g2_X9h / trainer_state.json
tzchen07's picture
Upload folder using huggingface_hub
5876d55 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 747,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02009545340366742,
"grad_norm": 101.4629135131836,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.9256,
"step": 5
},
{
"epoch": 0.04019090680733484,
"grad_norm": 83.51904296875,
"learning_rate": 9.000000000000001e-07,
"loss": 2.7459,
"step": 10
},
{
"epoch": 0.06028636021100226,
"grad_norm": 25.10388946533203,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.637,
"step": 15
},
{
"epoch": 0.08038181361466969,
"grad_norm": 13.024300575256348,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.1459,
"step": 20
},
{
"epoch": 0.1004772670183371,
"grad_norm": 8.315956115722656,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.7456,
"step": 25
},
{
"epoch": 0.12057272042200452,
"grad_norm": 8.930346488952637,
"learning_rate": 2.9e-06,
"loss": 0.5717,
"step": 30
},
{
"epoch": 0.14066817382567195,
"grad_norm": 7.356456756591797,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.414,
"step": 35
},
{
"epoch": 0.16076362722933937,
"grad_norm": 5.648008346557617,
"learning_rate": 3.900000000000001e-06,
"loss": 0.2577,
"step": 40
},
{
"epoch": 0.1808590806330068,
"grad_norm": 6.329988956451416,
"learning_rate": 4.4e-06,
"loss": 0.2394,
"step": 45
},
{
"epoch": 0.2009545340366742,
"grad_norm": 5.1738080978393555,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.1848,
"step": 50
},
{
"epoch": 0.22104998744034163,
"grad_norm": 4.86478853225708,
"learning_rate": 4.999016565957633e-06,
"loss": 0.2195,
"step": 55
},
{
"epoch": 0.24114544084400905,
"grad_norm": 4.442976474761963,
"learning_rate": 4.995022691166621e-06,
"loss": 0.1582,
"step": 60
},
{
"epoch": 0.26124089424767644,
"grad_norm": 3.704345941543579,
"learning_rate": 4.987961816680493e-06,
"loss": 0.183,
"step": 65
},
{
"epoch": 0.2813363476513439,
"grad_norm": 3.772160768508911,
"learning_rate": 4.977842622059546e-06,
"loss": 0.164,
"step": 70
},
{
"epoch": 0.30143180105501133,
"grad_norm": 3.2532081604003906,
"learning_rate": 4.96467754629559e-06,
"loss": 0.1781,
"step": 75
},
{
"epoch": 0.32152725445867875,
"grad_norm": 2.893615484237671,
"learning_rate": 4.948482772521346e-06,
"loss": 0.1288,
"step": 80
},
{
"epoch": 0.34162270786234616,
"grad_norm": 4.654979705810547,
"learning_rate": 4.929278208117378e-06,
"loss": 0.1444,
"step": 85
},
{
"epoch": 0.3617181612660136,
"grad_norm": 2.8989882469177246,
"learning_rate": 4.907087460240999e-06,
"loss": 0.1151,
"step": 90
},
{
"epoch": 0.381813614669681,
"grad_norm": 3.7547988891601562,
"learning_rate": 4.881937806807241e-06,
"loss": 0.1197,
"step": 95
},
{
"epoch": 0.4019090680733484,
"grad_norm": 2.273831605911255,
"learning_rate": 4.8538601629575525e-06,
"loss": 0.0966,
"step": 100
},
{
"epoch": 0.42200452147701584,
"grad_norm": 2.4642996788024902,
"learning_rate": 4.822889043057446e-06,
"loss": 0.1088,
"step": 105
},
{
"epoch": 0.44209997488068326,
"grad_norm": 3.29301381111145,
"learning_rate": 4.789062518269812e-06,
"loss": 0.1163,
"step": 110
},
{
"epoch": 0.4621954282843507,
"grad_norm": 2.45603084564209,
"learning_rate": 4.752422169756048e-06,
"loss": 0.1151,
"step": 115
},
{
"epoch": 0.4822908816880181,
"grad_norm": 3.199894666671753,
"learning_rate": 4.713013037562531e-06,
"loss": 0.098,
"step": 120
},
{
"epoch": 0.5023863350916855,
"grad_norm": 1.7128061056137085,
"learning_rate": 4.670883565255264e-06,
"loss": 0.0968,
"step": 125
},
{
"epoch": 0.5224817884953529,
"grad_norm": 2.645235776901245,
"learning_rate": 4.6260855403707625e-06,
"loss": 0.1068,
"step": 130
},
{
"epoch": 0.5425772418990203,
"grad_norm": 2.3140530586242676,
"learning_rate": 4.578674030756364e-06,
"loss": 0.0914,
"step": 135
},
{
"epoch": 0.5626726953026878,
"grad_norm": 1.8588067293167114,
"learning_rate": 4.528707316878233e-06,
"loss": 0.0995,
"step": 140
},
{
"epoch": 0.5827681487063552,
"grad_norm": 1.9172967672348022,
"learning_rate": 4.476246820180259e-06,
"loss": 0.08,
"step": 145
},
{
"epoch": 0.6028636021100227,
"grad_norm": 2.9082584381103516,
"learning_rate": 4.421357027581921e-06,
"loss": 0.1066,
"step": 150
},
{
"epoch": 0.62295905551369,
"grad_norm": 3.6944031715393066,
"learning_rate": 4.364105412207914e-06,
"loss": 0.1124,
"step": 155
},
{
"epoch": 0.6430545089173575,
"grad_norm": 1.5622600317001343,
"learning_rate": 4.304562350447008e-06,
"loss": 0.0856,
"step": 160
},
{
"epoch": 0.6631499623210249,
"grad_norm": 2.388239860534668,
"learning_rate": 4.242801035442059e-06,
"loss": 0.0766,
"step": 165
},
{
"epoch": 0.6832454157246923,
"grad_norm": 1.7182718515396118,
"learning_rate": 4.178897387117547e-06,
"loss": 0.104,
"step": 170
},
{
"epoch": 0.7033408691283597,
"grad_norm": 2.2367119789123535,
"learning_rate": 4.11292995885522e-06,
"loss": 0.0737,
"step": 175
},
{
"epoch": 0.7234363225320272,
"grad_norm": 2.007200241088867,
"learning_rate": 4.044979840932567e-06,
"loss": 0.0893,
"step": 180
},
{
"epoch": 0.7435317759356945,
"grad_norm": 2.6910905838012695,
"learning_rate": 3.975130560842821e-06,
"loss": 0.0944,
"step": 185
},
{
"epoch": 0.763627229339362,
"grad_norm": 2.042320489883423,
"learning_rate": 3.9034679806190204e-06,
"loss": 0.0843,
"step": 190
},
{
"epoch": 0.7837226827430294,
"grad_norm": 2.700977087020874,
"learning_rate": 3.830080191288342e-06,
"loss": 0.0669,
"step": 195
},
{
"epoch": 0.8038181361466968,
"grad_norm": 3.0307390689849854,
"learning_rate": 3.755057404586455e-06,
"loss": 0.0955,
"step": 200
},
{
"epoch": 0.8239135895503642,
"grad_norm": 1.3993719816207886,
"learning_rate": 2.666666666666667e-07,
"loss": 0.099,
"step": 205
},
{
"epoch": 0.8440090429540317,
"grad_norm": 1.7611238956451416,
"learning_rate": 6.000000000000001e-07,
"loss": 0.0771,
"step": 210
},
{
"epoch": 0.864104496357699,
"grad_norm": 2.088745594024658,
"learning_rate": 9.333333333333334e-07,
"loss": 0.0911,
"step": 215
},
{
"epoch": 0.8841999497613665,
"grad_norm": 2.071209669113159,
"learning_rate": 1.2666666666666669e-06,
"loss": 0.0757,
"step": 220
},
{
"epoch": 0.9042954031650339,
"grad_norm": 2.046583414077759,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.0609,
"step": 225
},
{
"epoch": 0.9243908565687013,
"grad_norm": 2.160752534866333,
"learning_rate": 1.9333333333333336e-06,
"loss": 0.1033,
"step": 230
},
{
"epoch": 0.9444863099723687,
"grad_norm": 1.2902394533157349,
"learning_rate": 2.266666666666667e-06,
"loss": 0.0987,
"step": 235
},
{
"epoch": 0.9645817633760362,
"grad_norm": 2.7047502994537354,
"learning_rate": 2.6e-06,
"loss": 0.084,
"step": 240
},
{
"epoch": 0.9846772167797035,
"grad_norm": 1.3737807273864746,
"learning_rate": 2.9333333333333338e-06,
"loss": 0.0879,
"step": 245
},
{
"epoch": 1.0040190906807336,
"grad_norm": 1.6534603834152222,
"learning_rate": 3.266666666666667e-06,
"loss": 0.0933,
"step": 250
},
{
"epoch": 1.0241145440844008,
"grad_norm": 1.805727481842041,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0528,
"step": 255
},
{
"epoch": 1.0442099974880683,
"grad_norm": 1.864627480506897,
"learning_rate": 3.9333333333333335e-06,
"loss": 0.0678,
"step": 260
},
{
"epoch": 1.0643054508917358,
"grad_norm": 3.2414352893829346,
"learning_rate": 4.266666666666668e-06,
"loss": 0.0671,
"step": 265
},
{
"epoch": 1.0844009042954033,
"grad_norm": 2.1301753520965576,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0666,
"step": 270
},
{
"epoch": 1.1044963576990705,
"grad_norm": 1.5783054828643799,
"learning_rate": 4.933333333333334e-06,
"loss": 0.061,
"step": 275
},
{
"epoch": 1.124591811102738,
"grad_norm": 1.8704148530960083,
"learning_rate": 4.999562902281866e-06,
"loss": 0.067,
"step": 280
},
{
"epoch": 1.1446872645064055,
"grad_norm": 3.888225555419922,
"learning_rate": 4.997787454752217e-06,
"loss": 0.0629,
"step": 285
},
{
"epoch": 1.164782717910073,
"grad_norm": 3.0024731159210205,
"learning_rate": 4.994647308096509e-06,
"loss": 0.0734,
"step": 290
},
{
"epoch": 1.1848781713137402,
"grad_norm": 1.866017460823059,
"learning_rate": 4.99014417797529e-06,
"loss": 0.076,
"step": 295
},
{
"epoch": 1.2049736247174077,
"grad_norm": 2.368576765060425,
"learning_rate": 4.984280524733107e-06,
"loss": 0.0722,
"step": 300
},
{
"epoch": 1.2250690781210751,
"grad_norm": 1.0686993598937988,
"learning_rate": 4.97705955205426e-06,
"loss": 0.0564,
"step": 305
},
{
"epoch": 1.2451645315247426,
"grad_norm": 2.0142111778259277,
"learning_rate": 4.968485205212429e-06,
"loss": 0.069,
"step": 310
},
{
"epoch": 1.2652599849284099,
"grad_norm": 1.7636579275131226,
"learning_rate": 4.958562168915121e-06,
"loss": 0.0748,
"step": 315
},
{
"epoch": 1.2853554383320773,
"grad_norm": 2.050908327102661,
"learning_rate": 4.947295864744121e-06,
"loss": 0.0636,
"step": 320
},
{
"epoch": 1.3054508917357448,
"grad_norm": 2.618356227874756,
"learning_rate": 4.9346924481933345e-06,
"loss": 0.06,
"step": 325
},
{
"epoch": 1.3255463451394123,
"grad_norm": 2.7333900928497314,
"learning_rate": 4.920758805305654e-06,
"loss": 0.0714,
"step": 330
},
{
"epoch": 1.3456417985430797,
"grad_norm": 1.96294105052948,
"learning_rate": 4.905502548910681e-06,
"loss": 0.0599,
"step": 335
},
{
"epoch": 1.365737251946747,
"grad_norm": 1.5320404767990112,
"learning_rate": 4.8889320144653525e-06,
"loss": 0.0618,
"step": 340
},
{
"epoch": 1.3858327053504145,
"grad_norm": 1.1524103879928589,
"learning_rate": 4.871056255499758e-06,
"loss": 0.058,
"step": 345
},
{
"epoch": 1.405928158754082,
"grad_norm": 1.3121646642684937,
"learning_rate": 4.851885038670618e-06,
"loss": 0.0684,
"step": 350
},
{
"epoch": 1.4260236121577492,
"grad_norm": 6.67919397354126,
"learning_rate": 4.831428838425153e-06,
"loss": 0.0766,
"step": 355
},
{
"epoch": 1.4461190655614167,
"grad_norm": 1.1791391372680664,
"learning_rate": 4.809698831278217e-06,
"loss": 0.0705,
"step": 360
},
{
"epoch": 1.4662145189650841,
"grad_norm": 0.794983983039856,
"learning_rate": 4.7867068897058725e-06,
"loss": 0.0654,
"step": 365
},
{
"epoch": 1.4863099723687516,
"grad_norm": 1.4783415794372559,
"learning_rate": 4.7624655756587e-06,
"loss": 0.0644,
"step": 370
},
{
"epoch": 1.506405425772419,
"grad_norm": 2.592212200164795,
"learning_rate": 4.736988133698416e-06,
"loss": 0.0621,
"step": 375
},
{
"epoch": 1.5265008791760866,
"grad_norm": 16.9811954498291,
"learning_rate": 4.710288483761524e-06,
"loss": 0.0824,
"step": 380
},
{
"epoch": 1.5465963325797538,
"grad_norm": 1.3936235904693604,
"learning_rate": 4.682381213553986e-06,
"loss": 0.069,
"step": 385
},
{
"epoch": 1.5666917859834213,
"grad_norm": 1.3866426944732666,
"learning_rate": 4.653281570581023e-06,
"loss": 0.0612,
"step": 390
},
{
"epoch": 1.5867872393870885,
"grad_norm": 4.862287521362305,
"learning_rate": 4.623005453816447e-06,
"loss": 0.0592,
"step": 395
},
{
"epoch": 1.606882692790756,
"grad_norm": 1.4648241996765137,
"learning_rate": 4.59156940501605e-06,
"loss": 0.0656,
"step": 400
},
{
"epoch": 1.6269781461944235,
"grad_norm": 1.3857091665267944,
"learning_rate": 4.558990599679787e-06,
"loss": 0.053,
"step": 405
},
{
"epoch": 1.647073599598091,
"grad_norm": 1.5649819374084473,
"learning_rate": 4.525286837667726e-06,
"loss": 0.0679,
"step": 410
},
{
"epoch": 1.6671690530017584,
"grad_norm": 1.6404094696044922,
"learning_rate": 4.490476533474854e-06,
"loss": 0.0593,
"step": 415
},
{
"epoch": 1.687264506405426,
"grad_norm": 2.027069091796875,
"learning_rate": 4.454578706170075e-06,
"loss": 0.066,
"step": 420
},
{
"epoch": 1.7073599598090932,
"grad_norm": 1.5853019952774048,
"learning_rate": 4.4176129690048905e-06,
"loss": 0.0575,
"step": 425
},
{
"epoch": 1.7274554132127606,
"grad_norm": 1.673964262008667,
"learning_rate": 4.379599518697444e-06,
"loss": 0.0699,
"step": 430
},
{
"epoch": 1.747550866616428,
"grad_norm": 1.7655727863311768,
"learning_rate": 4.340559124397774e-06,
"loss": 0.0648,
"step": 435
},
{
"epoch": 1.7676463200200954,
"grad_norm": 1.7724250555038452,
"learning_rate": 4.300513116340317e-06,
"loss": 0.0649,
"step": 440
},
{
"epoch": 1.7877417734237628,
"grad_norm": 2.0756025314331055,
"learning_rate": 4.259483374189851e-06,
"loss": 0.0671,
"step": 445
},
{
"epoch": 1.8078372268274303,
"grad_norm": 1.371147871017456,
"learning_rate": 4.217492315087255e-06,
"loss": 0.0577,
"step": 450
},
{
"epoch": 1.8279326802310978,
"grad_norm": 1.650765061378479,
"learning_rate": 4.174562881401602e-06,
"loss": 0.0529,
"step": 455
},
{
"epoch": 1.8480281336347653,
"grad_norm": 1.710800290107727,
"learning_rate": 4.130718528195303e-06,
"loss": 0.0773,
"step": 460
},
{
"epoch": 1.8681235870384325,
"grad_norm": 1.3324027061462402,
"learning_rate": 4.085983210409114e-06,
"loss": 0.0489,
"step": 465
},
{
"epoch": 1.8882190404421,
"grad_norm": 1.2311439514160156,
"learning_rate": 4.040381369774045e-06,
"loss": 0.0626,
"step": 470
},
{
"epoch": 1.9083144938457672,
"grad_norm": 1.9271433353424072,
"learning_rate": 3.993937921457292e-06,
"loss": 0.0552,
"step": 475
},
{
"epoch": 1.9284099472494347,
"grad_norm": 1.261828899383545,
"learning_rate": 3.946678240449515e-06,
"loss": 0.0566,
"step": 480
},
{
"epoch": 1.9485054006531022,
"grad_norm": 0.6837953329086304,
"learning_rate": 3.898628147700869e-06,
"loss": 0.0536,
"step": 485
},
{
"epoch": 1.9686008540567697,
"grad_norm": 1.0735151767730713,
"learning_rate": 3.849813896013392e-06,
"loss": 0.05,
"step": 490
},
{
"epoch": 1.9886963074604371,
"grad_norm": 0.8213454484939575,
"learning_rate": 3.8002621556974367e-06,
"loss": 0.0586,
"step": 495
},
{
"epoch": 2.008038181361467,
"grad_norm": 0.6580628156661987,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.06,
"step": 500
},
{
"epoch": 2.028133634765134,
"grad_norm": 0.7195087671279907,
"learning_rate": 3.699054890312892e-06,
"loss": 0.045,
"step": 505
},
{
"epoch": 2.0482290881688017,
"grad_norm": 1.023980736732483,
"learning_rate": 3.6474546611688446e-06,
"loss": 0.0411,
"step": 510
},
{
"epoch": 2.068324541572469,
"grad_norm": 2.1551263332366943,
"learning_rate": 3.595227505033747e-06,
"loss": 0.0445,
"step": 515
},
{
"epoch": 2.0884199949761366,
"grad_norm": 1.0194848775863647,
"learning_rate": 3.542401956903321e-06,
"loss": 0.0435,
"step": 520
},
{
"epoch": 2.108515448379804,
"grad_norm": 1.3117692470550537,
"learning_rate": 3.4890068787126475e-06,
"loss": 0.0425,
"step": 525
},
{
"epoch": 2.1286109017834716,
"grad_norm": 1.0447578430175781,
"learning_rate": 3.4350714435670706e-06,
"loss": 0.0457,
"step": 530
},
{
"epoch": 2.148706355187139,
"grad_norm": 1.320180058479309,
"learning_rate": 3.3806251198030843e-06,
"loss": 0.0451,
"step": 535
},
{
"epoch": 2.1688018085908065,
"grad_norm": 1.2361814975738525,
"learning_rate": 3.3256976548879183e-06,
"loss": 0.0399,
"step": 540
},
{
"epoch": 2.188897261994474,
"grad_norm": 1.0395464897155762,
"learning_rate": 3.2703190591666174e-06,
"loss": 0.044,
"step": 545
},
{
"epoch": 2.208992715398141,
"grad_norm": 1.1011066436767578,
"learning_rate": 3.2145195894654947e-06,
"loss": 0.0475,
"step": 550
},
{
"epoch": 2.2290881688018085,
"grad_norm": 1.1726021766662598,
"learning_rate": 3.1583297325609117e-06,
"loss": 0.0388,
"step": 555
},
{
"epoch": 2.249183622205476,
"grad_norm": 0.5452726483345032,
"learning_rate": 3.1017801885224332e-06,
"loss": 0.0397,
"step": 560
},
{
"epoch": 2.2692790756091434,
"grad_norm": 0.5013831853866577,
"learning_rate": 3.0449018539394274e-06,
"loss": 0.0416,
"step": 565
},
{
"epoch": 2.289374529012811,
"grad_norm": 1.811000108718872,
"learning_rate": 2.9877258050403214e-06,
"loss": 0.0446,
"step": 570
},
{
"epoch": 2.3094699824164784,
"grad_norm": 0.47706952691078186,
"learning_rate": 2.93028328071368e-06,
"loss": 0.0401,
"step": 575
},
{
"epoch": 2.329565435820146,
"grad_norm": 0.6600978970527649,
"learning_rate": 2.872605665440436e-06,
"loss": 0.038,
"step": 580
},
{
"epoch": 2.349660889223813,
"grad_norm": 0.7098400592803955,
"learning_rate": 2.814724472146564e-06,
"loss": 0.0417,
"step": 585
},
{
"epoch": 2.3697563426274804,
"grad_norm": 1.493393063545227,
"learning_rate": 2.7566713249855715e-06,
"loss": 0.0454,
"step": 590
},
{
"epoch": 2.389851796031148,
"grad_norm": 1.273262619972229,
"learning_rate": 2.6984779420602324e-06,
"loss": 0.044,
"step": 595
},
{
"epoch": 2.4099472494348153,
"grad_norm": 0.6910083293914795,
"learning_rate": 2.6401761180929798e-06,
"loss": 0.0411,
"step": 600
},
{
"epoch": 2.430042702838483,
"grad_norm": 0.8312556743621826,
"learning_rate": 2.5817977070544408e-06,
"loss": 0.0417,
"step": 605
},
{
"epoch": 2.4501381562421503,
"grad_norm": 0.5327412486076355,
"learning_rate": 2.5233746047595984e-06,
"loss": 0.0466,
"step": 610
},
{
"epoch": 2.4702336096458177,
"grad_norm": 0.7914028167724609,
"learning_rate": 2.464938731441095e-06,
"loss": 0.044,
"step": 615
},
{
"epoch": 2.490329063049485,
"grad_norm": 0.6906220316886902,
"learning_rate": 2.4065220143091863e-06,
"loss": 0.0397,
"step": 620
},
{
"epoch": 2.5104245164531527,
"grad_norm": 0.6936028003692627,
"learning_rate": 2.348156370107897e-06,
"loss": 0.0435,
"step": 625
},
{
"epoch": 2.5305199698568197,
"grad_norm": 1.5331124067306519,
"learning_rate": 2.2898736876768816e-06,
"loss": 0.0425,
"step": 630
},
{
"epoch": 2.550615423260487,
"grad_norm": 1.3947535753250122,
"learning_rate": 2.231705810528534e-06,
"loss": 0.044,
"step": 635
},
{
"epoch": 2.5707108766641547,
"grad_norm": 0.6972404718399048,
"learning_rate": 2.173684519449872e-06,
"loss": 0.0409,
"step": 640
},
{
"epoch": 2.590806330067822,
"grad_norm": 0.8982294201850891,
"learning_rate": 2.1158415151386746e-06,
"loss": 0.0405,
"step": 645
},
{
"epoch": 2.6109017834714896,
"grad_norm": 0.7696537971496582,
"learning_rate": 2.0582084008834003e-06,
"loss": 0.0388,
"step": 650
},
{
"epoch": 2.630997236875157,
"grad_norm": 1.5828746557235718,
"learning_rate": 2.000816665296302e-06,
"loss": 0.0412,
"step": 655
},
{
"epoch": 2.6510926902788245,
"grad_norm": 0.7513744831085205,
"learning_rate": 1.9436976651092143e-06,
"loss": 0.0406,
"step": 660
},
{
"epoch": 2.6711881436824916,
"grad_norm": 1.0159986019134521,
"learning_rate": 1.8868826080413876e-06,
"loss": 0.0414,
"step": 665
},
{
"epoch": 2.6912835970861595,
"grad_norm": 1.909378170967102,
"learning_rate": 1.8304025357487427e-06,
"loss": 0.0405,
"step": 670
},
{
"epoch": 2.7113790504898265,
"grad_norm": 0.875823974609375,
"learning_rate": 1.7742883068638447e-06,
"loss": 0.0413,
"step": 675
},
{
"epoch": 2.731474503893494,
"grad_norm": 1.1646164655685425,
"learning_rate": 1.7185705801358892e-06,
"loss": 0.0431,
"step": 680
},
{
"epoch": 2.7515699572971615,
"grad_norm": 0.9963555335998535,
"learning_rate": 1.6632797976798887e-06,
"loss": 0.0481,
"step": 685
},
{
"epoch": 2.771665410700829,
"grad_norm": 1.4356679916381836,
"learning_rate": 1.6084461683442176e-06,
"loss": 0.0449,
"step": 690
},
{
"epoch": 2.7917608641044964,
"grad_norm": 1.0450688600540161,
"learning_rate": 1.5540996512056164e-06,
"loss": 0.0401,
"step": 695
},
{
"epoch": 2.811856317508164,
"grad_norm": 1.4896055459976196,
"learning_rate": 1.500269939200648e-06,
"loss": 0.036,
"step": 700
},
{
"epoch": 2.8319517709118314,
"grad_norm": 1.0106236934661865,
"learning_rate": 1.446986442902574e-06,
"loss": 0.0428,
"step": 705
},
{
"epoch": 2.8520472243154984,
"grad_norm": 1.2998173236846924,
"learning_rate": 1.3942782744524974e-06,
"loss": 0.0412,
"step": 710
},
{
"epoch": 2.8721426777191663,
"grad_norm": 0.6855912804603577,
"learning_rate": 1.342174231653564e-06,
"loss": 0.042,
"step": 715
},
{
"epoch": 2.8922381311228333,
"grad_norm": 0.4582258462905884,
"learning_rate": 1.2907027822369006e-06,
"loss": 0.0356,
"step": 720
},
{
"epoch": 2.912333584526501,
"grad_norm": 0.9219332337379456,
"learning_rate": 1.2398920483078939e-06,
"loss": 0.0359,
"step": 725
},
{
"epoch": 2.9324290379301683,
"grad_norm": 1.0564415454864502,
"learning_rate": 1.1897697909813058e-06,
"loss": 0.0406,
"step": 730
},
{
"epoch": 2.9525244913338358,
"grad_norm": 2.999720811843872,
"learning_rate": 1.140363395213629e-06,
"loss": 0.0397,
"step": 735
},
{
"epoch": 2.9726199447375032,
"grad_norm": 0.8473829030990601,
"learning_rate": 1.0916998548409449e-06,
"loss": 0.0363,
"step": 740
},
{
"epoch": 2.9927153981411707,
"grad_norm": 0.6004119515419006,
"learning_rate": 1.043805757830495e-06,
"loss": 0.0365,
"step": 745
},
{
"epoch": 3.0,
"step": 747,
"total_flos": 1.9266920499218227e+18,
"train_loss": 0.04098171001696682,
"train_runtime": 11305.9315,
"train_samples_per_second": 4.225,
"train_steps_per_second": 0.066
}
],
"logging_steps": 5,
"max_steps": 747,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.9266920499218227e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}