0.908,
"step": 770
},
{
"epoch": 0.7,
"grad_norm": 1.4412475309656017,
"learning_rate": 5.000000000000003e-06,
"loss": 0.9165,
"step": 775
},
{
"epoch": 0.7,
"grad_norm": 1.4134533602820125,
"learning_rate": 4.86404618634314e-06,
"loss": 0.9279,
"step": 780
},
{
"epoch": 0.71,
"grad_norm": 1.3837626714460547,
"learning_rate": 4.729369791138085e-06,
"loss": 0.9189,
"step": 785
},
{
"epoch": 0.71,
"grad_norm": 1.397147185881214,
"learning_rate": 4.596004311203243e-06,
"loss": 0.9421,
"step": 790
},
{
"epoch": 0.72,
"grad_norm": 1.3486469288795642,
"learning_rate": 4.463982917305155e-06,
"loss": 0.9156,
"step": 795
},
{
"epoch": 0.72,
"grad_norm": 1.3475341827233354,
"learning_rate": 4.333338445908225e-06,
"loss": 0.9292,
"step": 800
},
{
"epoch": 0.73,
"grad_norm": 1.3536202190201114,
"learning_rate": 4.2041033910076235e-06,
"loss": 0.8996,
"step": 805
},
{
"epoch": 0.73,
"grad_norm": 1.3534435686443709,
"learning_rate": 4.076309896047337e-06,
"loss": 0.9357,
"step": 810
},
{
"epoch": 0.74,
"grad_norm": 1.3961829341566565,
"learning_rate": 3.9499897459254375e-06,
"loss": 0.9233,
"step": 815
},
{
"epoch": 0.74,
"grad_norm": 1.348649115175699,
"learning_rate": 3.825174359088526e-06,
"loss": 0.9097,
"step": 820
},
{
"epoch": 0.75,
"grad_norm": 1.4476303062234663,
"learning_rate": 3.7018947797172864e-06,
"loss": 0.9274,
"step": 825
},
{
"epoch": 0.75,
"grad_norm": 1.390535701834856,
"learning_rate": 3.580181670005183e-06,
"loss": 0.9184,
"step": 830
},
{
"epoch": 0.75,
"grad_norm": 1.3785793159092763,
"learning_rate": 3.4600653025321085e-06,
"loss": 0.9055,
"step": 835
},
{
"epoch": 0.76,
"grad_norm": 1.354137886395205,
"learning_rate": 3.341575552734978e-06,
"loss": 0.9109,
"step": 840
},
{
"epoch": 0.76,
"grad_norm": 1.4067176317883785,
"learning_rate": 3.224741891477096e-06,
"loss": 0.9241,
"step": 845
},
{
"epoch": 0.77,
"grad_norm": 1.374060716621096,
"learning_rate": 3.1095933777181165e-06,
"loss": 0.9118,
"step": 850
},
{
"epoch": 0.77,
"grad_norm": 1.3942906283270295,
"learning_rate": 2.9961586512864947e-06,
"loss": 0.9,
"step": 855
},
{
"epoch": 0.78,
"grad_norm": 1.4465506221807978,
"learning_rate": 2.884465925756159e-06,
"loss": 0.9242,
"step": 860
},
{
"epoch": 0.78,
"grad_norm": 1.3396029078248526,
"learning_rate": 2.7745429814292147e-06,
"loss": 0.9241,
"step": 865
},
{
"epoch": 0.79,
"grad_norm": 1.3098914704831672,
"learning_rate": 2.666417158426393e-06,
"loss": 0.9228,
"step": 870
},
{
"epoch": 0.79,
"grad_norm": 1.434445807607541,
"learning_rate": 2.5601153498870137e-06,
"loss": 0.9191,
"step": 875
},
{
"epoch": 0.79,
"grad_norm": 1.3696234318588858,
"learning_rate": 2.4556639952800786e-06,
"loss": 0.9216,
"step": 880
},
{
"epoch": 0.8,
"grad_norm": 1.3799439546633658,
"learning_rate": 2.353089073828255e-06,
"loss": 0.9066,
"step": 885
},
{
"epoch": 0.8,
"grad_norm": 1.3783696426493683,
"learning_rate": 2.252416098046275e-06,
"loss": 0.9102,
"step": 890
},
{
"epoch": 0.81,
"grad_norm": 1.3692307220867967,
"learning_rate": 2.153670107395456e-06,
"loss": 0.8958,
"step": 895
},
{
"epoch": 0.81,
"grad_norm": 1.3494441419685654,
"learning_rate": 2.056875662055874e-06,
"loss": 0.9144,
"step": 900
},
{
"epoch": 0.82,
"grad_norm": 1.356794216227153,
"learning_rate": 1.9620568368177183e-06,
"loss": 0.8964,
"step": 905
},
{
"epoch": 0.82,
"grad_norm": 1.3429980043030805,
"learning_rate": 1.8692372150934113e-06,
"loss": 0.9194,
"step": 910
},
{
"epoch": 0.83,
"grad_norm": 1.339376480893687,
"learning_rate": 1.7784398830519002e-06,
"loss": 0.9093,
"step": 915
},
{
"epoch": 0.83,
"grad_norm": 1.3355920171762052,
"learning_rate": 1.6896874238766703e-06,
"loss": 0.8913,
"step": 920
},
{
"epoch": 0.84,
"grad_norm": 1.293120986101463,
"learning_rate": 1.6030019121488227e-06,
"loss": 0.9182,
"step": 925
},
{
"epoch": 0.84,
"grad_norm": 1.4443458217709528,
"learning_rate": 1.5184049083566688e-06,
"loss": 0.9123,
"step": 930
},
{
"epoch": 0.84,
"grad_norm": 1.3695869429477345,
"learning_rate": 1.4359174535331998e-06,
"loss": 0.9092,
"step": 935
},
{
"epoch": 0.85,
"grad_norm": 1.339902530091704,
"learning_rate": 1.3555600640227284e-06,
"loss": 0.9254,
"step": 940
},
{
"epoch": 0.85,
"grad_norm": 1.4388242190037084,
"learning_rate": 1.2773527263780626e-06,
"loss": 0.8972,
"step": 945
},
{
"epoch": 0.86,
"grad_norm": 1.430786276692823,
"learning_rate": 1.2013148923894213e-06,
"loss": 0.9197,
"step": 950
},
{
"epoch": 0.86,
"grad_norm": 1.3197356728810627,
"learning_rate": 1.1274654742463842e-06,
"loss": 0.897,
"step": 955
},
{
"epoch": 0.87,
"grad_norm": 1.3361601981054119,
"learning_rate": 1.0558228398340188e-06,
"loss": 0.9094,
"step": 960
},
{
"epoch": 0.87,
"grad_norm": 1.3263397846241956,
"learning_rate": 9.86404808164426e-07,
"loss": 0.8958,
"step": 965
},
{
"epoch": 0.88,
"grad_norm": 1.3279928456335177,
"learning_rate": 9.192286449447684e-07,
"loss": 0.8967,
"step": 970
},
{
"epoch": 0.88,
"grad_norm": 1.3258111261619026,
"learning_rate": 8.543110582829272e-07,
"loss": 0.9021,
"step": 975
},
{
"epoch": 0.89,
"grad_norm": 1.2957246118366699,
"learning_rate": 7.916681945318649e-07,
"loss": 0.9083,
"step": 980
},
{
"epoch": 0.89,
"grad_norm": 1.3406921495185697,
"learning_rate": 7.313156342736738e-07,
"loss": 0.898,
"step": 985
},
{
"epoch": 0.89,
"grad_norm": 1.3197731448045178,
"learning_rate": 6.732683884443736e-07,
"loss": 0.8957,
"step": 990
},
{
"epoch": 0.9,
"grad_norm": 1.3468993226799906,
"learning_rate": 6.175408946003703e-07,
"loss": 0.9035,
"step": 995
},
{
"epoch": 0.9,
"grad_norm": 1.3353098250857058,
"learning_rate": 5.641470133275473e-07,
"loss": 0.894,
"step": 1000
},
{
"epoch": 0.91,
"grad_norm": 1.3632991670701868,
"learning_rate": 5.131000247938367e-07,
"loss": 0.9149,
"step": 1005
},
{
"epoch": 0.91,
"grad_norm": 1.3014286387338503,
"learning_rate": 4.644126254461756e-07,
"loss": 0.8919,
"step": 1010
},
{
"epoch": 0.92,
"grad_norm": 1.3376939712764266,
"learning_rate": 4.180969248526334e-07,
"loss": 0.9151,
"step": 1015
},
{
"epoch": 0.92,
"grad_norm": 1.316358705323747,
"learning_rate": 3.7416444269050335e-07,
"loss": 0.9109,
"step": 1020
},
{
"epoch": 0.93,
"grad_norm": 1.351422091186982,
"learning_rate": 3.326261058811331e-07,
"loss": 0.9046,
"step": 1025
},
{
"epoch": 0.93,
"grad_norm": 1.3147060361947367,
"learning_rate": 2.9349224587215786e-07,
"loss": 0.9036,
"step": 1030
},
{
"epoch": 0.93,
"grad_norm": 1.376354495442706,
"learning_rate": 2.5677259606786686e-07,
"loss": 0.9109,
"step": 1035
},
{
"epoch": 0.94,
"grad_norm": 1.318239765222968,
"learning_rate": 2.2247628940829214e-07,
"loss": 0.9011,
"step": 1040
},
{
"epoch": 0.94,
"grad_norm": 1.334098597139642,
"learning_rate": 1.9061185609766996e-07,
"loss": 0.9158,
"step": 1045
},
{
"epoch": 0.95,
"grad_norm": 1.311535708505789,
"learning_rate": 1.6118722148278586e-07,
"loss": 0.9069,
"step": 1050
},
{
"epoch": 0.95,
"grad_norm": 1.3399145129480423,
"learning_rate": 1.3420970408178912e-07,
"loss": 0.9108,
"step": 1055
},
{
"epoch": 0.96,
"grad_norm": 1.3369774366097849,
"learning_rate": 1.0968601376391996e-07,
"loss": 0.9022,
"step": 1060
},
{
"epoch": 0.96,
"grad_norm": 1.327397654041781,
"learning_rate": 8.762225008062675e-08,
"loss": 0.9063,
"step": 1065
},
{
"epoch": 0.97,
"grad_norm": 1.3398923885085607,
"learning_rate": 6.802390074847731e-08,
"loss": 0.92,
"step": 1070
},
{
"epoch": 0.97,
"grad_norm": 1.3031847902685991,
"learning_rate": 5.0895840284257424e-08,
"loss": 0.8971,
"step": 1075
},
{
"epoch": 0.98,
"grad_norm": 1.34860295723008,
"learning_rate": 3.6242328792567286e-08,
"loss": 0.9018,
"step": 1080
},
{
"epoch": 0.98,
"grad_norm": 1.314620543755103,
"learning_rate": 2.406701090625463e-08,
"loss": 0.8847,
"step": 1085
},
{
"epoch": 0.98,
"grad_norm": 1.315793020724077,
"learning_rate": 1.4372914879909882e-08,
"loss": 0.896,
"step": 1090
},
{
"epoch": 0.99,
"grad_norm": 1.3160311821089112,
"learning_rate": 7.162451836685291e-09,
"loss": 0.9092,
"step": 1095
},
{
"epoch": 0.99,
"grad_norm": 1.381770390973591,
"learning_rate": 2.4374151685913063e-09,
"loss": 0.9208,
"step": 1100
},
{
"epoch": 1.0,
"grad_norm": 1.3304085867307816,
"learning_rate": 1.989800904445005e-10,
"loss": 0.9189,
"step": 1105
},
{
"epoch": 1.0,
"eval_loss": 0.9156445264816284,
"eval_runtime": 344.7542,
"eval_samples_per_second": 45.482,
"eval_steps_per_second": 0.711,
"step": 1107
},
{
"epoch": 1.0,
"step": 1107,
"total_flos": 463566557675520.0,
"train_loss": 0.9518642601066596,
"train_runtime": 13070.0796,
"train_samples_per_second": 10.839,
"train_steps_per_second": 0.085
}
],
"logging_steps": 5,
"max_steps": 1107,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 463566557675520.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}