etuckerman's picture
Initial commit of fine-tuned model using the omi-health/medical-dialogue-to-soap-summary dataset
b72b816 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9993928354584092,
"eval_steps": 500,
"global_step": 823,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006071645415907711,
"grad_norm": 0.24457845688569232,
"learning_rate": 9.999089317673432e-05,
"loss": 1.5749,
"step": 5
},
{
"epoch": 0.012143290831815421,
"grad_norm": 0.26391371346280523,
"learning_rate": 9.996357602430646e-05,
"loss": 1.5727,
"step": 10
},
{
"epoch": 0.018214936247723135,
"grad_norm": 0.27050405369105746,
"learning_rate": 9.991805849361562e-05,
"loss": 1.4543,
"step": 15
},
{
"epoch": 0.024286581663630843,
"grad_norm": 0.39705249849447666,
"learning_rate": 9.985435716546608e-05,
"loss": 1.3521,
"step": 20
},
{
"epoch": 0.030358227079538554,
"grad_norm": 0.34482550859107886,
"learning_rate": 9.977249524452732e-05,
"loss": 1.2841,
"step": 25
},
{
"epoch": 0.03642987249544627,
"grad_norm": 0.38424241285585997,
"learning_rate": 9.96725025508812e-05,
"loss": 1.1925,
"step": 30
},
{
"epoch": 0.042501517911353974,
"grad_norm": 0.2991869711584357,
"learning_rate": 9.95544155091593e-05,
"loss": 1.1573,
"step": 35
},
{
"epoch": 0.048573163327261686,
"grad_norm": 0.29091768319491834,
"learning_rate": 9.941827713527434e-05,
"loss": 1.1386,
"step": 40
},
{
"epoch": 0.0546448087431694,
"grad_norm": 0.2701117441828494,
"learning_rate": 9.926413702075075e-05,
"loss": 1.0848,
"step": 45
},
{
"epoch": 0.06071645415907711,
"grad_norm": 0.2660514207123453,
"learning_rate": 9.909205131465979e-05,
"loss": 1.0918,
"step": 50
},
{
"epoch": 0.06678809957498483,
"grad_norm": 0.24936524134232213,
"learning_rate": 9.890208270316594e-05,
"loss": 1.1005,
"step": 55
},
{
"epoch": 0.07285974499089254,
"grad_norm": 0.2453116793576235,
"learning_rate": 9.869430038669202e-05,
"loss": 1.0775,
"step": 60
},
{
"epoch": 0.07893139040680024,
"grad_norm": 0.27766127791240464,
"learning_rate": 9.846878005471138e-05,
"loss": 1.0932,
"step": 65
},
{
"epoch": 0.08500303582270795,
"grad_norm": 0.2706580007666611,
"learning_rate": 9.82256038581763e-05,
"loss": 1.077,
"step": 70
},
{
"epoch": 0.09107468123861566,
"grad_norm": 0.2622352686116729,
"learning_rate": 9.796486037959252e-05,
"loss": 1.0645,
"step": 75
},
{
"epoch": 0.09714632665452337,
"grad_norm": 0.2915416298324084,
"learning_rate": 9.768664460075113e-05,
"loss": 1.0584,
"step": 80
},
{
"epoch": 0.10321797207043108,
"grad_norm": 0.28210266400278944,
"learning_rate": 9.739105786812924e-05,
"loss": 1.0043,
"step": 85
},
{
"epoch": 0.1092896174863388,
"grad_norm": 0.2834916737475469,
"learning_rate": 9.707820785597219e-05,
"loss": 1.0909,
"step": 90
},
{
"epoch": 0.1153612629022465,
"grad_norm": 0.28178909138002517,
"learning_rate": 9.674820852707076e-05,
"loss": 1.0605,
"step": 95
},
{
"epoch": 0.12143290831815422,
"grad_norm": 0.2899825819853286,
"learning_rate": 9.64011800912476e-05,
"loss": 0.9849,
"step": 100
},
{
"epoch": 0.12750455373406194,
"grad_norm": 0.26579632159231636,
"learning_rate": 9.603724896156805e-05,
"loss": 1.0159,
"step": 105
},
{
"epoch": 0.13357619914996965,
"grad_norm": 0.2905253394887582,
"learning_rate": 9.565654770829123e-05,
"loss": 1.0435,
"step": 110
},
{
"epoch": 0.13964784456587737,
"grad_norm": 0.2853787242613106,
"learning_rate": 9.52592150105784e-05,
"loss": 1.0113,
"step": 115
},
{
"epoch": 0.14571948998178508,
"grad_norm": 0.2908783611322731,
"learning_rate": 9.484539560597576e-05,
"loss": 1.0053,
"step": 120
},
{
"epoch": 0.15179113539769276,
"grad_norm": 0.2884438105008898,
"learning_rate": 9.441524023769058e-05,
"loss": 1.0028,
"step": 125
},
{
"epoch": 0.15786278081360047,
"grad_norm": 0.3429769385996274,
"learning_rate": 9.396890559967951e-05,
"loss": 1.0139,
"step": 130
},
{
"epoch": 0.16393442622950818,
"grad_norm": 0.3056010970713378,
"learning_rate": 9.350655427956918e-05,
"loss": 1.0315,
"step": 135
},
{
"epoch": 0.1700060716454159,
"grad_norm": 0.3048115308528829,
"learning_rate": 9.302835469942992e-05,
"loss": 1.0359,
"step": 140
},
{
"epoch": 0.1760777170613236,
"grad_norm": 0.30341692290041095,
"learning_rate": 9.253448105442422e-05,
"loss": 1.0297,
"step": 145
},
{
"epoch": 0.18214936247723132,
"grad_norm": 0.31063335948647086,
"learning_rate": 9.202511324935213e-05,
"loss": 1.03,
"step": 150
},
{
"epoch": 0.18822100789313903,
"grad_norm": 0.32897710252989215,
"learning_rate": 9.150043683311673e-05,
"loss": 1.0367,
"step": 155
},
{
"epoch": 0.19429265330904674,
"grad_norm": 0.28758174259282,
"learning_rate": 9.096064293113382e-05,
"loss": 1.0204,
"step": 160
},
{
"epoch": 0.20036429872495445,
"grad_norm": 0.3022100238885681,
"learning_rate": 9.040592817571001e-05,
"loss": 1.025,
"step": 165
},
{
"epoch": 0.20643594414086217,
"grad_norm": 0.31328298710681657,
"learning_rate": 8.983649463441493e-05,
"loss": 1.0103,
"step": 170
},
{
"epoch": 0.21250758955676988,
"grad_norm": 0.3056230604848522,
"learning_rate": 8.925254973647343e-05,
"loss": 1.0119,
"step": 175
},
{
"epoch": 0.2185792349726776,
"grad_norm": 0.2932278475986119,
"learning_rate": 8.865430619720483e-05,
"loss": 1.0125,
"step": 180
},
{
"epoch": 0.2246508803885853,
"grad_norm": 0.28707514291349817,
"learning_rate": 8.804198194053642e-05,
"loss": 0.9675,
"step": 185
},
{
"epoch": 0.230722525804493,
"grad_norm": 0.31551606190516496,
"learning_rate": 8.741580001961966e-05,
"loss": 0.9934,
"step": 190
},
{
"epoch": 0.23679417122040072,
"grad_norm": 0.3081186246259813,
"learning_rate": 8.677598853557797e-05,
"loss": 1.0446,
"step": 195
},
{
"epoch": 0.24286581663630843,
"grad_norm": 0.32635829071646627,
"learning_rate": 8.612278055441573e-05,
"loss": 0.9928,
"step": 200
},
{
"epoch": 0.24893746205221615,
"grad_norm": 0.3056664443473449,
"learning_rate": 8.54564140221185e-05,
"loss": 0.998,
"step": 205
},
{
"epoch": 0.2550091074681239,
"grad_norm": 0.31526198269540723,
"learning_rate": 8.477713167797591e-05,
"loss": 1.0053,
"step": 210
},
{
"epoch": 0.2610807528840316,
"grad_norm": 0.3222176583928717,
"learning_rate": 8.408518096615817e-05,
"loss": 1.0034,
"step": 215
},
{
"epoch": 0.2671523982999393,
"grad_norm": 0.3169713895071339,
"learning_rate": 8.338081394557892e-05,
"loss": 0.9812,
"step": 220
},
{
"epoch": 0.273224043715847,
"grad_norm": 0.32407653940571435,
"learning_rate": 8.2664287198077e-05,
"loss": 1.0051,
"step": 225
},
{
"epoch": 0.27929568913175473,
"grad_norm": 0.3295876290581108,
"learning_rate": 8.193586173495056e-05,
"loss": 0.9978,
"step": 230
},
{
"epoch": 0.28536733454766244,
"grad_norm": 0.3188765761682836,
"learning_rate": 8.119580290187783e-05,
"loss": 1.0001,
"step": 235
},
{
"epoch": 0.29143897996357016,
"grad_norm": 0.3387778443057323,
"learning_rate": 8.044438028225879e-05,
"loss": 1.0466,
"step": 240
},
{
"epoch": 0.2975106253794778,
"grad_norm": 0.32002789503741597,
"learning_rate": 7.968186759901315e-05,
"loss": 1.0313,
"step": 245
},
{
"epoch": 0.3035822707953855,
"grad_norm": 0.3216979529684869,
"learning_rate": 7.890854261487074e-05,
"loss": 0.9845,
"step": 250
},
{
"epoch": 0.30965391621129323,
"grad_norm": 0.3222228418533532,
"learning_rate": 7.812468703118985e-05,
"loss": 0.9985,
"step": 255
},
{
"epoch": 0.31572556162720095,
"grad_norm": 0.32349662017935793,
"learning_rate": 7.733058638534113e-05,
"loss": 0.9589,
"step": 260
},
{
"epoch": 0.32179720704310866,
"grad_norm": 0.31939553229363304,
"learning_rate": 7.652652994669406e-05,
"loss": 1.0175,
"step": 265
},
{
"epoch": 0.32786885245901637,
"grad_norm": 0.311734388011201,
"learning_rate": 7.571281061124394e-05,
"loss": 0.9874,
"step": 270
},
{
"epoch": 0.3339404978749241,
"grad_norm": 0.3322440364094201,
"learning_rate": 7.488972479491778e-05,
"loss": 1.001,
"step": 275
},
{
"epoch": 0.3400121432908318,
"grad_norm": 0.3293068128055922,
"learning_rate": 7.405757232559807e-05,
"loss": 0.9384,
"step": 280
},
{
"epoch": 0.3460837887067395,
"grad_norm": 0.34714958730180595,
"learning_rate": 7.321665633390355e-05,
"loss": 0.9812,
"step": 285
},
{
"epoch": 0.3521554341226472,
"grad_norm": 0.3341860479562958,
"learning_rate": 7.236728314276692e-05,
"loss": 1.0073,
"step": 290
},
{
"epoch": 0.3582270795385549,
"grad_norm": 0.3477899939169161,
"learning_rate": 7.150976215584967e-05,
"loss": 0.9846,
"step": 295
},
{
"epoch": 0.36429872495446264,
"grad_norm": 0.3435321427630364,
"learning_rate": 7.064440574483482e-05,
"loss": 0.961,
"step": 300
},
{
"epoch": 0.37037037037037035,
"grad_norm": 0.3571408920594794,
"learning_rate": 6.977152913563825e-05,
"loss": 0.9517,
"step": 305
},
{
"epoch": 0.37644201578627806,
"grad_norm": 0.3378465695868974,
"learning_rate": 6.889145029358046e-05,
"loss": 0.9717,
"step": 310
},
{
"epoch": 0.3825136612021858,
"grad_norm": 0.34744636886470215,
"learning_rate": 6.800448980756042e-05,
"loss": 1.0026,
"step": 315
},
{
"epoch": 0.3885853066180935,
"grad_norm": 0.3279610405694282,
"learning_rate": 6.711097077327372e-05,
"loss": 0.9726,
"step": 320
},
{
"epoch": 0.3946569520340012,
"grad_norm": 0.3417715632798864,
"learning_rate": 6.621121867551759e-05,
"loss": 0.9958,
"step": 325
},
{
"epoch": 0.4007285974499089,
"grad_norm": 0.33073846039850685,
"learning_rate": 6.530556126962545e-05,
"loss": 0.9771,
"step": 330
},
{
"epoch": 0.4068002428658166,
"grad_norm": 0.37065478796323925,
"learning_rate": 6.439432846207475e-05,
"loss": 0.9954,
"step": 335
},
{
"epoch": 0.41287188828172433,
"grad_norm": 0.35459118756191277,
"learning_rate": 6.347785219031077e-05,
"loss": 0.9812,
"step": 340
},
{
"epoch": 0.41894353369763204,
"grad_norm": 0.33241922586525224,
"learning_rate": 6.255646630183082e-05,
"loss": 0.9793,
"step": 345
},
{
"epoch": 0.42501517911353975,
"grad_norm": 0.3392477463965851,
"learning_rate": 6.163050643257282e-05,
"loss": 1.0413,
"step": 350
},
{
"epoch": 0.43108682452944747,
"grad_norm": 0.36159716352209215,
"learning_rate": 6.070030988465192e-05,
"loss": 0.9742,
"step": 355
},
{
"epoch": 0.4371584699453552,
"grad_norm": 0.36382042578767604,
"learning_rate": 5.976621550349072e-05,
"loss": 0.9664,
"step": 360
},
{
"epoch": 0.4432301153612629,
"grad_norm": 0.34643585549602424,
"learning_rate": 5.8828563554386954e-05,
"loss": 0.9871,
"step": 365
},
{
"epoch": 0.4493017607771706,
"grad_norm": 0.36541385782952596,
"learning_rate": 5.7887695598563975e-05,
"loss": 1.0445,
"step": 370
},
{
"epoch": 0.4553734061930783,
"grad_norm": 0.3621329521595355,
"learning_rate": 5.694395436874942e-05,
"loss": 0.9847,
"step": 375
},
{
"epoch": 0.461445051608986,
"grad_norm": 0.35444381061319274,
"learning_rate": 5.5997683644326804e-05,
"loss": 0.9952,
"step": 380
},
{
"epoch": 0.46751669702489373,
"grad_norm": 0.3393936558293067,
"learning_rate": 5.50492281261061e-05,
"loss": 1.0073,
"step": 385
},
{
"epoch": 0.47358834244080145,
"grad_norm": 0.35553712556373906,
"learning_rate": 5.40989333107585e-05,
"loss": 1.0,
"step": 390
},
{
"epoch": 0.47965998785670916,
"grad_norm": 0.3508589267110535,
"learning_rate": 5.314714536496135e-05,
"loss": 1.0051,
"step": 395
},
{
"epoch": 0.48573163327261687,
"grad_norm": 0.3688927085936352,
"learning_rate": 5.219421099929899e-05,
"loss": 1.028,
"step": 400
},
{
"epoch": 0.4918032786885246,
"grad_norm": 0.3478126659800513,
"learning_rate": 5.1240477341965485e-05,
"loss": 0.9681,
"step": 405
},
{
"epoch": 0.4978749241044323,
"grad_norm": 0.3403963388182524,
"learning_rate": 5.028629181231526e-05,
"loss": 0.9781,
"step": 410
},
{
"epoch": 0.50394656952034,
"grad_norm": 0.3706190417343179,
"learning_rate": 4.933200199430754e-05,
"loss": 0.9824,
"step": 415
},
{
"epoch": 0.5100182149362478,
"grad_norm": 0.3340345296512503,
"learning_rate": 4.837795550989101e-05,
"loss": 0.9414,
"step": 420
},
{
"epoch": 0.5160898603521554,
"grad_norm": 0.35075966838432565,
"learning_rate": 4.74244998923745e-05,
"loss": 1.0231,
"step": 425
},
{
"epoch": 0.5221615057680632,
"grad_norm": 0.3500843432014112,
"learning_rate": 4.647198245983005e-05,
"loss": 0.9868,
"step": 430
},
{
"epoch": 0.5282331511839709,
"grad_norm": 0.35747081745898696,
"learning_rate": 4.552075018857423e-05,
"loss": 0.9591,
"step": 435
},
{
"epoch": 0.5343047965998786,
"grad_norm": 0.3462424877362867,
"learning_rate": 4.457114958677424e-05,
"loss": 0.9705,
"step": 440
},
{
"epoch": 0.5403764420157863,
"grad_norm": 0.3329658938355871,
"learning_rate": 4.362352656822422e-05,
"loss": 0.9658,
"step": 445
},
{
"epoch": 0.546448087431694,
"grad_norm": 0.3465063916450208,
"learning_rate": 4.2678226326338246e-05,
"loss": 0.9821,
"step": 450
},
{
"epoch": 0.5525197328476017,
"grad_norm": 0.36950370087466716,
"learning_rate": 4.173559320840579e-05,
"loss": 0.975,
"step": 455
},
{
"epoch": 0.5585913782635095,
"grad_norm": 0.38755895845945404,
"learning_rate": 4.079597059015518e-05,
"loss": 0.9871,
"step": 460
},
{
"epoch": 0.5646630236794171,
"grad_norm": 0.36167893272457224,
"learning_rate": 3.9859700750671275e-05,
"loss": 0.9539,
"step": 465
},
{
"epoch": 0.5707346690953249,
"grad_norm": 0.3393106959735491,
"learning_rate": 3.892712474771237e-05,
"loss": 0.9642,
"step": 470
},
{
"epoch": 0.5768063145112325,
"grad_norm": 0.36327402527885383,
"learning_rate": 3.7998582293472084e-05,
"loss": 0.9541,
"step": 475
},
{
"epoch": 0.5828779599271403,
"grad_norm": 0.35803017903945483,
"learning_rate": 3.707441163083146e-05,
"loss": 0.9581,
"step": 480
},
{
"epoch": 0.588949605343048,
"grad_norm": 0.35636927377775207,
"learning_rate": 3.6154949410146136e-05,
"loss": 0.9915,
"step": 485
},
{
"epoch": 0.5950212507589556,
"grad_norm": 0.3478523328672183,
"learning_rate": 3.524053056661385e-05,
"loss": 0.9658,
"step": 490
},
{
"epoch": 0.6010928961748634,
"grad_norm": 0.3622729352136925,
"learning_rate": 3.4331488198266576e-05,
"loss": 0.9662,
"step": 495
},
{
"epoch": 0.607164541590771,
"grad_norm": 0.36926496729541863,
"learning_rate": 3.34281534446319e-05,
"loss": 0.9308,
"step": 500
},
{
"epoch": 0.6132361870066788,
"grad_norm": 0.3725805831457224,
"learning_rate": 3.253085536610786e-05,
"loss": 1.0059,
"step": 505
},
{
"epoch": 0.6193078324225865,
"grad_norm": 0.356438235198244,
"learning_rate": 3.163992082409515e-05,
"loss": 0.9844,
"step": 510
},
{
"epoch": 0.6253794778384942,
"grad_norm": 0.3674543124679783,
"learning_rate": 3.0755674361930385e-05,
"loss": 0.9734,
"step": 515
},
{
"epoch": 0.6314511232544019,
"grad_norm": 0.3667296471323237,
"learning_rate": 2.987843808666375e-05,
"loss": 0.945,
"step": 520
},
{
"epoch": 0.6375227686703097,
"grad_norm": 0.35853673283205795,
"learning_rate": 2.9008531551724095e-05,
"loss": 0.9305,
"step": 525
},
{
"epoch": 0.6435944140862173,
"grad_norm": 0.3612263024162725,
"learning_rate": 2.814627164051429e-05,
"loss": 0.9662,
"step": 530
},
{
"epoch": 0.6496660595021251,
"grad_norm": 0.36442156113628843,
"learning_rate": 2.729197245097908e-05,
"loss": 0.961,
"step": 535
},
{
"epoch": 0.6557377049180327,
"grad_norm": 0.37491981923510603,
"learning_rate": 2.6445945181187947e-05,
"loss": 0.9942,
"step": 540
},
{
"epoch": 0.6618093503339405,
"grad_norm": 0.37088299839099026,
"learning_rate": 2.5608498015973813e-05,
"loss": 0.9711,
"step": 545
},
{
"epoch": 0.6678809957498482,
"grad_norm": 0.36485018535725894,
"learning_rate": 2.4779936014669792e-05,
"loss": 0.9841,
"step": 550
},
{
"epoch": 0.6739526411657559,
"grad_norm": 0.37286440050209124,
"learning_rate": 2.396056099998435e-05,
"loss": 0.9781,
"step": 555
},
{
"epoch": 0.6800242865816636,
"grad_norm": 0.38374404754220387,
"learning_rate": 2.31506714480553e-05,
"loss": 0.9712,
"step": 560
},
{
"epoch": 0.6860959319975714,
"grad_norm": 0.34919826336650855,
"learning_rate": 2.2350562379723263e-05,
"loss": 0.9345,
"step": 565
},
{
"epoch": 0.692167577413479,
"grad_norm": 0.37159419535563243,
"learning_rate": 2.1560525253063358e-05,
"loss": 0.9537,
"step": 570
},
{
"epoch": 0.6982392228293868,
"grad_norm": 0.35402600110835986,
"learning_rate": 2.0780847857215006e-05,
"loss": 0.9961,
"step": 575
},
{
"epoch": 0.7043108682452944,
"grad_norm": 0.36907420983715,
"learning_rate": 2.001181420754819e-05,
"loss": 0.9739,
"step": 580
},
{
"epoch": 0.7103825136612022,
"grad_norm": 0.35691133344150777,
"learning_rate": 1.925370444220415e-05,
"loss": 0.961,
"step": 585
},
{
"epoch": 0.7164541590771099,
"grad_norm": 0.3654680752856991,
"learning_rate": 1.8506794720048902e-05,
"loss": 0.9554,
"step": 590
},
{
"epoch": 0.7225258044930176,
"grad_norm": 0.36670809620950345,
"learning_rate": 1.777135712007583e-05,
"loss": 0.9968,
"step": 595
},
{
"epoch": 0.7285974499089253,
"grad_norm": 0.37074108181866644,
"learning_rate": 1.704765954229476e-05,
"loss": 0.9916,
"step": 600
},
{
"epoch": 0.734669095324833,
"grad_norm": 0.3699841020680654,
"learning_rate": 1.6335965610143272e-05,
"loss": 0.9822,
"step": 605
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.34824224824135186,
"learning_rate": 1.5636534574455686e-05,
"loss": 0.9515,
"step": 610
},
{
"epoch": 0.7468123861566485,
"grad_norm": 0.35545971051734354,
"learning_rate": 1.4949621219025194e-05,
"loss": 0.979,
"step": 615
},
{
"epoch": 0.7528840315725561,
"grad_norm": 0.36939000283625245,
"learning_rate": 1.4275475767792845e-05,
"loss": 0.9447,
"step": 620
},
{
"epoch": 0.7589556769884639,
"grad_norm": 0.37722833600145106,
"learning_rate": 1.361434379369783e-05,
"loss": 0.9825,
"step": 625
},
{
"epoch": 0.7650273224043715,
"grad_norm": 0.3737568094142613,
"learning_rate": 1.2966466129221883e-05,
"loss": 0.9594,
"step": 630
},
{
"epoch": 0.7710989678202793,
"grad_norm": 0.38063677046968875,
"learning_rate": 1.2332078778660517e-05,
"loss": 0.9536,
"step": 635
},
{
"epoch": 0.777170613236187,
"grad_norm": 0.36470282230989215,
"learning_rate": 1.1711412832153101e-05,
"loss": 0.9604,
"step": 640
},
{
"epoch": 0.7832422586520947,
"grad_norm": 0.36050493110455295,
"learning_rate": 1.11046943815029e-05,
"loss": 0.9661,
"step": 645
},
{
"epoch": 0.7893139040680024,
"grad_norm": 0.36561374914578487,
"learning_rate": 1.0512144437817994e-05,
"loss": 0.981,
"step": 650
},
{
"epoch": 0.7953855494839102,
"grad_norm": 0.378396003181358,
"learning_rate": 9.933978851002913e-06,
"loss": 0.9655,
"step": 655
},
{
"epoch": 0.8014571948998178,
"grad_norm": 0.37891923107554043,
"learning_rate": 9.370408231130346e-06,
"loss": 0.9359,
"step": 660
},
{
"epoch": 0.8075288403157256,
"grad_norm": 0.3668948751622055,
"learning_rate": 8.821637871721621e-06,
"loss": 0.9567,
"step": 665
},
{
"epoch": 0.8136004857316332,
"grad_norm": 0.3908476341217553,
"learning_rate": 8.287867674963807e-06,
"loss": 0.9694,
"step": 670
},
{
"epoch": 0.819672131147541,
"grad_norm": 0.35662541569917056,
"learning_rate": 7.769292078890745e-06,
"loss": 0.9424,
"step": 675
},
{
"epoch": 0.8257437765634487,
"grad_norm": 0.3651570402984319,
"learning_rate": 7.266099986554576e-06,
"loss": 0.9955,
"step": 680
},
{
"epoch": 0.8318154219793564,
"grad_norm": 0.3661244231382078,
"learning_rate": 6.778474697213427e-06,
"loss": 0.9677,
"step": 685
},
{
"epoch": 0.8378870673952641,
"grad_norm": 0.36996265866155903,
"learning_rate": 6.306593839560521e-06,
"loss": 0.9487,
"step": 690
},
{
"epoch": 0.8439587128111719,
"grad_norm": 0.3621026556302149,
"learning_rate": 5.850629307018768e-06,
"loss": 0.9315,
"step": 695
},
{
"epoch": 0.8500303582270795,
"grad_norm": 0.362727406662448,
"learning_rate": 5.410747195124704e-06,
"loss": 0.9498,
"step": 700
},
{
"epoch": 0.8561020036429873,
"grad_norm": 0.370792614501865,
"learning_rate": 4.98710774102435e-06,
"loss": 0.9726,
"step": 705
},
{
"epoch": 0.8621736490588949,
"grad_norm": 0.3803856942579128,
"learning_rate": 4.5798652651031835e-06,
"loss": 1.007,
"step": 710
},
{
"epoch": 0.8682452944748027,
"grad_norm": 0.35999841674151944,
"learning_rate": 4.189168114771391e-06,
"loss": 0.9331,
"step": 715
},
{
"epoch": 0.8743169398907104,
"grad_norm": 0.3602664439468411,
"learning_rate": 3.815158610424896e-06,
"loss": 0.9597,
"step": 720
},
{
"epoch": 0.8803885853066181,
"grad_norm": 0.35149568085349064,
"learning_rate": 3.4579729936019655e-06,
"loss": 0.97,
"step": 725
},
{
"epoch": 0.8864602307225258,
"grad_norm": 0.3624842659189334,
"learning_rate": 3.1177413773539775e-06,
"loss": 0.9351,
"step": 730
},
{
"epoch": 0.8925318761384335,
"grad_norm": 0.36379142989482044,
"learning_rate": 2.7945876988488883e-06,
"loss": 0.9501,
"step": 735
},
{
"epoch": 0.8986035215543412,
"grad_norm": 0.37684310590658127,
"learning_rate": 2.488629674224213e-06,
"loss": 0.9701,
"step": 740
},
{
"epoch": 0.904675166970249,
"grad_norm": 0.3587826562170923,
"learning_rate": 2.199978755706228e-06,
"loss": 0.9387,
"step": 745
},
{
"epoch": 0.9107468123861566,
"grad_norm": 0.36521231530865467,
"learning_rate": 1.928740091010961e-06,
"loss": 0.9637,
"step": 750
},
{
"epoch": 0.9168184578020644,
"grad_norm": 0.35686456437969416,
"learning_rate": 1.6750124850416826e-06,
"loss": 0.9706,
"step": 755
},
{
"epoch": 0.922890103217972,
"grad_norm": 0.362462586295161,
"learning_rate": 1.4388883638970063e-06,
"loss": 0.9857,
"step": 760
},
{
"epoch": 0.9289617486338798,
"grad_norm": 0.37168300236487517,
"learning_rate": 1.220453741202543e-06,
"loss": 0.9939,
"step": 765
},
{
"epoch": 0.9350333940497875,
"grad_norm": 0.3892333517564668,
"learning_rate": 1.0197881867784365e-06,
"loss": 0.9534,
"step": 770
},
{
"epoch": 0.9411050394656952,
"grad_norm": 0.3800794703218157,
"learning_rate": 8.369647976542883e-07,
"loss": 0.9638,
"step": 775
},
{
"epoch": 0.9471766848816029,
"grad_norm": 0.37279762749246226,
"learning_rate": 6.720501714418237e-07,
"loss": 0.9872,
"step": 780
},
{
"epoch": 0.9532483302975107,
"grad_norm": 0.3678126186430571,
"learning_rate": 5.251043820752532e-07,
"loss": 0.9706,
"step": 785
},
{
"epoch": 0.9593199757134183,
"grad_norm": 0.36745295930354865,
"learning_rate": 3.9618095792790524e-07,
"loss": 0.9686,
"step": 790
},
{
"epoch": 0.9653916211293261,
"grad_norm": 0.3545247585982039,
"learning_rate": 2.853268623133232e-07,
"loss": 0.8937,
"step": 795
},
{
"epoch": 0.9714632665452337,
"grad_norm": 0.3562774345464157,
"learning_rate": 1.9258247637778392e-07,
"loss": 0.982,
"step": 800
},
{
"epoch": 0.9775349119611415,
"grad_norm": 0.3912418038591769,
"learning_rate": 1.179815843905585e-07,
"loss": 0.9705,
"step": 805
},
{
"epoch": 0.9836065573770492,
"grad_norm": 0.36095941098323664,
"learning_rate": 6.155136143718987e-08,
"loss": 0.9478,
"step": 810
},
{
"epoch": 0.9896782027929569,
"grad_norm": 0.39365635306638663,
"learning_rate": 2.3312363520378023e-08,
"loss": 0.9949,
"step": 815
},
{
"epoch": 0.9957498482088646,
"grad_norm": 0.36179997068618486,
"learning_rate": 3.2785200719476216e-09,
"loss": 0.9421,
"step": 820
},
{
"epoch": 0.9993928354584092,
"eval_loss": 1.1136568784713745,
"eval_runtime": 17.0161,
"eval_samples_per_second": 8.991,
"eval_steps_per_second": 2.292,
"step": 823
}
],
"logging_steps": 5,
"max_steps": 823,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 517472256000000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}