step_cot / checkpoint-3000 /trainer_state.json
salmannyu's picture
Upload folder using huggingface_hub
fa1352e verified
Raw
History Blame Contribute Delete
54.2 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.5236160487557135,
"eval_steps": 500,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005078720162519045,
"grad_norm": 8.11971664428711,
"learning_rate": 7.614213197969544e-08,
"loss": 0.755,
"step": 10
},
{
"epoch": 0.01015744032503809,
"grad_norm": 7.887208938598633,
"learning_rate": 1.607445008460237e-07,
"loss": 0.7436,
"step": 20
},
{
"epoch": 0.015236160487557136,
"grad_norm": 6.621643543243408,
"learning_rate": 2.4534686971235194e-07,
"loss": 0.7286,
"step": 30
},
{
"epoch": 0.02031488065007618,
"grad_norm": 5.338628768920898,
"learning_rate": 3.2994923857868026e-07,
"loss": 0.6637,
"step": 40
},
{
"epoch": 0.025393600812595226,
"grad_norm": 3.3166372776031494,
"learning_rate": 4.1455160744500853e-07,
"loss": 0.5849,
"step": 50
},
{
"epoch": 0.03047232097511427,
"grad_norm": 2.2426822185516357,
"learning_rate": 4.991539763113367e-07,
"loss": 0.5074,
"step": 60
},
{
"epoch": 0.03555104113763331,
"grad_norm": 1.4896293878555298,
"learning_rate": 5.83756345177665e-07,
"loss": 0.4381,
"step": 70
},
{
"epoch": 0.04062976130015236,
"grad_norm": 1.3547300100326538,
"learning_rate": 6.683587140439933e-07,
"loss": 0.3912,
"step": 80
},
{
"epoch": 0.0457084814626714,
"grad_norm": 1.2349778413772583,
"learning_rate": 7.529610829103214e-07,
"loss": 0.3717,
"step": 90
},
{
"epoch": 0.05078720162519045,
"grad_norm": 1.228826880455017,
"learning_rate": 8.375634517766498e-07,
"loss": 0.3763,
"step": 100
},
{
"epoch": 0.055865921787709494,
"grad_norm": 1.9437307119369507,
"learning_rate": 9.22165820642978e-07,
"loss": 0.3648,
"step": 110
},
{
"epoch": 0.06094464195022854,
"grad_norm": 1.1562706232070923,
"learning_rate": 1.0067681895093063e-06,
"loss": 0.3593,
"step": 120
},
{
"epoch": 0.06602336211274759,
"grad_norm": 1.2007368803024292,
"learning_rate": 1.0913705583756345e-06,
"loss": 0.3619,
"step": 130
},
{
"epoch": 0.07110208227526663,
"grad_norm": 1.1364222764968872,
"learning_rate": 1.1759729272419628e-06,
"loss": 0.3492,
"step": 140
},
{
"epoch": 0.07618080243778567,
"grad_norm": 1.2867300510406494,
"learning_rate": 1.2605752961082913e-06,
"loss": 0.359,
"step": 150
},
{
"epoch": 0.08125952260030472,
"grad_norm": 1.230358600616455,
"learning_rate": 1.3451776649746193e-06,
"loss": 0.3396,
"step": 160
},
{
"epoch": 0.08633824276282377,
"grad_norm": 1.1166342496871948,
"learning_rate": 1.4297800338409476e-06,
"loss": 0.3412,
"step": 170
},
{
"epoch": 0.0914169629253428,
"grad_norm": 1.1211029291152954,
"learning_rate": 1.5143824027072759e-06,
"loss": 0.3436,
"step": 180
},
{
"epoch": 0.09649568308786186,
"grad_norm": 1.0837715864181519,
"learning_rate": 1.5989847715736043e-06,
"loss": 0.3399,
"step": 190
},
{
"epoch": 0.1015744032503809,
"grad_norm": 1.1223688125610352,
"learning_rate": 1.6835871404399324e-06,
"loss": 0.3465,
"step": 200
},
{
"epoch": 0.10665312341289995,
"grad_norm": 1.1082217693328857,
"learning_rate": 1.7681895093062607e-06,
"loss": 0.3422,
"step": 210
},
{
"epoch": 0.11173184357541899,
"grad_norm": 1.1912903785705566,
"learning_rate": 1.852791878172589e-06,
"loss": 0.3336,
"step": 220
},
{
"epoch": 0.11681056373793804,
"grad_norm": 1.1215198040008545,
"learning_rate": 1.937394247038917e-06,
"loss": 0.3293,
"step": 230
},
{
"epoch": 0.12188928390045708,
"grad_norm": 1.1722122430801392,
"learning_rate": 2.0219966159052453e-06,
"loss": 0.3376,
"step": 240
},
{
"epoch": 0.12696800406297612,
"grad_norm": 1.1333527565002441,
"learning_rate": 2.1065989847715737e-06,
"loss": 0.342,
"step": 250
},
{
"epoch": 0.13204672422549518,
"grad_norm": 1.0237016677856445,
"learning_rate": 2.1912013536379022e-06,
"loss": 0.3322,
"step": 260
},
{
"epoch": 0.13712544438801422,
"grad_norm": 1.061033844947815,
"learning_rate": 2.2758037225042303e-06,
"loss": 0.3311,
"step": 270
},
{
"epoch": 0.14220416455053325,
"grad_norm": 1.1101399660110474,
"learning_rate": 2.3604060913705588e-06,
"loss": 0.3426,
"step": 280
},
{
"epoch": 0.14728288471305231,
"grad_norm": 1.1787445545196533,
"learning_rate": 2.445008460236887e-06,
"loss": 0.321,
"step": 290
},
{
"epoch": 0.15236160487557135,
"grad_norm": 1.0249688625335693,
"learning_rate": 2.5296108291032153e-06,
"loss": 0.328,
"step": 300
},
{
"epoch": 0.1574403250380904,
"grad_norm": 1.058312177658081,
"learning_rate": 2.6142131979695434e-06,
"loss": 0.3299,
"step": 310
},
{
"epoch": 0.16251904520060945,
"grad_norm": 1.0902348756790161,
"learning_rate": 2.698815566835872e-06,
"loss": 0.3192,
"step": 320
},
{
"epoch": 0.16759776536312848,
"grad_norm": 1.0917754173278809,
"learning_rate": 2.7834179357022e-06,
"loss": 0.3211,
"step": 330
},
{
"epoch": 0.17267648552564754,
"grad_norm": 1.0080076456069946,
"learning_rate": 2.8680203045685284e-06,
"loss": 0.3299,
"step": 340
},
{
"epoch": 0.17775520568816658,
"grad_norm": 1.2910374402999878,
"learning_rate": 2.952622673434856e-06,
"loss": 0.3286,
"step": 350
},
{
"epoch": 0.1828339258506856,
"grad_norm": 1.014559268951416,
"learning_rate": 3.0372250423011845e-06,
"loss": 0.3174,
"step": 360
},
{
"epoch": 0.18791264601320468,
"grad_norm": 1.0668742656707764,
"learning_rate": 3.121827411167513e-06,
"loss": 0.327,
"step": 370
},
{
"epoch": 0.1929913661757237,
"grad_norm": 1.0306109189987183,
"learning_rate": 3.206429780033841e-06,
"loss": 0.3266,
"step": 380
},
{
"epoch": 0.19807008633824277,
"grad_norm": 1.1934700012207031,
"learning_rate": 3.2910321489001695e-06,
"loss": 0.3288,
"step": 390
},
{
"epoch": 0.2031488065007618,
"grad_norm": 1.1355713605880737,
"learning_rate": 3.375634517766498e-06,
"loss": 0.3318,
"step": 400
},
{
"epoch": 0.20822752666328084,
"grad_norm": 1.0128185749053955,
"learning_rate": 3.460236886632826e-06,
"loss": 0.3153,
"step": 410
},
{
"epoch": 0.2133062468257999,
"grad_norm": 1.1666514873504639,
"learning_rate": 3.5448392554991545e-06,
"loss": 0.3249,
"step": 420
},
{
"epoch": 0.21838496698831894,
"grad_norm": 1.1061981916427612,
"learning_rate": 3.629441624365482e-06,
"loss": 0.3218,
"step": 430
},
{
"epoch": 0.22346368715083798,
"grad_norm": 1.1475132703781128,
"learning_rate": 3.7140439932318106e-06,
"loss": 0.3338,
"step": 440
},
{
"epoch": 0.22854240731335704,
"grad_norm": 1.1342549324035645,
"learning_rate": 3.798646362098139e-06,
"loss": 0.3251,
"step": 450
},
{
"epoch": 0.23362112747587607,
"grad_norm": 1.0099126100540161,
"learning_rate": 3.883248730964467e-06,
"loss": 0.3251,
"step": 460
},
{
"epoch": 0.23869984763839514,
"grad_norm": 1.112540602684021,
"learning_rate": 3.967851099830796e-06,
"loss": 0.3234,
"step": 470
},
{
"epoch": 0.24377856780091417,
"grad_norm": 1.0405648946762085,
"learning_rate": 4.052453468697124e-06,
"loss": 0.3255,
"step": 480
},
{
"epoch": 0.2488572879634332,
"grad_norm": 1.0701533555984497,
"learning_rate": 4.137055837563453e-06,
"loss": 0.3214,
"step": 490
},
{
"epoch": 0.25393600812595224,
"grad_norm": 1.2194687128067017,
"learning_rate": 4.22165820642978e-06,
"loss": 0.3221,
"step": 500
},
{
"epoch": 0.25393600812595224,
"eval_loss": 0.3276064395904541,
"eval_runtime": 121.7232,
"eval_samples_per_second": 41.077,
"eval_steps_per_second": 2.571,
"step": 500
},
{
"epoch": 0.25901472828847133,
"grad_norm": 1.0545361042022705,
"learning_rate": 4.306260575296109e-06,
"loss": 0.3102,
"step": 510
},
{
"epoch": 0.26409344845099036,
"grad_norm": 0.9262936115264893,
"learning_rate": 4.390862944162436e-06,
"loss": 0.3044,
"step": 520
},
{
"epoch": 0.2691721686135094,
"grad_norm": 1.0422135591506958,
"learning_rate": 4.475465313028765e-06,
"loss": 0.3178,
"step": 530
},
{
"epoch": 0.27425088877602843,
"grad_norm": 1.108899474143982,
"learning_rate": 4.560067681895093e-06,
"loss": 0.3224,
"step": 540
},
{
"epoch": 0.27932960893854747,
"grad_norm": 0.9598031044006348,
"learning_rate": 4.644670050761422e-06,
"loss": 0.3232,
"step": 550
},
{
"epoch": 0.2844083291010665,
"grad_norm": 1.0063800811767578,
"learning_rate": 4.72927241962775e-06,
"loss": 0.3224,
"step": 560
},
{
"epoch": 0.2894870492635856,
"grad_norm": 1.0170040130615234,
"learning_rate": 4.813874788494079e-06,
"loss": 0.3204,
"step": 570
},
{
"epoch": 0.29456576942610463,
"grad_norm": 1.1103383302688599,
"learning_rate": 4.898477157360406e-06,
"loss": 0.3249,
"step": 580
},
{
"epoch": 0.29964448958862366,
"grad_norm": 1.101906657218933,
"learning_rate": 4.983079526226735e-06,
"loss": 0.3185,
"step": 590
},
{
"epoch": 0.3047232097511427,
"grad_norm": 0.9216155409812927,
"learning_rate": 4.999972060477541e-06,
"loss": 0.3197,
"step": 600
},
{
"epoch": 0.30980192991366173,
"grad_norm": 1.0119545459747314,
"learning_rate": 4.999858557237848e-06,
"loss": 0.316,
"step": 610
},
{
"epoch": 0.3148806500761808,
"grad_norm": 0.9301111698150635,
"learning_rate": 4.999657748021748e-06,
"loss": 0.3256,
"step": 620
},
{
"epoch": 0.31995937023869986,
"grad_norm": 0.944416344165802,
"learning_rate": 4.999369639842375e-06,
"loss": 0.3253,
"step": 630
},
{
"epoch": 0.3250380904012189,
"grad_norm": 0.856289803981781,
"learning_rate": 4.998994242761724e-06,
"loss": 0.3142,
"step": 640
},
{
"epoch": 0.33011681056373793,
"grad_norm": 1.0146931409835815,
"learning_rate": 4.998531569890301e-06,
"loss": 0.3117,
"step": 650
},
{
"epoch": 0.33519553072625696,
"grad_norm": 0.859649121761322,
"learning_rate": 4.997981637386663e-06,
"loss": 0.3089,
"step": 660
},
{
"epoch": 0.34027425088877605,
"grad_norm": 0.9393402338027954,
"learning_rate": 4.997344464456854e-06,
"loss": 0.3121,
"step": 670
},
{
"epoch": 0.3453529710512951,
"grad_norm": 0.9901228547096252,
"learning_rate": 4.9966200733537345e-06,
"loss": 0.3268,
"step": 680
},
{
"epoch": 0.3504316912138141,
"grad_norm": 0.9233267307281494,
"learning_rate": 4.995808489376206e-06,
"loss": 0.3214,
"step": 690
},
{
"epoch": 0.35551041137633316,
"grad_norm": 0.8530528545379639,
"learning_rate": 4.9949097408683235e-06,
"loss": 0.3148,
"step": 700
},
{
"epoch": 0.3605891315388522,
"grad_norm": 0.9197198748588562,
"learning_rate": 4.99392385921831e-06,
"loss": 0.3108,
"step": 710
},
{
"epoch": 0.3656678517013712,
"grad_norm": 0.9738614559173584,
"learning_rate": 4.992850878857458e-06,
"loss": 0.3189,
"step": 720
},
{
"epoch": 0.3707465718638903,
"grad_norm": 0.9086189270019531,
"learning_rate": 4.991690837258926e-06,
"loss": 0.3157,
"step": 730
},
{
"epoch": 0.37582529202640935,
"grad_norm": 1.1314260959625244,
"learning_rate": 4.990443774936432e-06,
"loss": 0.3295,
"step": 740
},
{
"epoch": 0.3809040121889284,
"grad_norm": 0.9313626885414124,
"learning_rate": 4.989109735442838e-06,
"loss": 0.3223,
"step": 750
},
{
"epoch": 0.3859827323514474,
"grad_norm": 0.894349217414856,
"learning_rate": 4.987688765368628e-06,
"loss": 0.3068,
"step": 760
},
{
"epoch": 0.39106145251396646,
"grad_norm": 0.8493692874908447,
"learning_rate": 4.986180914340281e-06,
"loss": 0.3145,
"step": 770
},
{
"epoch": 0.39614017267648555,
"grad_norm": 0.935171365737915,
"learning_rate": 4.9845862350185405e-06,
"loss": 0.3155,
"step": 780
},
{
"epoch": 0.4012188928390046,
"grad_norm": 0.8560822010040283,
"learning_rate": 4.98290478309657e-06,
"loss": 0.3274,
"step": 790
},
{
"epoch": 0.4062976130015236,
"grad_norm": 0.867138147354126,
"learning_rate": 4.981136617298012e-06,
"loss": 0.314,
"step": 800
},
{
"epoch": 0.41137633316404265,
"grad_norm": 0.8818840384483337,
"learning_rate": 4.97928179937494e-06,
"loss": 0.3182,
"step": 810
},
{
"epoch": 0.4164550533265617,
"grad_norm": 0.9063979387283325,
"learning_rate": 4.977340394105692e-06,
"loss": 0.3152,
"step": 820
},
{
"epoch": 0.4215337734890808,
"grad_norm": 0.8890411257743835,
"learning_rate": 4.975312469292618e-06,
"loss": 0.3084,
"step": 830
},
{
"epoch": 0.4266124936515998,
"grad_norm": 0.8582976460456848,
"learning_rate": 4.973198095759708e-06,
"loss": 0.3054,
"step": 840
},
{
"epoch": 0.43169121381411885,
"grad_norm": 0.8314648270606995,
"learning_rate": 4.970997347350117e-06,
"loss": 0.3067,
"step": 850
},
{
"epoch": 0.4367699339766379,
"grad_norm": 0.9010292887687683,
"learning_rate": 4.96871030092359e-06,
"loss": 0.3112,
"step": 860
},
{
"epoch": 0.4418486541391569,
"grad_norm": 0.8275406956672668,
"learning_rate": 4.966337036353775e-06,
"loss": 0.3075,
"step": 870
},
{
"epoch": 0.44692737430167595,
"grad_norm": 1.2174943685531616,
"learning_rate": 4.963877636525431e-06,
"loss": 0.3166,
"step": 880
},
{
"epoch": 0.45200609446419504,
"grad_norm": 0.8684174418449402,
"learning_rate": 4.961332187331541e-06,
"loss": 0.3221,
"step": 890
},
{
"epoch": 0.4570848146267141,
"grad_norm": 0.864565372467041,
"learning_rate": 4.958700777670306e-06,
"loss": 0.3168,
"step": 900
},
{
"epoch": 0.4621635347892331,
"grad_norm": 0.8785614967346191,
"learning_rate": 4.955983499442039e-06,
"loss": 0.3168,
"step": 910
},
{
"epoch": 0.46724225495175215,
"grad_norm": 0.7927045226097107,
"learning_rate": 4.953180447545965e-06,
"loss": 0.3175,
"step": 920
},
{
"epoch": 0.4723209751142712,
"grad_norm": 0.9102469086647034,
"learning_rate": 4.950291719876891e-06,
"loss": 0.3217,
"step": 930
},
{
"epoch": 0.47739969527679027,
"grad_norm": 0.8130275011062622,
"learning_rate": 4.947317417321803e-06,
"loss": 0.2997,
"step": 940
},
{
"epoch": 0.4824784154393093,
"grad_norm": 0.8968609571456909,
"learning_rate": 4.944257643756333e-06,
"loss": 0.3148,
"step": 950
},
{
"epoch": 0.48755713560182834,
"grad_norm": 0.9034120440483093,
"learning_rate": 4.941112506041135e-06,
"loss": 0.3132,
"step": 960
},
{
"epoch": 0.4926358557643474,
"grad_norm": 0.8752701282501221,
"learning_rate": 4.93788211401815e-06,
"loss": 0.3141,
"step": 970
},
{
"epoch": 0.4977145759268664,
"grad_norm": 0.9108573794364929,
"learning_rate": 4.9345665805067735e-06,
"loss": 0.3175,
"step": 980
},
{
"epoch": 0.5027932960893855,
"grad_norm": 0.9702094197273254,
"learning_rate": 4.931166021299914e-06,
"loss": 0.3055,
"step": 990
},
{
"epoch": 0.5078720162519045,
"grad_norm": 0.9001919031143188,
"learning_rate": 4.927680555159946e-06,
"loss": 0.3095,
"step": 1000
},
{
"epoch": 0.5078720162519045,
"eval_loss": 0.3185386657714844,
"eval_runtime": 121.8144,
"eval_samples_per_second": 41.046,
"eval_steps_per_second": 2.569,
"step": 1000
},
{
"epoch": 0.5129507364144236,
"grad_norm": 0.9391583800315857,
"learning_rate": 4.924110303814567e-06,
"loss": 0.3165,
"step": 1010
},
{
"epoch": 0.5180294565769427,
"grad_norm": 0.8731343150138855,
"learning_rate": 4.920455391952543e-06,
"loss": 0.303,
"step": 1020
},
{
"epoch": 0.5231081767394616,
"grad_norm": 0.811320424079895,
"learning_rate": 4.916715947219356e-06,
"loss": 0.3015,
"step": 1030
},
{
"epoch": 0.5281868969019807,
"grad_norm": 0.9213032126426697,
"learning_rate": 4.912892100212744e-06,
"loss": 0.3054,
"step": 1040
},
{
"epoch": 0.5332656170644997,
"grad_norm": 0.8103631734848022,
"learning_rate": 4.908983984478141e-06,
"loss": 0.2985,
"step": 1050
},
{
"epoch": 0.5383443372270188,
"grad_norm": 0.8164056539535522,
"learning_rate": 4.9049917365040135e-06,
"loss": 0.3138,
"step": 1060
},
{
"epoch": 0.5434230573895379,
"grad_norm": 0.7794240713119507,
"learning_rate": 4.900915495717092e-06,
"loss": 0.3073,
"step": 1070
},
{
"epoch": 0.5485017775520569,
"grad_norm": 0.8127440810203552,
"learning_rate": 4.896755404477505e-06,
"loss": 0.3047,
"step": 1080
},
{
"epoch": 0.553580497714576,
"grad_norm": 0.8375741243362427,
"learning_rate": 4.892511608073804e-06,
"loss": 0.3178,
"step": 1090
},
{
"epoch": 0.5586592178770949,
"grad_norm": 0.836986243724823,
"learning_rate": 4.888184254717886e-06,
"loss": 0.314,
"step": 1100
},
{
"epoch": 0.563737938039614,
"grad_norm": 0.8443421125411987,
"learning_rate": 4.88377349553983e-06,
"loss": 0.3187,
"step": 1110
},
{
"epoch": 0.568816658202133,
"grad_norm": 0.8671994805335999,
"learning_rate": 4.879279484582603e-06,
"loss": 0.3152,
"step": 1120
},
{
"epoch": 0.5738953783646521,
"grad_norm": 0.7974778413772583,
"learning_rate": 4.874702378796694e-06,
"loss": 0.3064,
"step": 1130
},
{
"epoch": 0.5789740985271712,
"grad_norm": 0.8144264221191406,
"learning_rate": 4.870042338034618e-06,
"loss": 0.3083,
"step": 1140
},
{
"epoch": 0.5840528186896902,
"grad_norm": 0.8496512770652771,
"learning_rate": 4.8652995250453515e-06,
"loss": 0.3011,
"step": 1150
},
{
"epoch": 0.5891315388522093,
"grad_norm": 0.8523489832878113,
"learning_rate": 4.86047410546863e-06,
"loss": 0.3105,
"step": 1160
},
{
"epoch": 0.5942102590147282,
"grad_norm": 0.8697237968444824,
"learning_rate": 4.855566247829177e-06,
"loss": 0.3118,
"step": 1170
},
{
"epoch": 0.5992889791772473,
"grad_norm": 0.758233368396759,
"learning_rate": 4.85057612353081e-06,
"loss": 0.3057,
"step": 1180
},
{
"epoch": 0.6043676993397664,
"grad_norm": 1.0396537780761719,
"learning_rate": 4.845503906850461e-06,
"loss": 0.3081,
"step": 1190
},
{
"epoch": 0.6094464195022854,
"grad_norm": 0.8582219481468201,
"learning_rate": 4.840349774932081e-06,
"loss": 0.3101,
"step": 1200
},
{
"epoch": 0.6145251396648045,
"grad_norm": 0.8096279501914978,
"learning_rate": 4.835113907780464e-06,
"loss": 0.3162,
"step": 1210
},
{
"epoch": 0.6196038598273235,
"grad_norm": 0.7163273692131042,
"learning_rate": 4.829796488254954e-06,
"loss": 0.3104,
"step": 1220
},
{
"epoch": 0.6246825799898426,
"grad_norm": 0.8141240477561951,
"learning_rate": 4.824397702063058e-06,
"loss": 0.3225,
"step": 1230
},
{
"epoch": 0.6297613001523616,
"grad_norm": 0.7636848092079163,
"learning_rate": 4.8189177377539635e-06,
"loss": 0.3172,
"step": 1240
},
{
"epoch": 0.6348400203148806,
"grad_norm": 0.8381786942481995,
"learning_rate": 4.8133567867119525e-06,
"loss": 0.3091,
"step": 1250
},
{
"epoch": 0.6399187404773997,
"grad_norm": 0.7415141463279724,
"learning_rate": 4.8077150431497175e-06,
"loss": 0.3119,
"step": 1260
},
{
"epoch": 0.6449974606399187,
"grad_norm": 0.7708622813224792,
"learning_rate": 4.801992704101578e-06,
"loss": 0.3121,
"step": 1270
},
{
"epoch": 0.6500761808024378,
"grad_norm": 0.8236015439033508,
"learning_rate": 4.796189969416601e-06,
"loss": 0.3042,
"step": 1280
},
{
"epoch": 0.6551549009649569,
"grad_norm": 0.7215218544006348,
"learning_rate": 4.790307041751617e-06,
"loss": 0.3031,
"step": 1290
},
{
"epoch": 0.6602336211274759,
"grad_norm": 0.7796043753623962,
"learning_rate": 4.78434412656415e-06,
"loss": 0.305,
"step": 1300
},
{
"epoch": 0.665312341289995,
"grad_norm": 0.8012691140174866,
"learning_rate": 4.778301432105234e-06,
"loss": 0.3066,
"step": 1310
},
{
"epoch": 0.6703910614525139,
"grad_norm": 0.8139703273773193,
"learning_rate": 4.772179169412146e-06,
"loss": 0.3023,
"step": 1320
},
{
"epoch": 0.675469781615033,
"grad_norm": 0.7603716850280762,
"learning_rate": 4.765977552301031e-06,
"loss": 0.3093,
"step": 1330
},
{
"epoch": 0.6805485017775521,
"grad_norm": 0.8556414842605591,
"learning_rate": 4.759696797359438e-06,
"loss": 0.3084,
"step": 1340
},
{
"epoch": 0.6856272219400711,
"grad_norm": 0.7557649612426758,
"learning_rate": 4.753337123938754e-06,
"loss": 0.3057,
"step": 1350
},
{
"epoch": 0.6907059421025902,
"grad_norm": 0.6622769832611084,
"learning_rate": 4.746898754146545e-06,
"loss": 0.3034,
"step": 1360
},
{
"epoch": 0.6957846622651092,
"grad_norm": 0.8777470588684082,
"learning_rate": 4.740381912838797e-06,
"loss": 0.2972,
"step": 1370
},
{
"epoch": 0.7008633824276282,
"grad_norm": 0.9032386541366577,
"learning_rate": 4.733786827612064e-06,
"loss": 0.3075,
"step": 1380
},
{
"epoch": 0.7059421025901473,
"grad_norm": 0.7780275940895081,
"learning_rate": 4.72711372879552e-06,
"loss": 0.3057,
"step": 1390
},
{
"epoch": 0.7110208227526663,
"grad_norm": 0.8000150918960571,
"learning_rate": 4.720362849442912e-06,
"loss": 0.3118,
"step": 1400
},
{
"epoch": 0.7160995429151854,
"grad_norm": 0.7798091173171997,
"learning_rate": 4.713534425324426e-06,
"loss": 0.3049,
"step": 1410
},
{
"epoch": 0.7211782630777044,
"grad_norm": 0.7654507160186768,
"learning_rate": 4.706628694918448e-06,
"loss": 0.3107,
"step": 1420
},
{
"epoch": 0.7262569832402235,
"grad_norm": 0.846693217754364,
"learning_rate": 4.699645899403238e-06,
"loss": 0.3074,
"step": 1430
},
{
"epoch": 0.7313357034027425,
"grad_norm": 0.8081271648406982,
"learning_rate": 4.692586282648504e-06,
"loss": 0.3082,
"step": 1440
},
{
"epoch": 0.7364144235652615,
"grad_norm": 0.7759858965873718,
"learning_rate": 4.685450091206893e-06,
"loss": 0.3127,
"step": 1450
},
{
"epoch": 0.7414931437277806,
"grad_norm": 0.8160701990127563,
"learning_rate": 4.678237574305364e-06,
"loss": 0.3018,
"step": 1460
},
{
"epoch": 0.7465718638902996,
"grad_norm": 0.8192775845527649,
"learning_rate": 4.670948983836505e-06,
"loss": 0.3024,
"step": 1470
},
{
"epoch": 0.7516505840528187,
"grad_norm": 0.8106697797775269,
"learning_rate": 4.66358457434972e-06,
"loss": 0.3167,
"step": 1480
},
{
"epoch": 0.7567293042153377,
"grad_norm": 0.7517253160476685,
"learning_rate": 4.6561446030423435e-06,
"loss": 0.3064,
"step": 1490
},
{
"epoch": 0.7618080243778568,
"grad_norm": 0.7888948321342468,
"learning_rate": 4.648629329750662e-06,
"loss": 0.308,
"step": 1500
},
{
"epoch": 0.7618080243778568,
"eval_loss": 0.3137528896331787,
"eval_runtime": 121.613,
"eval_samples_per_second": 41.114,
"eval_steps_per_second": 2.574,
"step": 1500
},
{
"epoch": 0.7668867445403759,
"grad_norm": 0.7494853138923645,
"learning_rate": 4.641039016940832e-06,
"loss": 0.3086,
"step": 1510
},
{
"epoch": 0.7719654647028948,
"grad_norm": 0.7426589131355286,
"learning_rate": 4.6333739296997205e-06,
"loss": 0.3,
"step": 1520
},
{
"epoch": 0.7770441848654139,
"grad_norm": 0.7976534366607666,
"learning_rate": 4.625634335725644e-06,
"loss": 0.3134,
"step": 1530
},
{
"epoch": 0.7821229050279329,
"grad_norm": 0.8214184045791626,
"learning_rate": 4.617820505319018e-06,
"loss": 0.3076,
"step": 1540
},
{
"epoch": 0.787201625190452,
"grad_norm": 0.8541253209114075,
"learning_rate": 4.609932711372921e-06,
"loss": 0.3141,
"step": 1550
},
{
"epoch": 0.7922803453529711,
"grad_norm": 0.75464928150177,
"learning_rate": 4.601971229363558e-06,
"loss": 0.3053,
"step": 1560
},
{
"epoch": 0.7973590655154901,
"grad_norm": 0.8184385895729065,
"learning_rate": 4.593936337340645e-06,
"loss": 0.3123,
"step": 1570
},
{
"epoch": 0.8024377856780092,
"grad_norm": 0.7774415612220764,
"learning_rate": 4.5858283159176955e-06,
"loss": 0.2999,
"step": 1580
},
{
"epoch": 0.8075165058405281,
"grad_norm": 0.9587996602058411,
"learning_rate": 4.57764744826222e-06,
"loss": 0.3077,
"step": 1590
},
{
"epoch": 0.8125952260030472,
"grad_norm": 0.9347293972969055,
"learning_rate": 4.569394020085841e-06,
"loss": 0.3104,
"step": 1600
},
{
"epoch": 0.8176739461655663,
"grad_norm": 0.7690241932868958,
"learning_rate": 4.561068319634307e-06,
"loss": 0.2998,
"step": 1610
},
{
"epoch": 0.8227526663280853,
"grad_norm": 0.783155083656311,
"learning_rate": 4.552670637677432e-06,
"loss": 0.3011,
"step": 1620
},
{
"epoch": 0.8278313864906044,
"grad_norm": 0.8160974979400635,
"learning_rate": 4.544201267498939e-06,
"loss": 0.3042,
"step": 1630
},
{
"epoch": 0.8329101066531234,
"grad_norm": 0.9004737734794617,
"learning_rate": 4.535660504886215e-06,
"loss": 0.3079,
"step": 1640
},
{
"epoch": 0.8379888268156425,
"grad_norm": 0.7750893235206604,
"learning_rate": 4.527048648119986e-06,
"loss": 0.3002,
"step": 1650
},
{
"epoch": 0.8430675469781616,
"grad_norm": 0.7503623962402344,
"learning_rate": 4.5183659979638905e-06,
"loss": 0.3117,
"step": 1660
},
{
"epoch": 0.8481462671406805,
"grad_norm": 0.8173331618309021,
"learning_rate": 4.509612857653987e-06,
"loss": 0.3079,
"step": 1670
},
{
"epoch": 0.8532249873031996,
"grad_norm": 0.7421526312828064,
"learning_rate": 4.500789532888154e-06,
"loss": 0.2998,
"step": 1680
},
{
"epoch": 0.8583037074657186,
"grad_norm": 0.7622323632240295,
"learning_rate": 4.49189633181542e-06,
"loss": 0.3003,
"step": 1690
},
{
"epoch": 0.8633824276282377,
"grad_norm": 0.730026364326477,
"learning_rate": 4.482933565025198e-06,
"loss": 0.3118,
"step": 1700
},
{
"epoch": 0.8684611477907568,
"grad_norm": 0.7820921540260315,
"learning_rate": 4.47390154553644e-06,
"loss": 0.3056,
"step": 1710
},
{
"epoch": 0.8735398679532758,
"grad_norm": 0.8582718372344971,
"learning_rate": 4.4648005887867064e-06,
"loss": 0.2969,
"step": 1720
},
{
"epoch": 0.8786185881157949,
"grad_norm": 0.7791563272476196,
"learning_rate": 4.455631012621143e-06,
"loss": 0.3068,
"step": 1730
},
{
"epoch": 0.8836973082783138,
"grad_norm": 0.7581758499145508,
"learning_rate": 4.4463931372813914e-06,
"loss": 0.304,
"step": 1740
},
{
"epoch": 0.8887760284408329,
"grad_norm": 0.766441285610199,
"learning_rate": 4.4370872853943936e-06,
"loss": 0.298,
"step": 1750
},
{
"epoch": 0.8938547486033519,
"grad_norm": 0.7395172119140625,
"learning_rate": 4.427713781961132e-06,
"loss": 0.2996,
"step": 1760
},
{
"epoch": 0.898933468765871,
"grad_norm": 0.7233405709266663,
"learning_rate": 4.4182729543452765e-06,
"loss": 0.2929,
"step": 1770
},
{
"epoch": 0.9040121889283901,
"grad_norm": 0.7392520904541016,
"learning_rate": 4.408765132261749e-06,
"loss": 0.3088,
"step": 1780
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.7640084028244019,
"learning_rate": 4.399190647765213e-06,
"loss": 0.3059,
"step": 1790
},
{
"epoch": 0.9141696292534282,
"grad_norm": 0.7984718084335327,
"learning_rate": 4.389549835238473e-06,
"loss": 0.3088,
"step": 1800
},
{
"epoch": 0.9192483494159471,
"grad_norm": 0.7300999164581299,
"learning_rate": 4.379843031380801e-06,
"loss": 0.3025,
"step": 1810
},
{
"epoch": 0.9243270695784662,
"grad_norm": 0.7906836867332458,
"learning_rate": 4.370070575196172e-06,
"loss": 0.3056,
"step": 1820
},
{
"epoch": 0.9294057897409853,
"grad_norm": 0.7191804051399231,
"learning_rate": 4.360232807981426e-06,
"loss": 0.3001,
"step": 1830
},
{
"epoch": 0.9344845099035043,
"grad_norm": 0.7592332363128662,
"learning_rate": 4.350330073314351e-06,
"loss": 0.3101,
"step": 1840
},
{
"epoch": 0.9395632300660234,
"grad_norm": 0.8039364218711853,
"learning_rate": 4.340362717041682e-06,
"loss": 0.3055,
"step": 1850
},
{
"epoch": 0.9446419502285424,
"grad_norm": 0.7507144212722778,
"learning_rate": 4.3303310872670226e-06,
"loss": 0.3018,
"step": 1860
},
{
"epoch": 0.9497206703910615,
"grad_norm": 0.9044272303581238,
"learning_rate": 4.320235534338685e-06,
"loss": 0.2943,
"step": 1870
},
{
"epoch": 0.9547993905535805,
"grad_norm": 0.7523107528686523,
"learning_rate": 4.310076410837463e-06,
"loss": 0.3026,
"step": 1880
},
{
"epoch": 0.9598781107160995,
"grad_norm": 0.955448567867279,
"learning_rate": 4.299854071564307e-06,
"loss": 0.2926,
"step": 1890
},
{
"epoch": 0.9649568308786186,
"grad_norm": 0.7745742797851562,
"learning_rate": 4.289568873527941e-06,
"loss": 0.304,
"step": 1900
},
{
"epoch": 0.9700355510411376,
"grad_norm": 0.7563455104827881,
"learning_rate": 4.279221175932389e-06,
"loss": 0.297,
"step": 1910
},
{
"epoch": 0.9751142712036567,
"grad_norm": 0.8183065056800842,
"learning_rate": 4.268811340164436e-06,
"loss": 0.2986,
"step": 1920
},
{
"epoch": 0.9801929913661758,
"grad_norm": 0.7718958258628845,
"learning_rate": 4.258339729781e-06,
"loss": 0.2957,
"step": 1930
},
{
"epoch": 0.9852717115286947,
"grad_norm": 0.7502573728561401,
"learning_rate": 4.24780671049644e-06,
"loss": 0.3023,
"step": 1940
},
{
"epoch": 0.9903504316912138,
"grad_norm": 0.8469391465187073,
"learning_rate": 4.237212650169783e-06,
"loss": 0.3078,
"step": 1950
},
{
"epoch": 0.9954291518537328,
"grad_norm": 0.8061825633049011,
"learning_rate": 4.226557918791872e-06,
"loss": 0.3002,
"step": 1960
},
{
"epoch": 1.000507872016252,
"grad_norm": 0.7248758673667908,
"learning_rate": 4.215842888472452e-06,
"loss": 0.3125,
"step": 1970
},
{
"epoch": 1.005586592178771,
"grad_norm": 0.7721697092056274,
"learning_rate": 4.205067933427169e-06,
"loss": 0.2544,
"step": 1980
},
{
"epoch": 1.01066531234129,
"grad_norm": 0.7651776075363159,
"learning_rate": 4.194233429964501e-06,
"loss": 0.2535,
"step": 1990
},
{
"epoch": 1.015744032503809,
"grad_norm": 0.7415822148323059,
"learning_rate": 4.183339756472617e-06,
"loss": 0.2496,
"step": 2000
},
{
"epoch": 1.015744032503809,
"eval_loss": 0.31630080938339233,
"eval_runtime": 121.7314,
"eval_samples_per_second": 41.074,
"eval_steps_per_second": 2.571,
"step": 2000
},
{
"epoch": 1.020822752666328,
"grad_norm": 0.792204737663269,
"learning_rate": 4.172387293406164e-06,
"loss": 0.2465,
"step": 2010
},
{
"epoch": 1.0259014728288471,
"grad_norm": 0.7987692356109619,
"learning_rate": 4.161376423272974e-06,
"loss": 0.2479,
"step": 2020
},
{
"epoch": 1.0309801929913662,
"grad_norm": 0.7764890789985657,
"learning_rate": 4.150307530620714e-06,
"loss": 0.25,
"step": 2030
},
{
"epoch": 1.0360589131538853,
"grad_norm": 0.7811829447746277,
"learning_rate": 4.139181002023445e-06,
"loss": 0.2518,
"step": 2040
},
{
"epoch": 1.0411376333164042,
"grad_norm": 0.7891380190849304,
"learning_rate": 4.1279972260681286e-06,
"loss": 0.2521,
"step": 2050
},
{
"epoch": 1.0462163534789233,
"grad_norm": 0.831947922706604,
"learning_rate": 4.1167565933410575e-06,
"loss": 0.2529,
"step": 2060
},
{
"epoch": 1.0512950736414424,
"grad_norm": 0.8048622012138367,
"learning_rate": 4.105459496414207e-06,
"loss": 0.2508,
"step": 2070
},
{
"epoch": 1.0563737938039615,
"grad_norm": 0.7546584606170654,
"learning_rate": 4.094106329831531e-06,
"loss": 0.247,
"step": 2080
},
{
"epoch": 1.0614525139664805,
"grad_norm": 0.7589654922485352,
"learning_rate": 4.08269749009518e-06,
"loss": 0.2466,
"step": 2090
},
{
"epoch": 1.0665312341289994,
"grad_norm": 0.7780548334121704,
"learning_rate": 4.0712333756516535e-06,
"loss": 0.2482,
"step": 2100
},
{
"epoch": 1.0716099542915185,
"grad_norm": 0.8401651978492737,
"learning_rate": 4.059714386877886e-06,
"loss": 0.2578,
"step": 2110
},
{
"epoch": 1.0766886744540376,
"grad_norm": 0.7654274702072144,
"learning_rate": 4.048140926067262e-06,
"loss": 0.2568,
"step": 2120
},
{
"epoch": 1.0817673946165567,
"grad_norm": 0.8236129283905029,
"learning_rate": 4.036513397415571e-06,
"loss": 0.2496,
"step": 2130
},
{
"epoch": 1.0868461147790756,
"grad_norm": 0.8232077360153198,
"learning_rate": 4.024832207006883e-06,
"loss": 0.2489,
"step": 2140
},
{
"epoch": 1.0919248349415946,
"grad_norm": 0.7585301399230957,
"learning_rate": 4.013097762799372e-06,
"loss": 0.2503,
"step": 2150
},
{
"epoch": 1.0970035551041137,
"grad_norm": 0.7547110319137573,
"learning_rate": 4.001310474611069e-06,
"loss": 0.2489,
"step": 2160
},
{
"epoch": 1.1020822752666328,
"grad_norm": 0.8154515027999878,
"learning_rate": 3.989470754105546e-06,
"loss": 0.2516,
"step": 2170
},
{
"epoch": 1.107160995429152,
"grad_norm": 0.8041960000991821,
"learning_rate": 3.9775790147775425e-06,
"loss": 0.2455,
"step": 2180
},
{
"epoch": 1.112239715591671,
"grad_norm": 0.7653600573539734,
"learning_rate": 3.96563567193852e-06,
"loss": 0.2539,
"step": 2190
},
{
"epoch": 1.1173184357541899,
"grad_norm": 0.8358815312385559,
"learning_rate": 3.953641142702161e-06,
"loss": 0.2473,
"step": 2200
},
{
"epoch": 1.122397155916709,
"grad_norm": 0.8611774444580078,
"learning_rate": 3.941595845969799e-06,
"loss": 0.2522,
"step": 2210
},
{
"epoch": 1.127475876079228,
"grad_norm": 0.734160840511322,
"learning_rate": 3.929500202415793e-06,
"loss": 0.2469,
"step": 2220
},
{
"epoch": 1.1325545962417471,
"grad_norm": 0.7705450057983398,
"learning_rate": 3.917354634472831e-06,
"loss": 0.2475,
"step": 2230
},
{
"epoch": 1.137633316404266,
"grad_norm": 0.7762371897697449,
"learning_rate": 3.9051595663171795e-06,
"loss": 0.2519,
"step": 2240
},
{
"epoch": 1.142712036566785,
"grad_norm": 0.8073663115501404,
"learning_rate": 3.892915423853866e-06,
"loss": 0.2417,
"step": 2250
},
{
"epoch": 1.1477907567293042,
"grad_norm": 0.8323131203651428,
"learning_rate": 3.880622634701812e-06,
"loss": 0.2489,
"step": 2260
},
{
"epoch": 1.1528694768918233,
"grad_norm": 0.8708091974258423,
"learning_rate": 3.868281628178888e-06,
"loss": 0.2548,
"step": 2270
},
{
"epoch": 1.1579481970543424,
"grad_norm": 0.7699044346809387,
"learning_rate": 3.855892835286931e-06,
"loss": 0.2467,
"step": 2280
},
{
"epoch": 1.1630269172168615,
"grad_norm": 0.718021035194397,
"learning_rate": 3.843456688696683e-06,
"loss": 0.2486,
"step": 2290
},
{
"epoch": 1.1681056373793803,
"grad_norm": 0.7651357054710388,
"learning_rate": 3.830973622732686e-06,
"loss": 0.248,
"step": 2300
},
{
"epoch": 1.1731843575418994,
"grad_norm": 0.8027908802032471,
"learning_rate": 3.818444073358108e-06,
"loss": 0.2352,
"step": 2310
},
{
"epoch": 1.1782630777044185,
"grad_norm": 0.7923874855041504,
"learning_rate": 3.8058684781595277e-06,
"loss": 0.2434,
"step": 2320
},
{
"epoch": 1.1833417978669376,
"grad_norm": 0.8118336200714111,
"learning_rate": 3.793247276331636e-06,
"loss": 0.2488,
"step": 2330
},
{
"epoch": 1.1884205180294565,
"grad_norm": 0.7456130385398865,
"learning_rate": 3.780580908661915e-06,
"loss": 0.248,
"step": 2340
},
{
"epoch": 1.1934992381919756,
"grad_norm": 0.7925790548324585,
"learning_rate": 3.7678698175152286e-06,
"loss": 0.2529,
"step": 2350
},
{
"epoch": 1.1985779583544947,
"grad_norm": 0.7958409190177917,
"learning_rate": 3.7551144468183824e-06,
"loss": 0.2526,
"step": 2360
},
{
"epoch": 1.2036566785170137,
"grad_norm": 0.7938746809959412,
"learning_rate": 3.7423152420446185e-06,
"loss": 0.2478,
"step": 2370
},
{
"epoch": 1.2087353986795328,
"grad_norm": 0.8479053378105164,
"learning_rate": 3.729472650198054e-06,
"loss": 0.2434,
"step": 2380
},
{
"epoch": 1.213814118842052,
"grad_norm": 0.7347251176834106,
"learning_rate": 3.716587119798074e-06,
"loss": 0.2401,
"step": 2390
},
{
"epoch": 1.2188928390045708,
"grad_norm": 0.7714645266532898,
"learning_rate": 3.703659100863664e-06,
"loss": 0.2511,
"step": 2400
},
{
"epoch": 1.2239715591670899,
"grad_norm": 0.777991533279419,
"learning_rate": 3.690689044897695e-06,
"loss": 0.2509,
"step": 2410
},
{
"epoch": 1.229050279329609,
"grad_norm": 0.7387746572494507,
"learning_rate": 3.6776774048711558e-06,
"loss": 0.2466,
"step": 2420
},
{
"epoch": 1.234128999492128,
"grad_norm": 0.740714967250824,
"learning_rate": 3.66462463520733e-06,
"loss": 0.244,
"step": 2430
},
{
"epoch": 1.239207719654647,
"grad_norm": 0.7498502731323242,
"learning_rate": 3.6515311917659302e-06,
"loss": 0.2411,
"step": 2440
},
{
"epoch": 1.244286439817166,
"grad_norm": 0.7903018593788147,
"learning_rate": 3.6383975318271724e-06,
"loss": 0.2556,
"step": 2450
},
{
"epoch": 1.2493651599796851,
"grad_norm": 0.8446292281150818,
"learning_rate": 3.6252241140758103e-06,
"loss": 0.243,
"step": 2460
},
{
"epoch": 1.2544438801422042,
"grad_norm": 0.7503316402435303,
"learning_rate": 3.6120113985851134e-06,
"loss": 0.2522,
"step": 2470
},
{
"epoch": 1.2595226003047233,
"grad_norm": 0.7319806218147278,
"learning_rate": 3.5987598468007993e-06,
"loss": 0.2475,
"step": 2480
},
{
"epoch": 1.2646013204672424,
"grad_norm": 0.7854649424552917,
"learning_rate": 3.585469921524919e-06,
"loss": 0.2534,
"step": 2490
},
{
"epoch": 1.2696800406297613,
"grad_norm": 0.7887899279594421,
"learning_rate": 3.5721420868996943e-06,
"loss": 0.248,
"step": 2500
},
{
"epoch": 1.2696800406297613,
"eval_loss": 0.3149872124195099,
"eval_runtime": 121.8702,
"eval_samples_per_second": 41.027,
"eval_steps_per_second": 2.568,
"step": 2500
},
{
"epoch": 1.2747587607922803,
"grad_norm": 0.7797321677207947,
"learning_rate": 3.5587768083913037e-06,
"loss": 0.251,
"step": 2510
},
{
"epoch": 1.2798374809547994,
"grad_norm": 0.84684157371521,
"learning_rate": 3.545374552773635e-06,
"loss": 0.2514,
"step": 2520
},
{
"epoch": 1.2849162011173183,
"grad_norm": 0.8210347294807434,
"learning_rate": 3.5319357881119733e-06,
"loss": 0.2451,
"step": 2530
},
{
"epoch": 1.2899949212798374,
"grad_norm": 0.8470488786697388,
"learning_rate": 3.518460983746661e-06,
"loss": 0.248,
"step": 2540
},
{
"epoch": 1.2950736414423565,
"grad_norm": 0.7454930543899536,
"learning_rate": 3.5049506102767037e-06,
"loss": 0.2414,
"step": 2550
},
{
"epoch": 1.3001523616048756,
"grad_norm": 0.713578462600708,
"learning_rate": 3.4914051395433363e-06,
"loss": 0.2482,
"step": 2560
},
{
"epoch": 1.3052310817673947,
"grad_norm": 0.7766876816749573,
"learning_rate": 3.477825044613543e-06,
"loss": 0.2501,
"step": 2570
},
{
"epoch": 1.3103098019299138,
"grad_norm": 0.7383909821510315,
"learning_rate": 3.464210799763536e-06,
"loss": 0.247,
"step": 2580
},
{
"epoch": 1.3153885220924328,
"grad_norm": 0.7781063318252563,
"learning_rate": 3.450562880462191e-06,
"loss": 0.2479,
"step": 2590
},
{
"epoch": 1.3204672422549517,
"grad_norm": 0.7478165030479431,
"learning_rate": 3.436881763354444e-06,
"loss": 0.2502,
"step": 2600
},
{
"epoch": 1.3255459624174708,
"grad_norm": 0.7556635737419128,
"learning_rate": 3.4231679262446426e-06,
"loss": 0.2517,
"step": 2610
},
{
"epoch": 1.33062468257999,
"grad_norm": 0.7706420421600342,
"learning_rate": 3.4094218480798608e-06,
"loss": 0.2448,
"step": 2620
},
{
"epoch": 1.3357034027425088,
"grad_norm": 0.8588224053382874,
"learning_rate": 3.3956440089331687e-06,
"loss": 0.2431,
"step": 2630
},
{
"epoch": 1.3407821229050279,
"grad_norm": 0.7747892141342163,
"learning_rate": 3.3818348899868707e-06,
"loss": 0.2517,
"step": 2640
},
{
"epoch": 1.345860843067547,
"grad_norm": 0.8341949582099915,
"learning_rate": 3.3679949735156974e-06,
"loss": 0.2478,
"step": 2650
},
{
"epoch": 1.350939563230066,
"grad_norm": 0.7596986889839172,
"learning_rate": 3.354124742869965e-06,
"loss": 0.2451,
"step": 2660
},
{
"epoch": 1.3560182833925851,
"grad_norm": 0.8195773363113403,
"learning_rate": 3.3402246824586897e-06,
"loss": 0.2448,
"step": 2670
},
{
"epoch": 1.3610970035551042,
"grad_norm": 0.7367848753929138,
"learning_rate": 3.3262952777326775e-06,
"loss": 0.2503,
"step": 2680
},
{
"epoch": 1.366175723717623,
"grad_norm": 0.8999025821685791,
"learning_rate": 3.3123370151675615e-06,
"loss": 0.2537,
"step": 2690
},
{
"epoch": 1.3712544438801422,
"grad_norm": 0.7917847037315369,
"learning_rate": 3.2983503822468214e-06,
"loss": 0.2496,
"step": 2700
},
{
"epoch": 1.3763331640426613,
"grad_norm": 0.7561963200569153,
"learning_rate": 3.28433586744475e-06,
"loss": 0.2489,
"step": 2710
},
{
"epoch": 1.3814118842051804,
"grad_norm": 0.8509207963943481,
"learning_rate": 3.2702939602093988e-06,
"loss": 0.2448,
"step": 2720
},
{
"epoch": 1.3864906043676992,
"grad_norm": 0.8005545139312744,
"learning_rate": 3.2562251509454813e-06,
"loss": 0.2578,
"step": 2730
},
{
"epoch": 1.3915693245302183,
"grad_norm": 0.8283247351646423,
"learning_rate": 3.2421299309972485e-06,
"loss": 0.2489,
"step": 2740
},
{
"epoch": 1.3966480446927374,
"grad_norm": 0.7954180836677551,
"learning_rate": 3.2280087926313288e-06,
"loss": 0.248,
"step": 2750
},
{
"epoch": 1.4017267648552565,
"grad_norm": 0.8017697930335999,
"learning_rate": 3.2138622290195325e-06,
"loss": 0.2535,
"step": 2760
},
{
"epoch": 1.4068054850177756,
"grad_norm": 0.7989761829376221,
"learning_rate": 3.1996907342216318e-06,
"loss": 0.2434,
"step": 2770
},
{
"epoch": 1.4118842051802947,
"grad_norm": 0.8122096061706543,
"learning_rate": 3.1854948031681044e-06,
"loss": 0.2518,
"step": 2780
},
{
"epoch": 1.4169629253428135,
"grad_norm": 0.8307642936706543,
"learning_rate": 3.1712749316428487e-06,
"loss": 0.2433,
"step": 2790
},
{
"epoch": 1.4220416455053326,
"grad_norm": 0.7779731154441833,
"learning_rate": 3.157031616265871e-06,
"loss": 0.2543,
"step": 2800
},
{
"epoch": 1.4271203656678517,
"grad_norm": 0.7799838185310364,
"learning_rate": 3.1427653544759352e-06,
"loss": 0.247,
"step": 2810
},
{
"epoch": 1.4321990858303708,
"grad_norm": 0.7921550869941711,
"learning_rate": 3.1284766445131975e-06,
"loss": 0.2485,
"step": 2820
},
{
"epoch": 1.4372778059928897,
"grad_norm": 0.7986315488815308,
"learning_rate": 3.114165985401801e-06,
"loss": 0.2469,
"step": 2830
},
{
"epoch": 1.4423565261554088,
"grad_norm": 0.848434329032898,
"learning_rate": 3.09983387693245e-06,
"loss": 0.2492,
"step": 2840
},
{
"epoch": 1.4474352463179279,
"grad_norm": 0.7870414853096008,
"learning_rate": 3.085480819644951e-06,
"loss": 0.2417,
"step": 2850
},
{
"epoch": 1.452513966480447,
"grad_norm": 0.8498828411102295,
"learning_rate": 3.0711073148107395e-06,
"loss": 0.2533,
"step": 2860
},
{
"epoch": 1.457592686642966,
"grad_norm": 0.7977587580680847,
"learning_rate": 3.056713864415363e-06,
"loss": 0.2483,
"step": 2870
},
{
"epoch": 1.4626714068054851,
"grad_norm": 0.7781681418418884,
"learning_rate": 3.0423009711409614e-06,
"loss": 0.2502,
"step": 2880
},
{
"epoch": 1.467750126968004,
"grad_norm": 0.8061252236366272,
"learning_rate": 3.0278691383486992e-06,
"loss": 0.2491,
"step": 2890
},
{
"epoch": 1.472828847130523,
"grad_norm": 0.7913114428520203,
"learning_rate": 3.013418870061194e-06,
"loss": 0.2461,
"step": 2900
},
{
"epoch": 1.4779075672930422,
"grad_norm": 0.7775682806968689,
"learning_rate": 2.9989506709449123e-06,
"loss": 0.2498,
"step": 2910
},
{
"epoch": 1.4829862874555613,
"grad_norm": 0.77854323387146,
"learning_rate": 2.984465046292541e-06,
"loss": 0.2473,
"step": 2920
},
{
"epoch": 1.4880650076180801,
"grad_norm": 0.8510044813156128,
"learning_rate": 2.9699625020053457e-06,
"loss": 0.2443,
"step": 2930
},
{
"epoch": 1.4931437277805992,
"grad_norm": 0.823668897151947,
"learning_rate": 2.9554435445754976e-06,
"loss": 0.2386,
"step": 2940
},
{
"epoch": 1.4982224479431183,
"grad_norm": 0.7475908994674683,
"learning_rate": 2.9409086810683858e-06,
"loss": 0.2503,
"step": 2950
},
{
"epoch": 1.5033011681056374,
"grad_norm": 0.8057491183280945,
"learning_rate": 2.926358419104911e-06,
"loss": 0.2421,
"step": 2960
},
{
"epoch": 1.5083798882681565,
"grad_norm": 0.8842071890830994,
"learning_rate": 2.9117932668437542e-06,
"loss": 0.2515,
"step": 2970
},
{
"epoch": 1.5134586084306756,
"grad_norm": 0.7616868615150452,
"learning_rate": 2.8972137329636324e-06,
"loss": 0.2486,
"step": 2980
},
{
"epoch": 1.5185373285931947,
"grad_norm": 0.7204374074935913,
"learning_rate": 2.8826203266455276e-06,
"loss": 0.2406,
"step": 2990
},
{
"epoch": 1.5236160487557135,
"grad_norm": 0.801526665687561,
"learning_rate": 2.868013557554911e-06,
"loss": 0.2526,
"step": 3000
},
{
"epoch": 1.5236160487557135,
"eval_loss": 0.3125091791152954,
"eval_runtime": 121.6711,
"eval_samples_per_second": 41.094,
"eval_steps_per_second": 2.573,
"step": 3000
}
],
"logging_steps": 10,
"max_steps": 5907,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.5377622239977406e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}