gemma4-st1 / trainer_state.json
alwaysgood's picture
Upload final model from korean-financial-cpt-gemma4-st1
5c6d43a verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5803,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017234693437890474,
"grad_norm": 252.0,
"learning_rate": 1.549053356282272e-07,
"loss": 4.069989395141602,
"step": 10
},
{
"epoch": 0.003446938687578095,
"grad_norm": 242.0,
"learning_rate": 3.2702237521514633e-07,
"loss": 3.939067077636719,
"step": 20
},
{
"epoch": 0.005170408031367142,
"grad_norm": 268.0,
"learning_rate": 4.991394148020654e-07,
"loss": 3.982646942138672,
"step": 30
},
{
"epoch": 0.00689387737515619,
"grad_norm": 266.0,
"learning_rate": 6.712564543889846e-07,
"loss": 3.9836990356445314,
"step": 40
},
{
"epoch": 0.008617346718945236,
"grad_norm": 1600.0,
"learning_rate": 8.433734939759036e-07,
"loss": 3.9337554931640626,
"step": 50
},
{
"epoch": 0.010340816062734284,
"grad_norm": 247.0,
"learning_rate": 1.0154905335628228e-06,
"loss": 3.949005126953125,
"step": 60
},
{
"epoch": 0.012064285406523332,
"grad_norm": 1336.0,
"learning_rate": 1.187607573149742e-06,
"loss": 3.7827701568603516,
"step": 70
},
{
"epoch": 0.01378775475031238,
"grad_norm": 1640.0,
"learning_rate": 1.3597246127366612e-06,
"loss": 3.6136966705322267,
"step": 80
},
{
"epoch": 0.015511224094101427,
"grad_norm": 466.0,
"learning_rate": 1.5318416523235801e-06,
"loss": 3.3442989349365235,
"step": 90
},
{
"epoch": 0.017234693437890473,
"grad_norm": 125.5,
"learning_rate": 1.703958691910499e-06,
"loss": 3.1754783630371093,
"step": 100
},
{
"epoch": 0.01895816278167952,
"grad_norm": 161.0,
"learning_rate": 1.8760757314974185e-06,
"loss": 3.0345636367797852,
"step": 110
},
{
"epoch": 0.020681632125468568,
"grad_norm": 128.0,
"learning_rate": 2.0481927710843377e-06,
"loss": 2.904159736633301,
"step": 120
},
{
"epoch": 0.022405101469257616,
"grad_norm": 90.5,
"learning_rate": 2.2203098106712566e-06,
"loss": 2.7710594177246093,
"step": 130
},
{
"epoch": 0.024128570813046663,
"grad_norm": 144.0,
"learning_rate": 2.3924268502581756e-06,
"loss": 2.6466978073120115,
"step": 140
},
{
"epoch": 0.02585204015683571,
"grad_norm": 155.0,
"learning_rate": 2.5645438898450946e-06,
"loss": 2.5279001235961913,
"step": 150
},
{
"epoch": 0.02757550950062476,
"grad_norm": 37.75,
"learning_rate": 2.736660929432014e-06,
"loss": 2.46486759185791,
"step": 160
},
{
"epoch": 0.029298978844413806,
"grad_norm": 63.25,
"learning_rate": 2.9087779690189333e-06,
"loss": 2.371097946166992,
"step": 170
},
{
"epoch": 0.031022448188202854,
"grad_norm": 23.375,
"learning_rate": 3.080895008605852e-06,
"loss": 2.2781375885009765,
"step": 180
},
{
"epoch": 0.0327459175319919,
"grad_norm": 36.75,
"learning_rate": 3.2530120481927713e-06,
"loss": 2.2452520370483398,
"step": 190
},
{
"epoch": 0.034469386875780945,
"grad_norm": 46.0,
"learning_rate": 3.4251290877796906e-06,
"loss": 2.2093746185302736,
"step": 200
},
{
"epoch": 0.03619285621957,
"grad_norm": 36.75,
"learning_rate": 3.59724612736661e-06,
"loss": 2.234319877624512,
"step": 210
},
{
"epoch": 0.03791632556335904,
"grad_norm": 19.5,
"learning_rate": 3.7693631669535286e-06,
"loss": 2.2229013442993164,
"step": 220
},
{
"epoch": 0.03963979490714809,
"grad_norm": 39.75,
"learning_rate": 3.9414802065404475e-06,
"loss": 2.1696863174438477,
"step": 230
},
{
"epoch": 0.041363264250937136,
"grad_norm": 89.0,
"learning_rate": 4.113597246127367e-06,
"loss": 2.129756546020508,
"step": 240
},
{
"epoch": 0.04308673359472619,
"grad_norm": 16.125,
"learning_rate": 4.2857142857142855e-06,
"loss": 2.1558290481567384,
"step": 250
},
{
"epoch": 0.04481020293851523,
"grad_norm": 73.0,
"learning_rate": 4.457831325301205e-06,
"loss": 2.1444324493408202,
"step": 260
},
{
"epoch": 0.046533672282304275,
"grad_norm": 31.75,
"learning_rate": 4.629948364888124e-06,
"loss": 2.090166473388672,
"step": 270
},
{
"epoch": 0.048257141626093326,
"grad_norm": 57.25,
"learning_rate": 4.802065404475044e-06,
"loss": 2.111903953552246,
"step": 280
},
{
"epoch": 0.04998061096988237,
"grad_norm": 20.0,
"learning_rate": 4.974182444061962e-06,
"loss": 2.0885305404663086,
"step": 290
},
{
"epoch": 0.05170408031367142,
"grad_norm": 80.5,
"learning_rate": 5.146299483648882e-06,
"loss": 2.0660512924194334,
"step": 300
},
{
"epoch": 0.053427549657460466,
"grad_norm": 84.0,
"learning_rate": 5.318416523235801e-06,
"loss": 2.0948448181152344,
"step": 310
},
{
"epoch": 0.05515101900124952,
"grad_norm": 30.0,
"learning_rate": 5.4905335628227195e-06,
"loss": 2.0578670501708984,
"step": 320
},
{
"epoch": 0.05687448834503856,
"grad_norm": 14.0,
"learning_rate": 5.66265060240964e-06,
"loss": 2.0415544509887695,
"step": 330
},
{
"epoch": 0.05859795768882761,
"grad_norm": 37.25,
"learning_rate": 5.834767641996558e-06,
"loss": 2.058155822753906,
"step": 340
},
{
"epoch": 0.060321427032616656,
"grad_norm": 149.0,
"learning_rate": 6.006884681583477e-06,
"loss": 2.0764211654663085,
"step": 350
},
{
"epoch": 0.06204489637640571,
"grad_norm": 55.5,
"learning_rate": 6.179001721170397e-06,
"loss": 2.0607065200805663,
"step": 360
},
{
"epoch": 0.06376836572019476,
"grad_norm": 14.75,
"learning_rate": 6.3511187607573156e-06,
"loss": 1.9941295623779296,
"step": 370
},
{
"epoch": 0.0654918350639838,
"grad_norm": 9.6875,
"learning_rate": 6.523235800344234e-06,
"loss": 2.0088274002075197,
"step": 380
},
{
"epoch": 0.06721530440777285,
"grad_norm": 15.1875,
"learning_rate": 6.695352839931154e-06,
"loss": 2.0329540252685545,
"step": 390
},
{
"epoch": 0.06893877375156189,
"grad_norm": 22.5,
"learning_rate": 6.867469879518073e-06,
"loss": 1.9693401336669922,
"step": 400
},
{
"epoch": 0.07066224309535094,
"grad_norm": 133.0,
"learning_rate": 7.039586919104991e-06,
"loss": 1.9934684753417968,
"step": 410
},
{
"epoch": 0.07238571243914,
"grad_norm": 17.125,
"learning_rate": 7.211703958691912e-06,
"loss": 1.9895509719848632,
"step": 420
},
{
"epoch": 0.07410918178292904,
"grad_norm": 14.1875,
"learning_rate": 7.38382099827883e-06,
"loss": 1.9678184509277343,
"step": 430
},
{
"epoch": 0.07583265112671808,
"grad_norm": 22.25,
"learning_rate": 7.55593803786575e-06,
"loss": 1.9880996704101563,
"step": 440
},
{
"epoch": 0.07755612047050713,
"grad_norm": 12.5625,
"learning_rate": 7.728055077452669e-06,
"loss": 1.98846492767334,
"step": 450
},
{
"epoch": 0.07927958981429618,
"grad_norm": 13.875,
"learning_rate": 7.900172117039587e-06,
"loss": 1.9478538513183594,
"step": 460
},
{
"epoch": 0.08100305915808523,
"grad_norm": 10.375,
"learning_rate": 8.072289156626508e-06,
"loss": 1.9478981018066406,
"step": 470
},
{
"epoch": 0.08272652850187427,
"grad_norm": 46.5,
"learning_rate": 8.244406196213425e-06,
"loss": 1.984210205078125,
"step": 480
},
{
"epoch": 0.08444999784566332,
"grad_norm": 9.1875,
"learning_rate": 8.416523235800345e-06,
"loss": 1.9917068481445312,
"step": 490
},
{
"epoch": 0.08617346718945237,
"grad_norm": 99.5,
"learning_rate": 8.588640275387264e-06,
"loss": 1.939429473876953,
"step": 500
},
{
"epoch": 0.08617346718945237,
"eval_loss": 1.9641746282577515,
"eval_runtime": 194.9485,
"eval_samples_per_second": 24.294,
"eval_steps_per_second": 3.037,
"step": 500
},
{
"epoch": 0.08789693653324142,
"grad_norm": 28.0,
"learning_rate": 8.760757314974184e-06,
"loss": 1.9692066192626954,
"step": 510
},
{
"epoch": 0.08962040587703046,
"grad_norm": 11.5625,
"learning_rate": 8.932874354561101e-06,
"loss": 1.9270980834960938,
"step": 520
},
{
"epoch": 0.0913438752208195,
"grad_norm": 9.75,
"learning_rate": 9.104991394148022e-06,
"loss": 1.9370803833007812,
"step": 530
},
{
"epoch": 0.09306734456460855,
"grad_norm": 17.125,
"learning_rate": 9.27710843373494e-06,
"loss": 1.938580322265625,
"step": 540
},
{
"epoch": 0.09479081390839761,
"grad_norm": 21.25,
"learning_rate": 9.44922547332186e-06,
"loss": 1.948999786376953,
"step": 550
},
{
"epoch": 0.09651428325218665,
"grad_norm": 7.8125,
"learning_rate": 9.621342512908779e-06,
"loss": 1.9140813827514649,
"step": 560
},
{
"epoch": 0.0982377525959757,
"grad_norm": 6.28125,
"learning_rate": 9.793459552495698e-06,
"loss": 1.9098445892333984,
"step": 570
},
{
"epoch": 0.09996122193976474,
"grad_norm": 63.5,
"learning_rate": 9.965576592082618e-06,
"loss": 1.9676044464111329,
"step": 580
},
{
"epoch": 0.1016846912835538,
"grad_norm": 7.28125,
"learning_rate": 9.999942091121426e-06,
"loss": 1.9416418075561523,
"step": 590
},
{
"epoch": 0.10340816062734284,
"grad_norm": 14.9375,
"learning_rate": 9.999706838601156e-06,
"loss": 1.9148761749267578,
"step": 600
},
{
"epoch": 0.10513162997113189,
"grad_norm": 8.4375,
"learning_rate": 9.999290631642222e-06,
"loss": 1.9141145706176759,
"step": 610
},
{
"epoch": 0.10685509931492093,
"grad_norm": 8.5625,
"learning_rate": 9.99869348530841e-06,
"loss": 1.9634918212890624,
"step": 620
},
{
"epoch": 0.10857856865870999,
"grad_norm": 9.0625,
"learning_rate": 9.997915421212245e-06,
"loss": 1.8770341873168945,
"step": 630
},
{
"epoch": 0.11030203800249903,
"grad_norm": 8.0625,
"learning_rate": 9.996956467514203e-06,
"loss": 1.965164566040039,
"step": 640
},
{
"epoch": 0.11202550734628808,
"grad_norm": 11.9375,
"learning_rate": 9.99581665892171e-06,
"loss": 1.903609848022461,
"step": 650
},
{
"epoch": 0.11374897669007712,
"grad_norm": 9.0625,
"learning_rate": 9.994496036687866e-06,
"loss": 1.932215118408203,
"step": 660
},
{
"epoch": 0.11547244603386617,
"grad_norm": 10.0,
"learning_rate": 9.992994648609966e-06,
"loss": 1.9616926193237305,
"step": 670
},
{
"epoch": 0.11719591537765522,
"grad_norm": 5.8125,
"learning_rate": 9.991312549027762e-06,
"loss": 1.8867454528808594,
"step": 680
},
{
"epoch": 0.11891938472144427,
"grad_norm": 7.46875,
"learning_rate": 9.989449798821504e-06,
"loss": 1.9198978424072266,
"step": 690
},
{
"epoch": 0.12064285406523331,
"grad_norm": 9.0,
"learning_rate": 9.987406465409725e-06,
"loss": 1.9139331817626952,
"step": 700
},
{
"epoch": 0.12236632340902236,
"grad_norm": 23.625,
"learning_rate": 9.985182622746813e-06,
"loss": 1.9208333969116211,
"step": 710
},
{
"epoch": 0.12408979275281141,
"grad_norm": 6.21875,
"learning_rate": 9.982778351320329e-06,
"loss": 1.9320703506469727,
"step": 720
},
{
"epoch": 0.12581326209660046,
"grad_norm": 8.375,
"learning_rate": 9.980193738148087e-06,
"loss": 1.9007251739501954,
"step": 730
},
{
"epoch": 0.12753673144038952,
"grad_norm": 30.625,
"learning_rate": 9.977428876775022e-06,
"loss": 1.8702217102050782,
"step": 740
},
{
"epoch": 0.12926020078417855,
"grad_norm": 8.375,
"learning_rate": 9.974483867269787e-06,
"loss": 1.8927556991577148,
"step": 750
},
{
"epoch": 0.1309836701279676,
"grad_norm": 5.78125,
"learning_rate": 9.971358816221137e-06,
"loss": 1.9013349533081054,
"step": 760
},
{
"epoch": 0.13270713947175664,
"grad_norm": 7.46875,
"learning_rate": 9.96805383673408e-06,
"loss": 1.8408695220947267,
"step": 770
},
{
"epoch": 0.1344306088155457,
"grad_norm": 7.15625,
"learning_rate": 9.96456904842577e-06,
"loss": 1.869816207885742,
"step": 780
},
{
"epoch": 0.13615407815933475,
"grad_norm": 37.5,
"learning_rate": 9.960904577421182e-06,
"loss": 1.8965574264526368,
"step": 790
},
{
"epoch": 0.13787754750312378,
"grad_norm": 6.21875,
"learning_rate": 9.957060556348554e-06,
"loss": 1.9223035812377929,
"step": 800
},
{
"epoch": 0.13960101684691284,
"grad_norm": 6.1875,
"learning_rate": 9.953037124334576e-06,
"loss": 1.8931386947631836,
"step": 810
},
{
"epoch": 0.14132448619070187,
"grad_norm": 18.75,
"learning_rate": 9.948834426999363e-06,
"loss": 1.8595243453979493,
"step": 820
},
{
"epoch": 0.14304795553449093,
"grad_norm": 6.84375,
"learning_rate": 9.944452616451182e-06,
"loss": 1.859971046447754,
"step": 830
},
{
"epoch": 0.14477142487828,
"grad_norm": 6.59375,
"learning_rate": 9.939891851280943e-06,
"loss": 1.9094179153442383,
"step": 840
},
{
"epoch": 0.14649489422206902,
"grad_norm": 5.5,
"learning_rate": 9.935152296556467e-06,
"loss": 1.9463640213012696,
"step": 850
},
{
"epoch": 0.14821836356585807,
"grad_norm": 5.75,
"learning_rate": 9.930234123816503e-06,
"loss": 1.881173324584961,
"step": 860
},
{
"epoch": 0.14994183290964713,
"grad_norm": 6.09375,
"learning_rate": 9.925137511064527e-06,
"loss": 1.8919122695922852,
"step": 870
},
{
"epoch": 0.15166530225343616,
"grad_norm": 11.75,
"learning_rate": 9.919862642762291e-06,
"loss": 1.8629920959472657,
"step": 880
},
{
"epoch": 0.15338877159722522,
"grad_norm": 8.125,
"learning_rate": 9.914409709823158e-06,
"loss": 1.8775466918945312,
"step": 890
},
{
"epoch": 0.15511224094101425,
"grad_norm": 6.21875,
"learning_rate": 9.908778909605184e-06,
"loss": 1.8726503372192382,
"step": 900
},
{
"epoch": 0.1568357102848033,
"grad_norm": 11.8125,
"learning_rate": 9.902970445903974e-06,
"loss": 1.880959701538086,
"step": 910
},
{
"epoch": 0.15855917962859237,
"grad_norm": 8.3125,
"learning_rate": 9.896984528945313e-06,
"loss": 1.8687429428100586,
"step": 920
},
{
"epoch": 0.1602826489723814,
"grad_norm": 6.78125,
"learning_rate": 9.890821375377553e-06,
"loss": 1.8792970657348633,
"step": 930
},
{
"epoch": 0.16200611831617046,
"grad_norm": 6.3125,
"learning_rate": 9.88448120826377e-06,
"loss": 1.8895078659057618,
"step": 940
},
{
"epoch": 0.16372958765995949,
"grad_norm": 6.84375,
"learning_rate": 9.877964257073696e-06,
"loss": 1.8946203231811523,
"step": 950
},
{
"epoch": 0.16545305700374854,
"grad_norm": 9.5,
"learning_rate": 9.871270757675406e-06,
"loss": 1.8623432159423827,
"step": 960
},
{
"epoch": 0.1671765263475376,
"grad_norm": 51.5,
"learning_rate": 9.864400952326793e-06,
"loss": 1.912847900390625,
"step": 970
},
{
"epoch": 0.16889999569132663,
"grad_norm": 8.5625,
"learning_rate": 9.857355089666791e-06,
"loss": 1.8621129989624023,
"step": 980
},
{
"epoch": 0.1706234650351157,
"grad_norm": 5.15625,
"learning_rate": 9.850133424706371e-06,
"loss": 1.8847681045532227,
"step": 990
},
{
"epoch": 0.17234693437890475,
"grad_norm": 13.5,
"learning_rate": 9.842736218819327e-06,
"loss": 1.8754114151000976,
"step": 1000
},
{
"epoch": 0.17234693437890475,
"eval_loss": 1.8777226209640503,
"eval_runtime": 189.0816,
"eval_samples_per_second": 25.047,
"eval_steps_per_second": 3.131,
"step": 1000
},
{
"epoch": 0.17407040372269378,
"grad_norm": 8.3125,
"learning_rate": 9.835163739732805e-06,
"loss": 1.8813297271728515,
"step": 1010
},
{
"epoch": 0.17579387306648284,
"grad_norm": 5.8125,
"learning_rate": 9.827416261517613e-06,
"loss": 1.910245704650879,
"step": 1020
},
{
"epoch": 0.17751734241027187,
"grad_norm": 6.59375,
"learning_rate": 9.819494064578305e-06,
"loss": 1.8775476455688476,
"step": 1030
},
{
"epoch": 0.17924081175406092,
"grad_norm": 4.375,
"learning_rate": 9.811397435643037e-06,
"loss": 1.8659778594970704,
"step": 1040
},
{
"epoch": 0.18096428109784998,
"grad_norm": 11.25,
"learning_rate": 9.803126667753175e-06,
"loss": 1.886317253112793,
"step": 1050
},
{
"epoch": 0.182687750441639,
"grad_norm": 9.0625,
"learning_rate": 9.794682060252705e-06,
"loss": 1.9058975219726562,
"step": 1060
},
{
"epoch": 0.18441121978542807,
"grad_norm": 16.5,
"learning_rate": 9.786063918777386e-06,
"loss": 1.8786186218261718,
"step": 1070
},
{
"epoch": 0.1861346891292171,
"grad_norm": 10.3125,
"learning_rate": 9.777272555243702e-06,
"loss": 1.8804399490356445,
"step": 1080
},
{
"epoch": 0.18785815847300616,
"grad_norm": 25.875,
"learning_rate": 9.768308287837555e-06,
"loss": 1.83834228515625,
"step": 1090
},
{
"epoch": 0.18958162781679522,
"grad_norm": 9.9375,
"learning_rate": 9.759171441002766e-06,
"loss": 1.8528076171875,
"step": 1100
},
{
"epoch": 0.19130509716058425,
"grad_norm": 6.21875,
"learning_rate": 9.74986234542932e-06,
"loss": 1.8746351242065429,
"step": 1110
},
{
"epoch": 0.1930285665043733,
"grad_norm": 6.8125,
"learning_rate": 9.740381338041407e-06,
"loss": 1.881591796875,
"step": 1120
},
{
"epoch": 0.19475203584816236,
"grad_norm": 55.75,
"learning_rate": 9.730728761985218e-06,
"loss": 1.910407829284668,
"step": 1130
},
{
"epoch": 0.1964755051919514,
"grad_norm": 10.25,
"learning_rate": 9.720904966616533e-06,
"loss": 1.8622859954833983,
"step": 1140
},
{
"epoch": 0.19819897453574045,
"grad_norm": 5.9375,
"learning_rate": 9.710910307488075e-06,
"loss": 1.8853498458862306,
"step": 1150
},
{
"epoch": 0.19992244387952948,
"grad_norm": 28.875,
"learning_rate": 9.700745146336642e-06,
"loss": 1.900423812866211,
"step": 1160
},
{
"epoch": 0.20164591322331854,
"grad_norm": 8.375,
"learning_rate": 9.690409851070009e-06,
"loss": 1.889995002746582,
"step": 1170
},
{
"epoch": 0.2033693825671076,
"grad_norm": 8.875,
"learning_rate": 9.679904795753616e-06,
"loss": 1.8939664840698243,
"step": 1180
},
{
"epoch": 0.20509285191089663,
"grad_norm": 7.03125,
"learning_rate": 9.66923036059704e-06,
"loss": 1.8157171249389648,
"step": 1190
},
{
"epoch": 0.2068163212546857,
"grad_norm": 10.4375,
"learning_rate": 9.658386931940212e-06,
"loss": 1.8297653198242188,
"step": 1200
},
{
"epoch": 0.20853979059847472,
"grad_norm": 13.25,
"learning_rate": 9.647374902239452e-06,
"loss": 1.8692256927490234,
"step": 1210
},
{
"epoch": 0.21026325994226377,
"grad_norm": 7.1875,
"learning_rate": 9.636194670053263e-06,
"loss": 1.8458559036254882,
"step": 1220
},
{
"epoch": 0.21198672928605283,
"grad_norm": 10.625,
"learning_rate": 9.624846640027894e-06,
"loss": 1.8413688659667968,
"step": 1230
},
{
"epoch": 0.21371019862984186,
"grad_norm": 5.375,
"learning_rate": 9.61333122288271e-06,
"loss": 1.8779708862304687,
"step": 1240
},
{
"epoch": 0.21543366797363092,
"grad_norm": 5.90625,
"learning_rate": 9.601648835395314e-06,
"loss": 1.8429693222045898,
"step": 1250
},
{
"epoch": 0.21715713731741998,
"grad_norm": 29.125,
"learning_rate": 9.589799900386472e-06,
"loss": 1.862042236328125,
"step": 1260
},
{
"epoch": 0.218880606661209,
"grad_norm": 10.4375,
"learning_rate": 9.577784846704805e-06,
"loss": 1.8681344985961914,
"step": 1270
},
{
"epoch": 0.22060407600499807,
"grad_norm": 4.8125,
"learning_rate": 9.565604109211271e-06,
"loss": 1.8646697998046875,
"step": 1280
},
{
"epoch": 0.2223275453487871,
"grad_norm": 6.625,
"learning_rate": 9.553258128763418e-06,
"loss": 1.8120367050170898,
"step": 1290
},
{
"epoch": 0.22405101469257616,
"grad_norm": 8.375,
"learning_rate": 9.54074735219944e-06,
"loss": 1.8799192428588867,
"step": 1300
},
{
"epoch": 0.22577448403636521,
"grad_norm": 5.875,
"learning_rate": 9.528072232321996e-06,
"loss": 1.8551996231079102,
"step": 1310
},
{
"epoch": 0.22749795338015424,
"grad_norm": 9.0,
"learning_rate": 9.515233227881821e-06,
"loss": 1.871938705444336,
"step": 1320
},
{
"epoch": 0.2292214227239433,
"grad_norm": 191.0,
"learning_rate": 9.502230803561132e-06,
"loss": 1.8501504898071288,
"step": 1330
},
{
"epoch": 0.23094489206773233,
"grad_norm": 5.40625,
"learning_rate": 9.4890654299568e-06,
"loss": 1.8650516510009765,
"step": 1340
},
{
"epoch": 0.2326683614115214,
"grad_norm": 4.90625,
"learning_rate": 9.475737583563318e-06,
"loss": 1.860942268371582,
"step": 1350
},
{
"epoch": 0.23439183075531045,
"grad_norm": 6.875,
"learning_rate": 9.462247746755564e-06,
"loss": 1.8466346740722657,
"step": 1360
},
{
"epoch": 0.23611530009909948,
"grad_norm": 7.4375,
"learning_rate": 9.448596407771333e-06,
"loss": 1.8936279296875,
"step": 1370
},
{
"epoch": 0.23783876944288854,
"grad_norm": 37.0,
"learning_rate": 9.434784060693671e-06,
"loss": 1.8678653717041016,
"step": 1380
},
{
"epoch": 0.2395622387866776,
"grad_norm": 5.6875,
"learning_rate": 9.420811205432991e-06,
"loss": 1.8797569274902344,
"step": 1390
},
{
"epoch": 0.24128570813046663,
"grad_norm": 7.84375,
"learning_rate": 9.40667834770898e-06,
"loss": 1.8689140319824218,
"step": 1400
},
{
"epoch": 0.24300917747425568,
"grad_norm": 7.1875,
"learning_rate": 9.392385999032299e-06,
"loss": 1.8364645004272462,
"step": 1410
},
{
"epoch": 0.2447326468180447,
"grad_norm": 10.0625,
"learning_rate": 9.37793467668606e-06,
"loss": 1.8727912902832031,
"step": 1420
},
{
"epoch": 0.24645611616183377,
"grad_norm": 13.5625,
"learning_rate": 9.363324903707117e-06,
"loss": 1.8319427490234375,
"step": 1430
},
{
"epoch": 0.24817958550562283,
"grad_norm": 5.65625,
"learning_rate": 9.348557208867127e-06,
"loss": 1.8280084609985352,
"step": 1440
},
{
"epoch": 0.24990305484941186,
"grad_norm": 7.6875,
"learning_rate": 9.333632126653412e-06,
"loss": 1.8651538848876954,
"step": 1450
},
{
"epoch": 0.2516265241932009,
"grad_norm": 29.5,
"learning_rate": 9.318550197249619e-06,
"loss": 1.8845842361450196,
"step": 1460
},
{
"epoch": 0.25334999353698995,
"grad_norm": 8.3125,
"learning_rate": 9.30331196651617e-06,
"loss": 1.8626699447631836,
"step": 1470
},
{
"epoch": 0.25507346288077903,
"grad_norm": 8.625,
"learning_rate": 9.287917985970496e-06,
"loss": 1.8710561752319337,
"step": 1480
},
{
"epoch": 0.25679693222456806,
"grad_norm": 9.1875,
"learning_rate": 9.27236881276709e-06,
"loss": 1.829465675354004,
"step": 1490
},
{
"epoch": 0.2585204015683571,
"grad_norm": 40.0,
"learning_rate": 9.256665009677326e-06,
"loss": 1.8205698013305665,
"step": 1500
},
{
"epoch": 0.2585204015683571,
"eval_loss": 1.8534876108169556,
"eval_runtime": 189.1023,
"eval_samples_per_second": 25.045,
"eval_steps_per_second": 3.131,
"step": 1500
},
{
"epoch": 0.2602438709121461,
"grad_norm": 6.09375,
"learning_rate": 9.240807145069106e-06,
"loss": 1.8519729614257812,
"step": 1510
},
{
"epoch": 0.2619673402559352,
"grad_norm": 4.9375,
"learning_rate": 9.224795792886276e-06,
"loss": 1.827493667602539,
"step": 1520
},
{
"epoch": 0.26369080959972424,
"grad_norm": 7.375,
"learning_rate": 9.208631532627868e-06,
"loss": 1.8664134979248046,
"step": 1530
},
{
"epoch": 0.26541427894351327,
"grad_norm": 5.96875,
"learning_rate": 9.192314949327107e-06,
"loss": 1.8513822555541992,
"step": 1540
},
{
"epoch": 0.26713774828730236,
"grad_norm": 13.6875,
"learning_rate": 9.175846633530257e-06,
"loss": 1.828923797607422,
"step": 1550
},
{
"epoch": 0.2688612176310914,
"grad_norm": 7.03125,
"learning_rate": 9.15922718127523e-06,
"loss": 1.868868637084961,
"step": 1560
},
{
"epoch": 0.2705846869748804,
"grad_norm": 7.3125,
"learning_rate": 9.142457194070024e-06,
"loss": 1.8728532791137695,
"step": 1570
},
{
"epoch": 0.2723081563186695,
"grad_norm": 11.3125,
"learning_rate": 9.125537278870953e-06,
"loss": 1.8872152328491212,
"step": 1580
},
{
"epoch": 0.27403162566245853,
"grad_norm": 5.0,
"learning_rate": 9.108468048060675e-06,
"loss": 1.8836444854736327,
"step": 1590
},
{
"epoch": 0.27575509500624756,
"grad_norm": 5.96875,
"learning_rate": 9.091250119426023e-06,
"loss": 1.8695207595825196,
"step": 1600
},
{
"epoch": 0.27747856435003665,
"grad_norm": 7.375,
"learning_rate": 9.07388411613566e-06,
"loss": 1.822032356262207,
"step": 1610
},
{
"epoch": 0.2792020336938257,
"grad_norm": 19.375,
"learning_rate": 9.056370666717513e-06,
"loss": 1.8919815063476562,
"step": 1620
},
{
"epoch": 0.2809255030376147,
"grad_norm": 10.75,
"learning_rate": 9.03871040503603e-06,
"loss": 1.8365257263183594,
"step": 1630
},
{
"epoch": 0.28264897238140374,
"grad_norm": 8.9375,
"learning_rate": 9.020903970269233e-06,
"loss": 1.7987678527832032,
"step": 1640
},
{
"epoch": 0.2843724417251928,
"grad_norm": 7.8125,
"learning_rate": 9.002952006885592e-06,
"loss": 1.8505571365356446,
"step": 1650
},
{
"epoch": 0.28609591106898186,
"grad_norm": 7.125,
"learning_rate": 8.984855164620694e-06,
"loss": 1.8379674911499024,
"step": 1660
},
{
"epoch": 0.2878193804127709,
"grad_norm": 24.125,
"learning_rate": 8.966614098453728e-06,
"loss": 1.8600765228271485,
"step": 1670
},
{
"epoch": 0.28954284975656,
"grad_norm": 9.0625,
"learning_rate": 8.94822946858378e-06,
"loss": 1.825016975402832,
"step": 1680
},
{
"epoch": 0.291266319100349,
"grad_norm": 9.25,
"learning_rate": 8.929701940405939e-06,
"loss": 1.8779399871826172,
"step": 1690
},
{
"epoch": 0.29298978844413803,
"grad_norm": 6.65625,
"learning_rate": 8.911032184487216e-06,
"loss": 1.8601961135864258,
"step": 1700
},
{
"epoch": 0.2947132577879271,
"grad_norm": 7.5,
"learning_rate": 8.89222087654227e-06,
"loss": 1.851213264465332,
"step": 1710
},
{
"epoch": 0.29643672713171615,
"grad_norm": 4.90625,
"learning_rate": 8.873268697408952e-06,
"loss": 1.8635419845581054,
"step": 1720
},
{
"epoch": 0.2981601964755052,
"grad_norm": 47.25,
"learning_rate": 8.85417633302367e-06,
"loss": 1.8464191436767579,
"step": 1730
},
{
"epoch": 0.29988366581929427,
"grad_norm": 5.875,
"learning_rate": 8.834944474396551e-06,
"loss": 1.8149053573608398,
"step": 1740
},
{
"epoch": 0.3016071351630833,
"grad_norm": 6.84375,
"learning_rate": 8.815573817586448e-06,
"loss": 1.8667095184326172,
"step": 1750
},
{
"epoch": 0.3033306045068723,
"grad_norm": 11.875,
"learning_rate": 8.796065063675732e-06,
"loss": 1.8508197784423828,
"step": 1760
},
{
"epoch": 0.30505407385066136,
"grad_norm": 10.875,
"learning_rate": 8.776418918744922e-06,
"loss": 1.847660446166992,
"step": 1770
},
{
"epoch": 0.30677754319445044,
"grad_norm": 13.0625,
"learning_rate": 8.756636093847136e-06,
"loss": 1.8635337829589844,
"step": 1780
},
{
"epoch": 0.30850101253823947,
"grad_norm": 4.78125,
"learning_rate": 8.73671730498235e-06,
"loss": 1.8322547912597655,
"step": 1790
},
{
"epoch": 0.3102244818820285,
"grad_norm": 7.84375,
"learning_rate": 8.716663273071484e-06,
"loss": 1.8500213623046875,
"step": 1800
},
{
"epoch": 0.3119479512258176,
"grad_norm": 6.4375,
"learning_rate": 8.696474723930311e-06,
"loss": 1.828200340270996,
"step": 1810
},
{
"epoch": 0.3136714205696066,
"grad_norm": 6.5625,
"learning_rate": 8.676152388243191e-06,
"loss": 1.8678157806396485,
"step": 1820
},
{
"epoch": 0.31539488991339565,
"grad_norm": 17.125,
"learning_rate": 8.655697001536615e-06,
"loss": 1.825833511352539,
"step": 1830
},
{
"epoch": 0.31711835925718473,
"grad_norm": 5.6875,
"learning_rate": 8.635109304152598e-06,
"loss": 1.844728660583496,
"step": 1840
},
{
"epoch": 0.31884182860097376,
"grad_norm": 9.875,
"learning_rate": 8.614390041221872e-06,
"loss": 1.8418235778808594,
"step": 1850
},
{
"epoch": 0.3205652979447628,
"grad_norm": 11.3125,
"learning_rate": 8.593539962636924e-06,
"loss": 1.8504135131835937,
"step": 1860
},
{
"epoch": 0.3222887672885519,
"grad_norm": 7.78125,
"learning_rate": 8.572559823024853e-06,
"loss": 1.860449981689453,
"step": 1870
},
{
"epoch": 0.3240122366323409,
"grad_norm": 8.5625,
"learning_rate": 8.551450381720056e-06,
"loss": 1.8447723388671875,
"step": 1880
},
{
"epoch": 0.32573570597612994,
"grad_norm": 4.8125,
"learning_rate": 8.530212402736751e-06,
"loss": 1.8316837310791017,
"step": 1890
},
{
"epoch": 0.32745917531991897,
"grad_norm": 9.875,
"learning_rate": 8.508846654741318e-06,
"loss": 1.8276691436767578,
"step": 1900
},
{
"epoch": 0.32918264466370806,
"grad_norm": 6.0,
"learning_rate": 8.487353911024488e-06,
"loss": 1.8920913696289063,
"step": 1910
},
{
"epoch": 0.3309061140074971,
"grad_norm": 21.375,
"learning_rate": 8.46573494947334e-06,
"loss": 1.8723810195922852,
"step": 1920
},
{
"epoch": 0.3326295833512861,
"grad_norm": 10.4375,
"learning_rate": 8.443990552543165e-06,
"loss": 1.843758773803711,
"step": 1930
},
{
"epoch": 0.3343530526950752,
"grad_norm": 4.96875,
"learning_rate": 8.42212150722913e-06,
"loss": 1.8233121871948241,
"step": 1940
},
{
"epoch": 0.33607652203886423,
"grad_norm": 7.53125,
"learning_rate": 8.400128605037814e-06,
"loss": 1.842045211791992,
"step": 1950
},
{
"epoch": 0.33779999138265326,
"grad_norm": 7.9375,
"learning_rate": 8.378012641958537e-06,
"loss": 1.8421007156372071,
"step": 1960
},
{
"epoch": 0.33952346072644235,
"grad_norm": 33.75,
"learning_rate": 8.355774418434565e-06,
"loss": 1.846714401245117,
"step": 1970
},
{
"epoch": 0.3412469300702314,
"grad_norm": 6.875,
"learning_rate": 8.333414739334147e-06,
"loss": 1.858698272705078,
"step": 1980
},
{
"epoch": 0.3429703994140204,
"grad_norm": 24.125,
"learning_rate": 8.310934413921364e-06,
"loss": 1.8431358337402344,
"step": 1990
},
{
"epoch": 0.3446938687578095,
"grad_norm": 10.5,
"learning_rate": 8.288334255826853e-06,
"loss": 1.8638715744018555,
"step": 2000
},
{
"epoch": 0.3446938687578095,
"eval_loss": 1.8401983976364136,
"eval_runtime": 188.5578,
"eval_samples_per_second": 25.117,
"eval_steps_per_second": 3.14,
"step": 2000
},
{
"epoch": 0.3464173381015985,
"grad_norm": 5.53125,
"learning_rate": 8.26561508301836e-06,
"loss": 1.8239376068115234,
"step": 2010
},
{
"epoch": 0.34814080744538756,
"grad_norm": 7.75,
"learning_rate": 8.242777717771129e-06,
"loss": 1.8216110229492188,
"step": 2020
},
{
"epoch": 0.3498642767891766,
"grad_norm": 7.21875,
"learning_rate": 8.219822986638143e-06,
"loss": 1.817897415161133,
"step": 2030
},
{
"epoch": 0.3515877461329657,
"grad_norm": 6.40625,
"learning_rate": 8.196751720420216e-06,
"loss": 1.8432098388671876,
"step": 2040
},
{
"epoch": 0.3533112154767547,
"grad_norm": 4.5,
"learning_rate": 8.173564754135905e-06,
"loss": 1.8237773895263671,
"step": 2050
},
{
"epoch": 0.35503468482054373,
"grad_norm": 11.0,
"learning_rate": 8.150262926991314e-06,
"loss": 1.8344850540161133,
"step": 2060
},
{
"epoch": 0.3567581541643328,
"grad_norm": 4.125,
"learning_rate": 8.1268470823497e-06,
"loss": 1.8227569580078125,
"step": 2070
},
{
"epoch": 0.35848162350812185,
"grad_norm": 20.5,
"learning_rate": 8.103318067700957e-06,
"loss": 1.857133674621582,
"step": 2080
},
{
"epoch": 0.3602050928519109,
"grad_norm": 5.375,
"learning_rate": 8.079676734630941e-06,
"loss": 1.8662431716918946,
"step": 2090
},
{
"epoch": 0.36192856219569997,
"grad_norm": 8.0625,
"learning_rate": 8.055923938790657e-06,
"loss": 1.865074348449707,
"step": 2100
},
{
"epoch": 0.363652031539489,
"grad_norm": 7.125,
"learning_rate": 8.032060539865274e-06,
"loss": 1.8386310577392577,
"step": 2110
},
{
"epoch": 0.365375500883278,
"grad_norm": 6.8125,
"learning_rate": 8.008087401543026e-06,
"loss": 1.8924131393432617,
"step": 2120
},
{
"epoch": 0.3670989702270671,
"grad_norm": 21.0,
"learning_rate": 7.98400539148394e-06,
"loss": 1.8141424179077148,
"step": 2130
},
{
"epoch": 0.36882243957085614,
"grad_norm": 6.75,
"learning_rate": 7.959815381288445e-06,
"loss": 1.8318838119506835,
"step": 2140
},
{
"epoch": 0.3705459089146452,
"grad_norm": 7.59375,
"learning_rate": 7.935518246465815e-06,
"loss": 1.8339788436889648,
"step": 2150
},
{
"epoch": 0.3722693782584342,
"grad_norm": 12.625,
"learning_rate": 7.911114866402491e-06,
"loss": 1.8055469512939453,
"step": 2160
},
{
"epoch": 0.3739928476022233,
"grad_norm": 127.5,
"learning_rate": 7.886606124330249e-06,
"loss": 1.8341318130493165,
"step": 2170
},
{
"epoch": 0.3757163169460123,
"grad_norm": 10.3125,
"learning_rate": 7.861992907294227e-06,
"loss": 1.8485382080078125,
"step": 2180
},
{
"epoch": 0.37743978628980135,
"grad_norm": 7.875,
"learning_rate": 7.837276106120834e-06,
"loss": 1.8135955810546875,
"step": 2190
},
{
"epoch": 0.37916325563359043,
"grad_norm": 7.25,
"learning_rate": 7.812456615385496e-06,
"loss": 1.8876367568969727,
"step": 2200
},
{
"epoch": 0.38088672497737946,
"grad_norm": 9.25,
"learning_rate": 7.787535333380283e-06,
"loss": 1.8209230422973632,
"step": 2210
},
{
"epoch": 0.3826101943211685,
"grad_norm": 6.1875,
"learning_rate": 7.762513162081402e-06,
"loss": 1.8425830841064452,
"step": 2220
},
{
"epoch": 0.3843336636649576,
"grad_norm": 6.4375,
"learning_rate": 7.737391007116542e-06,
"loss": 1.869114875793457,
"step": 2230
},
{
"epoch": 0.3860571330087466,
"grad_norm": 5.5,
"learning_rate": 7.712169777732105e-06,
"loss": 1.804082489013672,
"step": 2240
},
{
"epoch": 0.38778060235253564,
"grad_norm": 4.125,
"learning_rate": 7.686850386760296e-06,
"loss": 1.8742061614990235,
"step": 2250
},
{
"epoch": 0.3895040716963247,
"grad_norm": 4.75,
"learning_rate": 7.661433750586077e-06,
"loss": 1.8540233612060546,
"step": 2260
},
{
"epoch": 0.39122754104011376,
"grad_norm": 6.90625,
"learning_rate": 7.635920789114012e-06,
"loss": 1.8454013824462892,
"step": 2270
},
{
"epoch": 0.3929510103839028,
"grad_norm": 10.125,
"learning_rate": 7.610312425734967e-06,
"loss": 1.8449623107910156,
"step": 2280
},
{
"epoch": 0.3946744797276918,
"grad_norm": 4.375,
"learning_rate": 7.584609587292686e-06,
"loss": 1.8612642288208008,
"step": 2290
},
{
"epoch": 0.3963979490714809,
"grad_norm": 9.5,
"learning_rate": 7.558813204050257e-06,
"loss": 1.8338241577148438,
"step": 2300
},
{
"epoch": 0.39812141841526993,
"grad_norm": 9.375,
"learning_rate": 7.532924209656429e-06,
"loss": 1.8515756607055665,
"step": 2310
},
{
"epoch": 0.39984488775905896,
"grad_norm": 16.375,
"learning_rate": 7.506943541111831e-06,
"loss": 1.8405086517333984,
"step": 2320
},
{
"epoch": 0.40156835710284805,
"grad_norm": 4.3125,
"learning_rate": 7.480872138735051e-06,
"loss": 1.8534727096557617,
"step": 2330
},
{
"epoch": 0.4032918264466371,
"grad_norm": 5.375,
"learning_rate": 7.454710946128617e-06,
"loss": 1.8462696075439453,
"step": 2340
},
{
"epoch": 0.4050152957904261,
"grad_norm": 83.0,
"learning_rate": 7.4284609101448265e-06,
"loss": 1.8416885375976562,
"step": 2350
},
{
"epoch": 0.4067387651342152,
"grad_norm": 8.25,
"learning_rate": 7.402122980851491e-06,
"loss": 1.8375621795654298,
"step": 2360
},
{
"epoch": 0.4084622344780042,
"grad_norm": 8.125,
"learning_rate": 7.37569811149754e-06,
"loss": 1.815802764892578,
"step": 2370
},
{
"epoch": 0.41018570382179326,
"grad_norm": 5.125,
"learning_rate": 7.349187258478534e-06,
"loss": 1.844595718383789,
"step": 2380
},
{
"epoch": 0.41190917316558234,
"grad_norm": 6.21875,
"learning_rate": 7.322591381302033e-06,
"loss": 1.8283041000366211,
"step": 2390
},
{
"epoch": 0.4136326425093714,
"grad_norm": 5.625,
"learning_rate": 7.2959114425528835e-06,
"loss": 1.8325546264648438,
"step": 2400
},
{
"epoch": 0.4153561118531604,
"grad_norm": 5.4375,
"learning_rate": 7.269148407858367e-06,
"loss": 1.8207094192504882,
"step": 2410
},
{
"epoch": 0.41707958119694943,
"grad_norm": 13.5625,
"learning_rate": 7.242303245853263e-06,
"loss": 1.8134254455566405,
"step": 2420
},
{
"epoch": 0.4188030505407385,
"grad_norm": 12.0625,
"learning_rate": 7.215376928144783e-06,
"loss": 1.8629745483398437,
"step": 2430
},
{
"epoch": 0.42052651988452755,
"grad_norm": 5.21875,
"learning_rate": 7.188370429277408e-06,
"loss": 1.8381343841552735,
"step": 2440
},
{
"epoch": 0.4222499892283166,
"grad_norm": 73.0,
"learning_rate": 7.161284726697616e-06,
"loss": 1.8185060501098633,
"step": 2450
},
{
"epoch": 0.42397345857210567,
"grad_norm": 5.40625,
"learning_rate": 7.134120800718507e-06,
"loss": 1.8640281677246093,
"step": 2460
},
{
"epoch": 0.4256969279158947,
"grad_norm": 5.375,
"learning_rate": 7.106879634484321e-06,
"loss": 1.8647268295288086,
"step": 2470
},
{
"epoch": 0.4274203972596837,
"grad_norm": 4.96875,
"learning_rate": 7.079562213934852e-06,
"loss": 1.832758331298828,
"step": 2480
},
{
"epoch": 0.4291438666034728,
"grad_norm": 7.34375,
"learning_rate": 7.052169527769772e-06,
"loss": 1.8156070709228516,
"step": 2490
},
{
"epoch": 0.43086733594726184,
"grad_norm": 5.0625,
"learning_rate": 7.024702567412839e-06,
"loss": 1.8204095840454102,
"step": 2500
},
{
"epoch": 0.43086733594726184,
"eval_loss": 1.83199143409729,
"eval_runtime": 189.3842,
"eval_samples_per_second": 25.007,
"eval_steps_per_second": 3.126,
"step": 2500
},
{
"epoch": 0.4325908052910509,
"grad_norm": 6.1875,
"learning_rate": 6.9971623269760204e-06,
"loss": 1.8643325805664062,
"step": 2510
},
{
"epoch": 0.43431427463483996,
"grad_norm": 5.4375,
"learning_rate": 6.969549803223508e-06,
"loss": 1.8427024841308595,
"step": 2520
},
{
"epoch": 0.436037743978629,
"grad_norm": 6.03125,
"learning_rate": 6.941865995535644e-06,
"loss": 1.8385257720947266,
"step": 2530
},
{
"epoch": 0.437761213322418,
"grad_norm": 5.15625,
"learning_rate": 6.914111905872752e-06,
"loss": 1.8454465866088867,
"step": 2540
},
{
"epoch": 0.43948468266620705,
"grad_norm": 6.875,
"learning_rate": 6.886288538738872e-06,
"loss": 1.7985853195190429,
"step": 2550
},
{
"epoch": 0.44120815200999614,
"grad_norm": 8.8125,
"learning_rate": 6.858396901145404e-06,
"loss": 1.8151981353759765,
"step": 2560
},
{
"epoch": 0.44293162135378517,
"grad_norm": 5.875,
"learning_rate": 6.83043800257466e-06,
"loss": 1.8277212142944337,
"step": 2570
},
{
"epoch": 0.4446550906975742,
"grad_norm": 6.5,
"learning_rate": 6.80241285494333e-06,
"loss": 1.8706268310546874,
"step": 2580
},
{
"epoch": 0.4463785600413633,
"grad_norm": 5.1875,
"learning_rate": 6.774322472565858e-06,
"loss": 1.8442064285278321,
"step": 2590
},
{
"epoch": 0.4481020293851523,
"grad_norm": 4.15625,
"learning_rate": 6.7461678721177285e-06,
"loss": 1.862114715576172,
"step": 2600
},
{
"epoch": 0.44982549872894134,
"grad_norm": 7.0,
"learning_rate": 6.717950072598673e-06,
"loss": 1.8287435531616212,
"step": 2610
},
{
"epoch": 0.45154896807273043,
"grad_norm": 5.65625,
"learning_rate": 6.689670095295784e-06,
"loss": 1.843255615234375,
"step": 2620
},
{
"epoch": 0.45327243741651946,
"grad_norm": 5.46875,
"learning_rate": 6.66132896374656e-06,
"loss": 1.8445619583129882,
"step": 2630
},
{
"epoch": 0.4549959067603085,
"grad_norm": 4.75,
"learning_rate": 6.6329277037018505e-06,
"loss": 1.8358469009399414,
"step": 2640
},
{
"epoch": 0.4567193761040976,
"grad_norm": 10.0625,
"learning_rate": 6.604467343088742e-06,
"loss": 1.8396055221557617,
"step": 2650
},
{
"epoch": 0.4584428454478866,
"grad_norm": 4.8125,
"learning_rate": 6.575948911973343e-06,
"loss": 1.8488874435424805,
"step": 2660
},
{
"epoch": 0.46016631479167563,
"grad_norm": 5.3125,
"learning_rate": 6.547373442523511e-06,
"loss": 1.8323183059692383,
"step": 2670
},
{
"epoch": 0.46188978413546466,
"grad_norm": 6.84375,
"learning_rate": 6.518741968971492e-06,
"loss": 1.8678075790405273,
"step": 2680
},
{
"epoch": 0.46361325347925375,
"grad_norm": 7.9375,
"learning_rate": 6.490055527576492e-06,
"loss": 1.7891368865966797,
"step": 2690
},
{
"epoch": 0.4653367228230428,
"grad_norm": 5.75,
"learning_rate": 6.461315156587162e-06,
"loss": 1.8243621826171874,
"step": 2700
},
{
"epoch": 0.4670601921668318,
"grad_norm": 4.875,
"learning_rate": 6.432521896204035e-06,
"loss": 1.8012350082397461,
"step": 2710
},
{
"epoch": 0.4687836615106209,
"grad_norm": 6.375,
"learning_rate": 6.4036767885418625e-06,
"loss": 1.8313072204589844,
"step": 2720
},
{
"epoch": 0.4705071308544099,
"grad_norm": 4.4375,
"learning_rate": 6.37478087759191e-06,
"loss": 1.8313379287719727,
"step": 2730
},
{
"epoch": 0.47223060019819896,
"grad_norm": 10.0,
"learning_rate": 6.345835209184169e-06,
"loss": 1.851654624938965,
"step": 2740
},
{
"epoch": 0.47395406954198804,
"grad_norm": 11.4375,
"learning_rate": 6.316840830949498e-06,
"loss": 1.834511947631836,
"step": 2750
},
{
"epoch": 0.4756775388857771,
"grad_norm": 5.90625,
"learning_rate": 6.287798792281713e-06,
"loss": 1.831475067138672,
"step": 2760
},
{
"epoch": 0.4774010082295661,
"grad_norm": 6.53125,
"learning_rate": 6.258710144299604e-06,
"loss": 1.8179866790771484,
"step": 2770
},
{
"epoch": 0.4791244775733552,
"grad_norm": 4.09375,
"learning_rate": 6.229575939808893e-06,
"loss": 1.8372505187988282,
"step": 2780
},
{
"epoch": 0.4808479469171442,
"grad_norm": 6.84375,
"learning_rate": 6.200397233264129e-06,
"loss": 1.8282224655151367,
"step": 2790
},
{
"epoch": 0.48257141626093325,
"grad_norm": 19.75,
"learning_rate": 6.171175080730526e-06,
"loss": 1.820566177368164,
"step": 2800
},
{
"epoch": 0.4842948856047223,
"grad_norm": 6.71875,
"learning_rate": 6.141910539845736e-06,
"loss": 1.8087228775024413,
"step": 2810
},
{
"epoch": 0.48601835494851137,
"grad_norm": 5.09375,
"learning_rate": 6.112604669781572e-06,
"loss": 1.833594512939453,
"step": 2820
},
{
"epoch": 0.4877418242923004,
"grad_norm": 6.0625,
"learning_rate": 6.083258531205681e-06,
"loss": 1.8270418167114257,
"step": 2830
},
{
"epoch": 0.4894652936360894,
"grad_norm": 10.0,
"learning_rate": 6.053873186243141e-06,
"loss": 1.8435356140136718,
"step": 2840
},
{
"epoch": 0.4911887629798785,
"grad_norm": 5.34375,
"learning_rate": 6.024449698438033e-06,
"loss": 1.8381929397583008,
"step": 2850
},
{
"epoch": 0.49291223232366754,
"grad_norm": 7.53125,
"learning_rate": 5.9949891327149375e-06,
"loss": 1.8102424621582032,
"step": 2860
},
{
"epoch": 0.4946357016674566,
"grad_norm": 72.5,
"learning_rate": 5.965492555340401e-06,
"loss": 1.8426288604736327,
"step": 2870
},
{
"epoch": 0.49635917101124566,
"grad_norm": 5.46875,
"learning_rate": 5.935961033884336e-06,
"loss": 1.8150890350341797,
"step": 2880
},
{
"epoch": 0.4980826403550347,
"grad_norm": 4.28125,
"learning_rate": 5.9063956371813905e-06,
"loss": 1.8337799072265626,
"step": 2890
},
{
"epoch": 0.4998061096988237,
"grad_norm": 5.59375,
"learning_rate": 5.876797435292254e-06,
"loss": 1.789473533630371,
"step": 2900
},
{
"epoch": 0.5015295790426127,
"grad_norm": 9.875,
"learning_rate": 5.847167499464941e-06,
"loss": 1.8173267364501953,
"step": 2910
},
{
"epoch": 0.5032530483864018,
"grad_norm": 5.1875,
"learning_rate": 5.817506902096007e-06,
"loss": 1.8565616607666016,
"step": 2920
},
{
"epoch": 0.5049765177301909,
"grad_norm": 13.75,
"learning_rate": 5.787816716691746e-06,
"loss": 1.8447467803955078,
"step": 2930
},
{
"epoch": 0.5066999870739799,
"grad_norm": 6.5,
"learning_rate": 5.758098017829329e-06,
"loss": 1.8645750045776368,
"step": 2940
},
{
"epoch": 0.508423456417769,
"grad_norm": 6.5,
"learning_rate": 5.728351881117915e-06,
"loss": 1.8155582427978516,
"step": 2950
},
{
"epoch": 0.5101469257615581,
"grad_norm": 24.375,
"learning_rate": 5.698579383159721e-06,
"loss": 1.799262809753418,
"step": 2960
},
{
"epoch": 0.511870395105347,
"grad_norm": 5.25,
"learning_rate": 5.668781601511059e-06,
"loss": 1.8040689468383788,
"step": 2970
},
{
"epoch": 0.5135938644491361,
"grad_norm": 6.1875,
"learning_rate": 5.638959614643333e-06,
"loss": 1.8163867950439454,
"step": 2980
},
{
"epoch": 0.5153173337929251,
"grad_norm": 5.28125,
"learning_rate": 5.609114501904006e-06,
"loss": 1.8470441818237304,
"step": 2990
},
{
"epoch": 0.5170408031367142,
"grad_norm": 10.6875,
"learning_rate": 5.579247343477533e-06,
"loss": 1.8359079360961914,
"step": 3000
},
{
"epoch": 0.5170408031367142,
"eval_loss": 1.8268558979034424,
"eval_runtime": 189.165,
"eval_samples_per_second": 25.036,
"eval_steps_per_second": 3.13,
"step": 3000
},
{
"epoch": 0.5187642724805033,
"grad_norm": 6.96875,
"learning_rate": 5.549359220346277e-06,
"loss": 1.818197250366211,
"step": 3010
},
{
"epoch": 0.5204877418242922,
"grad_norm": 5.78125,
"learning_rate": 5.519451214251368e-06,
"loss": 1.79785213470459,
"step": 3020
},
{
"epoch": 0.5222112111680813,
"grad_norm": 6.84375,
"learning_rate": 5.489524407653566e-06,
"loss": 1.824350357055664,
"step": 3030
},
{
"epoch": 0.5239346805118704,
"grad_norm": 3.484375,
"learning_rate": 5.459579883694075e-06,
"loss": 1.8040481567382813,
"step": 3040
},
{
"epoch": 0.5256581498556594,
"grad_norm": 14.4375,
"learning_rate": 5.429618726155344e-06,
"loss": 1.8301307678222656,
"step": 3050
},
{
"epoch": 0.5273816191994485,
"grad_norm": 4.875,
"learning_rate": 5.399642019421844e-06,
"loss": 1.7872705459594727,
"step": 3060
},
{
"epoch": 0.5291050885432376,
"grad_norm": 11.625,
"learning_rate": 5.369650848440813e-06,
"loss": 1.839627456665039,
"step": 3070
},
{
"epoch": 0.5308285578870265,
"grad_norm": 8.25,
"learning_rate": 5.339646298682997e-06,
"loss": 1.8403564453125,
"step": 3080
},
{
"epoch": 0.5325520272308156,
"grad_norm": 15.8125,
"learning_rate": 5.30962945610336e-06,
"loss": 1.8385784149169921,
"step": 3090
},
{
"epoch": 0.5342754965746047,
"grad_norm": 5.34375,
"learning_rate": 5.279601407101782e-06,
"loss": 1.8381383895874024,
"step": 3100
},
{
"epoch": 0.5359989659183937,
"grad_norm": 6.03125,
"learning_rate": 5.249563238483733e-06,
"loss": 1.8248268127441407,
"step": 3110
},
{
"epoch": 0.5377224352621828,
"grad_norm": 23.0,
"learning_rate": 5.219516037420946e-06,
"loss": 1.8576610565185547,
"step": 3120
},
{
"epoch": 0.5394459046059719,
"grad_norm": 9.375,
"learning_rate": 5.1894608914120635e-06,
"loss": 1.8108026504516601,
"step": 3130
},
{
"epoch": 0.5411693739497608,
"grad_norm": 7.78125,
"learning_rate": 5.159398888243279e-06,
"loss": 1.8647409439086915,
"step": 3140
},
{
"epoch": 0.5428928432935499,
"grad_norm": 7.3125,
"learning_rate": 5.129331115948968e-06,
"loss": 1.8226402282714844,
"step": 3150
},
{
"epoch": 0.544616312637339,
"grad_norm": 6.9375,
"learning_rate": 5.0992586627723075e-06,
"loss": 1.820734405517578,
"step": 3160
},
{
"epoch": 0.546339781981128,
"grad_norm": 12.625,
"learning_rate": 5.069182617125892e-06,
"loss": 1.8093095779418946,
"step": 3170
},
{
"epoch": 0.5480632513249171,
"grad_norm": 15.5,
"learning_rate": 5.039104067552336e-06,
"loss": 1.8144065856933593,
"step": 3180
},
{
"epoch": 0.5497867206687062,
"grad_norm": 7.375,
"learning_rate": 5.0090241026848806e-06,
"loss": 1.8056734085083008,
"step": 3190
},
{
"epoch": 0.5515101900124951,
"grad_norm": 6.15625,
"learning_rate": 4.978943811207988e-06,
"loss": 1.8280052185058593,
"step": 3200
},
{
"epoch": 0.5532336593562842,
"grad_norm": 4.59375,
"learning_rate": 4.948864281817941e-06,
"loss": 1.8493799209594726,
"step": 3210
},
{
"epoch": 0.5549571287000733,
"grad_norm": 7.34375,
"learning_rate": 4.918786603183447e-06,
"loss": 1.806777000427246,
"step": 3220
},
{
"epoch": 0.5566805980438623,
"grad_norm": 5.96875,
"learning_rate": 4.8887118639062175e-06,
"loss": 1.7821395874023438,
"step": 3230
},
{
"epoch": 0.5584040673876514,
"grad_norm": 6.59375,
"learning_rate": 4.858641152481592e-06,
"loss": 1.811480712890625,
"step": 3240
},
{
"epoch": 0.5601275367314403,
"grad_norm": 5.15625,
"learning_rate": 4.82857555725912e-06,
"loss": 1.7693416595458984,
"step": 3250
},
{
"epoch": 0.5618510060752294,
"grad_norm": 7.8125,
"learning_rate": 4.798516166403188e-06,
"loss": 1.8069271087646483,
"step": 3260
},
{
"epoch": 0.5635744754190185,
"grad_norm": 8.75,
"learning_rate": 4.76846406785362e-06,
"loss": 1.821498489379883,
"step": 3270
},
{
"epoch": 0.5652979447628075,
"grad_norm": 5.53125,
"learning_rate": 4.738420349286318e-06,
"loss": 1.8615631103515624,
"step": 3280
},
{
"epoch": 0.5670214141065966,
"grad_norm": 13.5,
"learning_rate": 4.708386098073878e-06,
"loss": 1.827471923828125,
"step": 3290
},
{
"epoch": 0.5687448834503857,
"grad_norm": 4.71875,
"learning_rate": 4.6783624012462505e-06,
"loss": 1.7911121368408203,
"step": 3300
},
{
"epoch": 0.5704683527941746,
"grad_norm": 7.28125,
"learning_rate": 4.648350345451394e-06,
"loss": 1.8227167129516602,
"step": 3310
},
{
"epoch": 0.5721918221379637,
"grad_norm": 9.875,
"learning_rate": 4.618351016915932e-06,
"loss": 1.8071161270141602,
"step": 3320
},
{
"epoch": 0.5739152914817528,
"grad_norm": 6.8125,
"learning_rate": 4.588365501405861e-06,
"loss": 1.869521141052246,
"step": 3330
},
{
"epoch": 0.5756387608255418,
"grad_norm": 10.5,
"learning_rate": 4.558394884187234e-06,
"loss": 1.8539451599121093,
"step": 3340
},
{
"epoch": 0.5773622301693309,
"grad_norm": 12.6875,
"learning_rate": 4.528440249986899e-06,
"loss": 1.8072568893432617,
"step": 3350
},
{
"epoch": 0.57908569951312,
"grad_norm": 5.03125,
"learning_rate": 4.498502682953219e-06,
"loss": 1.8290151596069335,
"step": 3360
},
{
"epoch": 0.5808091688569089,
"grad_norm": 8.1875,
"learning_rate": 4.468583266616856e-06,
"loss": 1.789365005493164,
"step": 3370
},
{
"epoch": 0.582532638200698,
"grad_norm": 5.75,
"learning_rate": 4.43868308385154e-06,
"loss": 1.8456544876098633,
"step": 3380
},
{
"epoch": 0.5842561075444871,
"grad_norm": 34.75,
"learning_rate": 4.4088032168348745e-06,
"loss": 1.8169525146484375,
"step": 3390
},
{
"epoch": 0.5859795768882761,
"grad_norm": 4.625,
"learning_rate": 4.378944747009185e-06,
"loss": 1.8146444320678712,
"step": 3400
},
{
"epoch": 0.5877030462320652,
"grad_norm": 6.96875,
"learning_rate": 4.3491087550423585e-06,
"loss": 1.820088768005371,
"step": 3410
},
{
"epoch": 0.5894265155758542,
"grad_norm": 4.5,
"learning_rate": 4.3192963207887466e-06,
"loss": 1.831465721130371,
"step": 3420
},
{
"epoch": 0.5911499849196432,
"grad_norm": 5.46875,
"learning_rate": 4.289508523250075e-06,
"loss": 1.8280218124389649,
"step": 3430
},
{
"epoch": 0.5928734542634323,
"grad_norm": 7.40625,
"learning_rate": 4.259746440536392e-06,
"loss": 1.8419511795043946,
"step": 3440
},
{
"epoch": 0.5945969236072214,
"grad_norm": 7.625,
"learning_rate": 4.230011149827049e-06,
"loss": 1.8106534957885743,
"step": 3450
},
{
"epoch": 0.5963203929510104,
"grad_norm": 17.125,
"learning_rate": 4.200303727331714e-06,
"loss": 1.837515640258789,
"step": 3460
},
{
"epoch": 0.5980438622947994,
"grad_norm": 5.59375,
"learning_rate": 4.170625248251423e-06,
"loss": 1.8307241439819335,
"step": 3470
},
{
"epoch": 0.5997673316385885,
"grad_norm": 5.0,
"learning_rate": 4.140976786739658e-06,
"loss": 1.8505414962768554,
"step": 3480
},
{
"epoch": 0.6014908009823775,
"grad_norm": 13.4375,
"learning_rate": 4.111359415863478e-06,
"loss": 1.8339092254638671,
"step": 3490
},
{
"epoch": 0.6032142703261666,
"grad_norm": 8.8125,
"learning_rate": 4.0817742075646785e-06,
"loss": 1.849088478088379,
"step": 3500
},
{
"epoch": 0.6032142703261666,
"eval_loss": 1.8238149881362915,
"eval_runtime": 189.2325,
"eval_samples_per_second": 25.027,
"eval_steps_per_second": 3.128,
"step": 3500
},
{
"epoch": 0.6049377396699556,
"grad_norm": 5.96875,
"learning_rate": 4.052222232620994e-06,
"loss": 1.8315574645996093,
"step": 3510
},
{
"epoch": 0.6066612090137447,
"grad_norm": 5.9375,
"learning_rate": 4.02270456060734e-06,
"loss": 1.8226449966430665,
"step": 3520
},
{
"epoch": 0.6083846783575337,
"grad_norm": 5.78125,
"learning_rate": 3.993222259857116e-06,
"loss": 1.7947715759277343,
"step": 3530
},
{
"epoch": 0.6101081477013227,
"grad_norm": 5.46875,
"learning_rate": 3.963776397423515e-06,
"loss": 1.8149684906005858,
"step": 3540
},
{
"epoch": 0.6118316170451118,
"grad_norm": 30.875,
"learning_rate": 3.934368039040929e-06,
"loss": 1.7860773086547852,
"step": 3550
},
{
"epoch": 0.6135550863889009,
"grad_norm": 6.28125,
"learning_rate": 3.904998249086362e-06,
"loss": 1.826930618286133,
"step": 3560
},
{
"epoch": 0.6152785557326899,
"grad_norm": 5.5,
"learning_rate": 3.875668090540907e-06,
"loss": 1.8217718124389648,
"step": 3570
},
{
"epoch": 0.6170020250764789,
"grad_norm": 4.5,
"learning_rate": 3.846378624951285e-06,
"loss": 1.824087142944336,
"step": 3580
},
{
"epoch": 0.618725494420268,
"grad_norm": 4.9375,
"learning_rate": 3.817130912391404e-06,
"loss": 1.8421728134155273,
"step": 3590
},
{
"epoch": 0.620448963764057,
"grad_norm": 5.25,
"learning_rate": 3.7879260114240202e-06,
"loss": 1.7913167953491211,
"step": 3600
},
{
"epoch": 0.6221724331078461,
"grad_norm": 5.59375,
"learning_rate": 3.7587649790623925e-06,
"loss": 1.8023431777954102,
"step": 3610
},
{
"epoch": 0.6238959024516352,
"grad_norm": 4.625,
"learning_rate": 3.729648870732058e-06,
"loss": 1.838007354736328,
"step": 3620
},
{
"epoch": 0.6256193717954242,
"grad_norm": 9.125,
"learning_rate": 3.7005787402326064e-06,
"loss": 1.8036937713623047,
"step": 3630
},
{
"epoch": 0.6273428411392132,
"grad_norm": 5.34375,
"learning_rate": 3.6715556396995584e-06,
"loss": 1.8324485778808595,
"step": 3640
},
{
"epoch": 0.6290663104830023,
"grad_norm": 5.75,
"learning_rate": 3.6425806195662777e-06,
"loss": 1.8155427932739259,
"step": 3650
},
{
"epoch": 0.6307897798267913,
"grad_norm": 4.8125,
"learning_rate": 3.613654728525948e-06,
"loss": 1.8596065521240235,
"step": 3660
},
{
"epoch": 0.6325132491705804,
"grad_norm": 5.5,
"learning_rate": 3.584779013493633e-06,
"loss": 1.8445602416992188,
"step": 3670
},
{
"epoch": 0.6342367185143695,
"grad_norm": 5.5625,
"learning_rate": 3.5559545195683644e-06,
"loss": 1.8150409698486327,
"step": 3680
},
{
"epoch": 0.6359601878581584,
"grad_norm": 5.4375,
"learning_rate": 3.527182289995339e-06,
"loss": 1.8006818771362305,
"step": 3690
},
{
"epoch": 0.6376836572019475,
"grad_norm": 10.125,
"learning_rate": 3.4984633661281387e-06,
"loss": 1.7760576248168944,
"step": 3700
},
{
"epoch": 0.6394071265457366,
"grad_norm": 6.40625,
"learning_rate": 3.46979878739106e-06,
"loss": 1.8336132049560547,
"step": 3710
},
{
"epoch": 0.6411305958895256,
"grad_norm": 10.6875,
"learning_rate": 3.441189591241484e-06,
"loss": 1.8170570373535155,
"step": 3720
},
{
"epoch": 0.6428540652333147,
"grad_norm": 5.0625,
"learning_rate": 3.412636813132323e-06,
"loss": 1.8622470855712892,
"step": 3730
},
{
"epoch": 0.6445775345771038,
"grad_norm": 152.0,
"learning_rate": 3.3841414864745602e-06,
"loss": 1.8457544326782227,
"step": 3740
},
{
"epoch": 0.6463010039208927,
"grad_norm": 6.6875,
"learning_rate": 3.3557046425998285e-06,
"loss": 1.8270475387573242,
"step": 3750
},
{
"epoch": 0.6480244732646818,
"grad_norm": 13.0625,
"learning_rate": 3.3273273107231007e-06,
"loss": 1.8271034240722657,
"step": 3760
},
{
"epoch": 0.6497479426084708,
"grad_norm": 6.9375,
"learning_rate": 3.2990105179054245e-06,
"loss": 1.823533821105957,
"step": 3770
},
{
"epoch": 0.6514714119522599,
"grad_norm": 4.4375,
"learning_rate": 3.2707552890167636e-06,
"loss": 1.820975112915039,
"step": 3780
},
{
"epoch": 0.653194881296049,
"grad_norm": 162.0,
"learning_rate": 3.2425626466988914e-06,
"loss": 1.7972105026245118,
"step": 3790
},
{
"epoch": 0.6549183506398379,
"grad_norm": 9.3125,
"learning_rate": 3.2144336113283893e-06,
"loss": 1.8197662353515625,
"step": 3800
},
{
"epoch": 0.656641819983627,
"grad_norm": 4.1875,
"learning_rate": 3.186369200979712e-06,
"loss": 1.8468887329101562,
"step": 3810
},
{
"epoch": 0.6583652893274161,
"grad_norm": 11.9375,
"learning_rate": 3.1583704313883346e-06,
"loss": 1.8152883529663086,
"step": 3820
},
{
"epoch": 0.6600887586712051,
"grad_norm": 5.65625,
"learning_rate": 3.130438315914005e-06,
"loss": 1.8321706771850585,
"step": 3830
},
{
"epoch": 0.6618122280149942,
"grad_norm": 3.890625,
"learning_rate": 3.102573865504047e-06,
"loss": 1.794466209411621,
"step": 3840
},
{
"epoch": 0.6635356973587833,
"grad_norm": 6.71875,
"learning_rate": 3.0747780886567922e-06,
"loss": 1.792155647277832,
"step": 3850
},
{
"epoch": 0.6652591667025722,
"grad_norm": 6.53125,
"learning_rate": 3.0470519913850604e-06,
"loss": 1.7653938293457032,
"step": 3860
},
{
"epoch": 0.6669826360463613,
"grad_norm": 8.0625,
"learning_rate": 3.019396577179765e-06,
"loss": 1.8039230346679687,
"step": 3870
},
{
"epoch": 0.6687061053901504,
"grad_norm": 27.0,
"learning_rate": 2.9918128469735853e-06,
"loss": 1.8375740051269531,
"step": 3880
},
{
"epoch": 0.6704295747339394,
"grad_norm": 6.8125,
"learning_rate": 2.964301799104735e-06,
"loss": 1.812276840209961,
"step": 3890
},
{
"epoch": 0.6721530440777285,
"grad_norm": 29.125,
"learning_rate": 2.9368644292808433e-06,
"loss": 1.834174919128418,
"step": 3900
},
{
"epoch": 0.6738765134215176,
"grad_norm": 5.65625,
"learning_rate": 2.909501730542902e-06,
"loss": 1.8168300628662108,
"step": 3910
},
{
"epoch": 0.6755999827653065,
"grad_norm": 21.625,
"learning_rate": 2.88221469322934e-06,
"loss": 1.8631282806396485,
"step": 3920
},
{
"epoch": 0.6773234521090956,
"grad_norm": 9.1875,
"learning_rate": 2.8550043049401593e-06,
"loss": 1.768804168701172,
"step": 3930
},
{
"epoch": 0.6790469214528847,
"grad_norm": 5.65625,
"learning_rate": 2.827871550501218e-06,
"loss": 1.8265512466430665,
"step": 3940
},
{
"epoch": 0.6807703907966737,
"grad_norm": 14.3125,
"learning_rate": 2.8008174119285566e-06,
"loss": 1.8523290634155274,
"step": 3950
},
{
"epoch": 0.6824938601404628,
"grad_norm": 18.0,
"learning_rate": 2.7738428683928824e-06,
"loss": 1.814921760559082,
"step": 3960
},
{
"epoch": 0.6842173294842518,
"grad_norm": 6.90625,
"learning_rate": 2.746948896184114e-06,
"loss": 1.7983022689819337,
"step": 3970
},
{
"epoch": 0.6859407988280408,
"grad_norm": 4.34375,
"learning_rate": 2.7201364686760493e-06,
"loss": 1.8213691711425781,
"step": 3980
},
{
"epoch": 0.6876642681718299,
"grad_norm": 7.1875,
"learning_rate": 2.6934065562911417e-06,
"loss": 1.8135198593139648,
"step": 3990
},
{
"epoch": 0.689387737515619,
"grad_norm": 7.375,
"learning_rate": 2.6667601264653718e-06,
"loss": 1.8103212356567382,
"step": 4000
},
{
"epoch": 0.689387737515619,
"eval_loss": 1.8220584392547607,
"eval_runtime": 189.1065,
"eval_samples_per_second": 25.044,
"eval_steps_per_second": 3.131,
"step": 4000
},
{
"epoch": 0.691111206859408,
"grad_norm": 4.75,
"learning_rate": 2.640198143613237e-06,
"loss": 1.8163627624511718,
"step": 4010
},
{
"epoch": 0.692834676203197,
"grad_norm": 8.8125,
"learning_rate": 2.613721569092841e-06,
"loss": 1.8307807922363282,
"step": 4020
},
{
"epoch": 0.694558145546986,
"grad_norm": 6.0625,
"learning_rate": 2.587331361171107e-06,
"loss": 1.8075574874877929,
"step": 4030
},
{
"epoch": 0.6962816148907751,
"grad_norm": 4.84375,
"learning_rate": 2.561028474989088e-06,
"loss": 1.8375968933105469,
"step": 4040
},
{
"epoch": 0.6980050842345642,
"grad_norm": 5.4375,
"learning_rate": 2.5348138625274004e-06,
"loss": 1.8355876922607421,
"step": 4050
},
{
"epoch": 0.6997285535783532,
"grad_norm": 10.125,
"learning_rate": 2.5086884725717764e-06,
"loss": 1.8059595108032227,
"step": 4060
},
{
"epoch": 0.7014520229221423,
"grad_norm": 12.3125,
"learning_rate": 2.482653250678702e-06,
"loss": 1.832951545715332,
"step": 4070
},
{
"epoch": 0.7031754922659313,
"grad_norm": 7.5625,
"learning_rate": 2.4567091391412274e-06,
"loss": 1.7960575103759766,
"step": 4080
},
{
"epoch": 0.7048989616097203,
"grad_norm": 6.84375,
"learning_rate": 2.4308570769548277e-06,
"loss": 1.7987342834472657,
"step": 4090
},
{
"epoch": 0.7066224309535094,
"grad_norm": 6.25,
"learning_rate": 2.405097999783451e-06,
"loss": 1.8265256881713867,
"step": 4100
},
{
"epoch": 0.7083459002972985,
"grad_norm": 100.0,
"learning_rate": 2.3794328399256235e-06,
"loss": 1.8468996047973634,
"step": 4110
},
{
"epoch": 0.7100693696410875,
"grad_norm": 11.1875,
"learning_rate": 2.353862526280732e-06,
"loss": 1.8254108428955078,
"step": 4120
},
{
"epoch": 0.7117928389848766,
"grad_norm": 7.5,
"learning_rate": 2.3283879843153873e-06,
"loss": 1.8398422241210937,
"step": 4130
},
{
"epoch": 0.7135163083286656,
"grad_norm": 4.5,
"learning_rate": 2.3030101360299377e-06,
"loss": 1.8488418579101562,
"step": 4140
},
{
"epoch": 0.7152397776724546,
"grad_norm": 5.03125,
"learning_rate": 2.2777298999250946e-06,
"loss": 1.834120750427246,
"step": 4150
},
{
"epoch": 0.7169632470162437,
"grad_norm": 9.875,
"learning_rate": 2.2525481909686916e-06,
"loss": 1.8231204986572265,
"step": 4160
},
{
"epoch": 0.7186867163600328,
"grad_norm": 5.5625,
"learning_rate": 2.227465920562567e-06,
"loss": 1.8394210815429688,
"step": 4170
},
{
"epoch": 0.7204101857038218,
"grad_norm": 5.34375,
"learning_rate": 2.2024839965095814e-06,
"loss": 1.829633903503418,
"step": 4180
},
{
"epoch": 0.7221336550476108,
"grad_norm": 9.8125,
"learning_rate": 2.177603322980756e-06,
"loss": 1.8519102096557618,
"step": 4190
},
{
"epoch": 0.7238571243913999,
"grad_norm": 7.28125,
"learning_rate": 2.152824800482552e-06,
"loss": 1.8017757415771485,
"step": 4200
},
{
"epoch": 0.7255805937351889,
"grad_norm": 8.3125,
"learning_rate": 2.1281493258242754e-06,
"loss": 1.8026397705078125,
"step": 4210
},
{
"epoch": 0.727304063078978,
"grad_norm": 9.125,
"learning_rate": 2.1035777920856282e-06,
"loss": 1.806100845336914,
"step": 4220
},
{
"epoch": 0.7290275324227671,
"grad_norm": 18.5,
"learning_rate": 2.079111088584365e-06,
"loss": 1.8078620910644532,
"step": 4230
},
{
"epoch": 0.730751001766556,
"grad_norm": 4.09375,
"learning_rate": 2.0547501008441336e-06,
"loss": 1.8371273040771485,
"step": 4240
},
{
"epoch": 0.7324744711103451,
"grad_norm": 9.8125,
"learning_rate": 2.0304957105623936e-06,
"loss": 1.8442197799682618,
"step": 4250
},
{
"epoch": 0.7341979404541342,
"grad_norm": 6.21875,
"learning_rate": 2.006348795578538e-06,
"loss": 1.8367244720458984,
"step": 4260
},
{
"epoch": 0.7359214097979232,
"grad_norm": 5.15625,
"learning_rate": 1.9823102298420916e-06,
"loss": 1.8028837203979493,
"step": 4270
},
{
"epoch": 0.7376448791417123,
"grad_norm": 4.78125,
"learning_rate": 1.958380883381105e-06,
"loss": 1.7981758117675781,
"step": 4280
},
{
"epoch": 0.7393683484855013,
"grad_norm": 6.96875,
"learning_rate": 1.934561622270645e-06,
"loss": 1.839104461669922,
"step": 4290
},
{
"epoch": 0.7410918178292903,
"grad_norm": 5.75,
"learning_rate": 1.9108533086014656e-06,
"loss": 1.8137498855590821,
"step": 4300
},
{
"epoch": 0.7428152871730794,
"grad_norm": 12.625,
"learning_rate": 1.8872568004487963e-06,
"loss": 1.8252948760986327,
"step": 4310
},
{
"epoch": 0.7445387565168684,
"grad_norm": 20.25,
"learning_rate": 1.8637729518412861e-06,
"loss": 1.8452091217041016,
"step": 4320
},
{
"epoch": 0.7462622258606575,
"grad_norm": 8.3125,
"learning_rate": 1.8404026127300996e-06,
"loss": 1.8453563690185546,
"step": 4330
},
{
"epoch": 0.7479856952044466,
"grad_norm": 5.28125,
"learning_rate": 1.8171466289581492e-06,
"loss": 1.8368492126464844,
"step": 4340
},
{
"epoch": 0.7497091645482356,
"grad_norm": 7.125,
"learning_rate": 1.7940058422294825e-06,
"loss": 1.8596685409545899,
"step": 4350
},
{
"epoch": 0.7514326338920246,
"grad_norm": 5.75,
"learning_rate": 1.7709810900788226e-06,
"loss": 1.780243492126465,
"step": 4360
},
{
"epoch": 0.7531561032358137,
"grad_norm": 5.71875,
"learning_rate": 1.748073205841247e-06,
"loss": 1.8522743225097655,
"step": 4370
},
{
"epoch": 0.7548795725796027,
"grad_norm": 8.3125,
"learning_rate": 1.7252830186220405e-06,
"loss": 1.8165380477905273,
"step": 4380
},
{
"epoch": 0.7566030419233918,
"grad_norm": 6.125,
"learning_rate": 1.702611353266665e-06,
"loss": 1.8107898712158204,
"step": 4390
},
{
"epoch": 0.7583265112671809,
"grad_norm": 4.46875,
"learning_rate": 1.6800590303309343e-06,
"loss": 1.8114805221557617,
"step": 4400
},
{
"epoch": 0.7600499806109698,
"grad_norm": 7.15625,
"learning_rate": 1.6576268660512873e-06,
"loss": 1.8261451721191406,
"step": 4410
},
{
"epoch": 0.7617734499547589,
"grad_norm": 9.75,
"learning_rate": 1.635315672315272e-06,
"loss": 1.7968561172485351,
"step": 4420
},
{
"epoch": 0.763496919298548,
"grad_norm": 5.375,
"learning_rate": 1.613126256632136e-06,
"loss": 1.8128055572509765,
"step": 4430
},
{
"epoch": 0.765220388642337,
"grad_norm": 8.5,
"learning_rate": 1.5910594221036236e-06,
"loss": 1.8332168579101562,
"step": 4440
},
{
"epoch": 0.7669438579861261,
"grad_norm": 6.375,
"learning_rate": 1.569115967394892e-06,
"loss": 1.8408638000488282,
"step": 4450
},
{
"epoch": 0.7686673273299152,
"grad_norm": 15.8125,
"learning_rate": 1.5472966867056122e-06,
"loss": 1.8163379669189452,
"step": 4460
},
{
"epoch": 0.7703907966737041,
"grad_norm": 7.1875,
"learning_rate": 1.5256023697412242e-06,
"loss": 1.8224592208862305,
"step": 4470
},
{
"epoch": 0.7721142660174932,
"grad_norm": 5.0625,
"learning_rate": 1.5040338016843552e-06,
"loss": 1.8208709716796876,
"step": 4480
},
{
"epoch": 0.7738377353612823,
"grad_norm": 6.6875,
"learning_rate": 1.482591763166401e-06,
"loss": 1.8458805084228516,
"step": 4490
},
{
"epoch": 0.7755612047050713,
"grad_norm": 8.125,
"learning_rate": 1.461277030239271e-06,
"loss": 1.8372306823730469,
"step": 4500
},
{
"epoch": 0.7755612047050713,
"eval_loss": 1.8214198350906372,
"eval_runtime": 189.2666,
"eval_samples_per_second": 25.023,
"eval_steps_per_second": 3.128,
"step": 4500
},
{
"epoch": 0.7772846740488604,
"grad_norm": 72.0,
"learning_rate": 1.4400903743473032e-06,
"loss": 1.80096435546875,
"step": 4510
},
{
"epoch": 0.7790081433926495,
"grad_norm": 6.0,
"learning_rate": 1.4190325622993434e-06,
"loss": 1.8002546310424805,
"step": 4520
},
{
"epoch": 0.7807316127364384,
"grad_norm": 5.65625,
"learning_rate": 1.398104356240988e-06,
"loss": 1.7890960693359375,
"step": 4530
},
{
"epoch": 0.7824550820802275,
"grad_norm": 31.125,
"learning_rate": 1.3773065136270036e-06,
"loss": 1.8436212539672852,
"step": 4540
},
{
"epoch": 0.7841785514240165,
"grad_norm": 4.875,
"learning_rate": 1.3566397871939147e-06,
"loss": 1.8495201110839843,
"step": 4550
},
{
"epoch": 0.7859020207678056,
"grad_norm": 6.4375,
"learning_rate": 1.336104924932753e-06,
"loss": 1.7932083129882812,
"step": 4560
},
{
"epoch": 0.7876254901115947,
"grad_norm": 5.0,
"learning_rate": 1.3157026700619885e-06,
"loss": 1.8371917724609375,
"step": 4570
},
{
"epoch": 0.7893489594553836,
"grad_norm": 10.0,
"learning_rate": 1.2954337610006335e-06,
"loss": 1.8438575744628907,
"step": 4580
},
{
"epoch": 0.7910724287991727,
"grad_norm": 7.25,
"learning_rate": 1.275298931341511e-06,
"loss": 1.7834117889404297,
"step": 4590
},
{
"epoch": 0.7927958981429618,
"grad_norm": 6.0,
"learning_rate": 1.2552989098247092e-06,
"loss": 1.8135692596435546,
"step": 4600
},
{
"epoch": 0.7945193674867508,
"grad_norm": 21.875,
"learning_rate": 1.2354344203112035e-06,
"loss": 1.8180233001708985,
"step": 4610
},
{
"epoch": 0.7962428368305399,
"grad_norm": 5.84375,
"learning_rate": 1.2157061817566568e-06,
"loss": 1.8474626541137695,
"step": 4620
},
{
"epoch": 0.797966306174329,
"grad_norm": 36.5,
"learning_rate": 1.1961149081854006e-06,
"loss": 1.8520895004272462,
"step": 4630
},
{
"epoch": 0.7996897755181179,
"grad_norm": 5.65625,
"learning_rate": 1.1766613086645928e-06,
"loss": 1.8065855026245117,
"step": 4640
},
{
"epoch": 0.801413244861907,
"grad_norm": 34.5,
"learning_rate": 1.1573460872785503e-06,
"loss": 1.8209779739379883,
"step": 4650
},
{
"epoch": 0.8031367142056961,
"grad_norm": 8.1875,
"learning_rate": 1.1381699431032695e-06,
"loss": 1.830772590637207,
"step": 4660
},
{
"epoch": 0.8048601835494851,
"grad_norm": 7.375,
"learning_rate": 1.1191335701811285e-06,
"loss": 1.8219244003295898,
"step": 4670
},
{
"epoch": 0.8065836528932742,
"grad_norm": 4.125,
"learning_rate": 1.100237657495754e-06,
"loss": 1.8321475982666016,
"step": 4680
},
{
"epoch": 0.8083071222370632,
"grad_norm": 9.1875,
"learning_rate": 1.0814828889471047e-06,
"loss": 1.7924293518066405,
"step": 4690
},
{
"epoch": 0.8100305915808522,
"grad_norm": 7.53125,
"learning_rate": 1.062869943326697e-06,
"loss": 1.8244857788085938,
"step": 4700
},
{
"epoch": 0.8117540609246413,
"grad_norm": 6.53125,
"learning_rate": 1.0443994942930592e-06,
"loss": 1.825185775756836,
"step": 4710
},
{
"epoch": 0.8134775302684304,
"grad_norm": 7.25,
"learning_rate": 1.0260722103473314e-06,
"loss": 1.834679412841797,
"step": 4720
},
{
"epoch": 0.8152009996122194,
"grad_norm": 5.75,
"learning_rate": 1.0078887548090827e-06,
"loss": 1.8148757934570312,
"step": 4730
},
{
"epoch": 0.8169244689560085,
"grad_norm": 4.84375,
"learning_rate": 9.898497857922978e-07,
"loss": 1.8438005447387695,
"step": 4740
},
{
"epoch": 0.8186479382997975,
"grad_norm": 4.5,
"learning_rate": 9.719559561815584e-07,
"loss": 1.8407489776611328,
"step": 4750
},
{
"epoch": 0.8203714076435865,
"grad_norm": 5.625,
"learning_rate": 9.542079136084154e-07,
"loss": 1.7916162490844727,
"step": 4760
},
{
"epoch": 0.8220948769873756,
"grad_norm": 14.5,
"learning_rate": 9.36606300427948e-07,
"loss": 1.8000501632690429,
"step": 4770
},
{
"epoch": 0.8238183463311647,
"grad_norm": 12.0,
"learning_rate": 9.191517536955152e-07,
"loss": 1.8663785934448243,
"step": 4780
},
{
"epoch": 0.8255418156749537,
"grad_norm": 5.59375,
"learning_rate": 9.018449051436973e-07,
"loss": 1.8362834930419922,
"step": 4790
},
{
"epoch": 0.8272652850187427,
"grad_norm": 28.625,
"learning_rate": 8.846863811594325e-07,
"loss": 1.8352352142333985,
"step": 4800
},
{
"epoch": 0.8289887543625317,
"grad_norm": 4.4375,
"learning_rate": 8.676768027613525e-07,
"loss": 1.824945068359375,
"step": 4810
},
{
"epoch": 0.8307122237063208,
"grad_norm": 23.25,
"learning_rate": 8.508167855772886e-07,
"loss": 1.830651092529297,
"step": 4820
},
{
"epoch": 0.8324356930501099,
"grad_norm": 19.125,
"learning_rate": 8.341069398220147e-07,
"loss": 1.7930862426757812,
"step": 4830
},
{
"epoch": 0.8341591623938989,
"grad_norm": 6.625,
"learning_rate": 8.17547870275136e-07,
"loss": 1.8139684677124024,
"step": 4840
},
{
"epoch": 0.835882631737688,
"grad_norm": 6.25,
"learning_rate": 8.011401762592242e-07,
"loss": 1.8471323013305665,
"step": 4850
},
{
"epoch": 0.837606101081477,
"grad_norm": 4.3125,
"learning_rate": 7.848844516181059e-07,
"loss": 1.8401981353759767,
"step": 4860
},
{
"epoch": 0.839329570425266,
"grad_norm": 6.09375,
"learning_rate": 7.687812846953846e-07,
"loss": 1.8234878540039063,
"step": 4870
},
{
"epoch": 0.8410530397690551,
"grad_norm": 6.375,
"learning_rate": 7.528312583131387e-07,
"loss": 1.8374950408935546,
"step": 4880
},
{
"epoch": 0.8427765091128442,
"grad_norm": 6.65625,
"learning_rate": 7.370349497508294e-07,
"loss": 1.8332042694091797,
"step": 4890
},
{
"epoch": 0.8444999784566332,
"grad_norm": 5.59375,
"learning_rate": 7.213929307244072e-07,
"loss": 1.8149314880371095,
"step": 4900
},
{
"epoch": 0.8462234478004222,
"grad_norm": 6.90625,
"learning_rate": 7.059057673656195e-07,
"loss": 1.8300373077392578,
"step": 4910
},
{
"epoch": 0.8479469171442113,
"grad_norm": 4.375,
"learning_rate": 6.905740202015232e-07,
"loss": 1.8287410736083984,
"step": 4920
},
{
"epoch": 0.8496703864880003,
"grad_norm": 4.4375,
"learning_rate": 6.753982441341928e-07,
"loss": 1.8332706451416017,
"step": 4930
},
{
"epoch": 0.8513938558317894,
"grad_norm": 4.8125,
"learning_rate": 6.603789884206402e-07,
"loss": 1.8314176559448243,
"step": 4940
},
{
"epoch": 0.8531173251755785,
"grad_norm": 6.375,
"learning_rate": 6.455167966529357e-07,
"loss": 1.8223894119262696,
"step": 4950
},
{
"epoch": 0.8548407945193675,
"grad_norm": 5.25,
"learning_rate": 6.308122067385302e-07,
"loss": 1.8024940490722656,
"step": 4960
},
{
"epoch": 0.8565642638631565,
"grad_norm": 4.5625,
"learning_rate": 6.162657508807934e-07,
"loss": 1.8048280715942382,
"step": 4970
},
{
"epoch": 0.8582877332069456,
"grad_norm": 29.875,
"learning_rate": 6.01877955559742e-07,
"loss": 1.8184221267700196,
"step": 4980
},
{
"epoch": 0.8600112025507346,
"grad_norm": 5.0,
"learning_rate": 5.876493415129958e-07,
"loss": 1.8146427154541016,
"step": 4990
},
{
"epoch": 0.8617346718945237,
"grad_norm": 5.625,
"learning_rate": 5.735804237169196e-07,
"loss": 1.8287715911865234,
"step": 5000
},
{
"epoch": 0.8617346718945237,
"eval_loss": 1.82126784324646,
"eval_runtime": 189.0457,
"eval_samples_per_second": 25.052,
"eval_steps_per_second": 3.132,
"step": 5000
},
{
"epoch": 0.8634581412383128,
"grad_norm": 36.75,
"learning_rate": 5.596717113679973e-07,
"loss": 1.804646110534668,
"step": 5010
},
{
"epoch": 0.8651816105821017,
"grad_norm": 5.28125,
"learning_rate": 5.459237078643864e-07,
"loss": 1.8178810119628905,
"step": 5020
},
{
"epoch": 0.8669050799258908,
"grad_norm": 10.25,
"learning_rate": 5.323369107877175e-07,
"loss": 1.8536310195922852,
"step": 5030
},
{
"epoch": 0.8686285492696799,
"grad_norm": 5.34375,
"learning_rate": 5.189118118850661e-07,
"loss": 1.815272903442383,
"step": 5040
},
{
"epoch": 0.8703520186134689,
"grad_norm": 9.8125,
"learning_rate": 5.056488970511714e-07,
"loss": 1.8256004333496094,
"step": 5050
},
{
"epoch": 0.872075487957258,
"grad_norm": 4.3125,
"learning_rate": 4.925486463108397e-07,
"loss": 1.839909553527832,
"step": 5060
},
{
"epoch": 0.873798957301047,
"grad_norm": 4.71875,
"learning_rate": 4.796115338015739e-07,
"loss": 1.8029901504516601,
"step": 5070
},
{
"epoch": 0.875522426644836,
"grad_norm": 7.21875,
"learning_rate": 4.668380277564144e-07,
"loss": 1.8375946044921876,
"step": 5080
},
{
"epoch": 0.8772458959886251,
"grad_norm": 4.6875,
"learning_rate": 4.542285904869903e-07,
"loss": 1.8381671905517578,
"step": 5090
},
{
"epoch": 0.8789693653324141,
"grad_norm": 5.84375,
"learning_rate": 4.417836783667889e-07,
"loss": 1.8078067779541016,
"step": 5100
},
{
"epoch": 0.8806928346762032,
"grad_norm": 6.46875,
"learning_rate": 4.2950374181463636e-07,
"loss": 1.850840187072754,
"step": 5110
},
{
"epoch": 0.8824163040199923,
"grad_norm": 5.59375,
"learning_rate": 4.173892252783962e-07,
"loss": 1.8183349609375,
"step": 5120
},
{
"epoch": 0.8841397733637812,
"grad_norm": 7.375,
"learning_rate": 4.0544056721888713e-07,
"loss": 1.7968463897705078,
"step": 5130
},
{
"epoch": 0.8858632427075703,
"grad_norm": 4.5625,
"learning_rate": 3.936582000940031e-07,
"loss": 1.8175657272338868,
"step": 5140
},
{
"epoch": 0.8875867120513594,
"grad_norm": 7.25,
"learning_rate": 3.8204255034307744e-07,
"loss": 1.8261638641357423,
"step": 5150
},
{
"epoch": 0.8893101813951484,
"grad_norm": 7.5,
"learning_rate": 3.705940383714318e-07,
"loss": 1.8337011337280273,
"step": 5160
},
{
"epoch": 0.8910336507389375,
"grad_norm": 20.0,
"learning_rate": 3.593130785351745e-07,
"loss": 1.8448541641235352,
"step": 5170
},
{
"epoch": 0.8927571200827266,
"grad_norm": 13.8125,
"learning_rate": 3.4820007912619523e-07,
"loss": 1.8629817962646484,
"step": 5180
},
{
"epoch": 0.8944805894265155,
"grad_norm": 5.34375,
"learning_rate": 3.372554423573904e-07,
"loss": 1.8010009765625,
"step": 5190
},
{
"epoch": 0.8962040587703046,
"grad_norm": 4.6875,
"learning_rate": 3.2647956434810556e-07,
"loss": 1.835978126525879,
"step": 5200
},
{
"epoch": 0.8979275281140937,
"grad_norm": 8.875,
"learning_rate": 3.1587283510980003e-07,
"loss": 1.8105642318725585,
"step": 5210
},
{
"epoch": 0.8996509974578827,
"grad_norm": 4.78125,
"learning_rate": 3.0543563853192903e-07,
"loss": 1.848411750793457,
"step": 5220
},
{
"epoch": 0.9013744668016718,
"grad_norm": 4.3125,
"learning_rate": 2.951683523680504e-07,
"loss": 1.820380401611328,
"step": 5230
},
{
"epoch": 0.9030979361454609,
"grad_norm": 9.8125,
"learning_rate": 2.850713482221529e-07,
"loss": 1.8283926010131837,
"step": 5240
},
{
"epoch": 0.9048214054892498,
"grad_norm": 7.46875,
"learning_rate": 2.751449915352067e-07,
"loss": 1.825888442993164,
"step": 5250
},
{
"epoch": 0.9065448748330389,
"grad_norm": 7.09375,
"learning_rate": 2.65389641571937e-07,
"loss": 1.815310287475586,
"step": 5260
},
{
"epoch": 0.908268344176828,
"grad_norm": 8.625,
"learning_rate": 2.5580565140781943e-07,
"loss": 1.8344499588012695,
"step": 5270
},
{
"epoch": 0.909991813520617,
"grad_norm": 6.21875,
"learning_rate": 2.463933679163072e-07,
"loss": 1.8131536483764648,
"step": 5280
},
{
"epoch": 0.9117152828644061,
"grad_norm": 8.875,
"learning_rate": 2.3715313175626585e-07,
"loss": 1.8332439422607423,
"step": 5290
},
{
"epoch": 0.9134387522081951,
"grad_norm": 7.25,
"learning_rate": 2.280852773596548e-07,
"loss": 1.826437759399414,
"step": 5300
},
{
"epoch": 0.9151622215519841,
"grad_norm": 9.0,
"learning_rate": 2.1919013291941683e-07,
"loss": 1.816366958618164,
"step": 5310
},
{
"epoch": 0.9168856908957732,
"grad_norm": 4.15625,
"learning_rate": 2.1046802037760273e-07,
"loss": 1.8252386093139648,
"step": 5320
},
{
"epoch": 0.9186091602395622,
"grad_norm": 4.90625,
"learning_rate": 2.0191925541371617e-07,
"loss": 1.8262447357177733,
"step": 5330
},
{
"epoch": 0.9203326295833513,
"grad_norm": 6.875,
"learning_rate": 1.935441474332922e-07,
"loss": 1.8153100967407227,
"step": 5340
},
{
"epoch": 0.9220560989271404,
"grad_norm": 8.4375,
"learning_rate": 1.8534299955669522e-07,
"loss": 1.8286188125610352,
"step": 5350
},
{
"epoch": 0.9237795682709293,
"grad_norm": 7.78125,
"learning_rate": 1.7731610860815152e-07,
"loss": 1.809466552734375,
"step": 5360
},
{
"epoch": 0.9255030376147184,
"grad_norm": 5.0,
"learning_rate": 1.6946376510500406e-07,
"loss": 1.8004470825195313,
"step": 5370
},
{
"epoch": 0.9272265069585075,
"grad_norm": 4.59375,
"learning_rate": 1.617862532471981e-07,
"loss": 1.837824821472168,
"step": 5380
},
{
"epoch": 0.9289499763022965,
"grad_norm": 10.125,
"learning_rate": 1.5428385090699438e-07,
"loss": 1.7913677215576171,
"step": 5390
},
{
"epoch": 0.9306734456460856,
"grad_norm": 6.25,
"learning_rate": 1.469568296189172e-07,
"loss": 1.838983917236328,
"step": 5400
},
{
"epoch": 0.9323969149898746,
"grad_norm": 5.90625,
"learning_rate": 1.3980545456991678e-07,
"loss": 1.8198732376098632,
"step": 5410
},
{
"epoch": 0.9341203843336636,
"grad_norm": 65.0,
"learning_rate": 1.328299845897829e-07,
"loss": 1.8647430419921875,
"step": 5420
},
{
"epoch": 0.9358438536774527,
"grad_norm": 7.40625,
"learning_rate": 1.2603067214176756e-07,
"loss": 1.8113037109375,
"step": 5430
},
{
"epoch": 0.9375673230212418,
"grad_norm": 6.5,
"learning_rate": 1.1940776331345383e-07,
"loss": 1.8113178253173827,
"step": 5440
},
{
"epoch": 0.9392907923650308,
"grad_norm": 5.78125,
"learning_rate": 1.1296149780784471e-07,
"loss": 1.8082130432128907,
"step": 5450
},
{
"epoch": 0.9410142617088199,
"grad_norm": 4.96875,
"learning_rate": 1.0669210893469173e-07,
"loss": 1.8550947189331055,
"step": 5460
},
{
"epoch": 0.9427377310526089,
"grad_norm": 6.6875,
"learning_rate": 1.0059982360204834e-07,
"loss": 1.8423307418823243,
"step": 5470
},
{
"epoch": 0.9444612003963979,
"grad_norm": 4.5,
"learning_rate": 9.468486230805652e-08,
"loss": 1.829061508178711,
"step": 5480
},
{
"epoch": 0.946184669740187,
"grad_norm": 5.65625,
"learning_rate": 8.894743913296866e-08,
"loss": 1.8378089904785155,
"step": 5490
},
{
"epoch": 0.9479081390839761,
"grad_norm": 10.6875,
"learning_rate": 8.338776173139773e-08,
"loss": 1.8404531478881836,
"step": 5500
},
{
"epoch": 0.9479081390839761,
"eval_loss": 1.8212356567382812,
"eval_runtime": 188.6548,
"eval_samples_per_second": 25.104,
"eval_steps_per_second": 3.138,
"step": 5500
},
{
"epoch": 0.9496316084277651,
"grad_norm": 5.375,
"learning_rate": 7.800603132480322e-08,
"loss": 1.8184125900268555,
"step": 5510
},
{
"epoch": 0.9513550777715541,
"grad_norm": 6.15625,
"learning_rate": 7.280244269420588e-08,
"loss": 1.868013572692871,
"step": 5520
},
{
"epoch": 0.9530785471153432,
"grad_norm": 5.5,
"learning_rate": 6.777718417314005e-08,
"loss": 1.8153545379638671,
"step": 5530
},
{
"epoch": 0.9548020164591322,
"grad_norm": 16.125,
"learning_rate": 6.293043764083684e-08,
"loss": 1.8529928207397461,
"step": 5540
},
{
"epoch": 0.9565254858029213,
"grad_norm": 4.3125,
"learning_rate": 5.826237851564109e-08,
"loss": 1.8267868041992188,
"step": 5550
},
{
"epoch": 0.9582489551467104,
"grad_norm": 6.59375,
"learning_rate": 5.377317574866314e-08,
"loss": 1.8245101928710938,
"step": 5560
},
{
"epoch": 0.9599724244904994,
"grad_norm": 15.9375,
"learning_rate": 4.946299181766201e-08,
"loss": 1.8356136322021483,
"step": 5570
},
{
"epoch": 0.9616958938342884,
"grad_norm": 7.75,
"learning_rate": 4.5331982721167345e-08,
"loss": 1.8132728576660155,
"step": 5580
},
{
"epoch": 0.9634193631780774,
"grad_norm": 4.65625,
"learning_rate": 4.138029797283116e-08,
"loss": 1.7819122314453124,
"step": 5590
},
{
"epoch": 0.9651428325218665,
"grad_norm": 18.625,
"learning_rate": 3.760808059601939e-08,
"loss": 1.8247360229492187,
"step": 5600
},
{
"epoch": 0.9668663018656556,
"grad_norm": 5.71875,
"learning_rate": 3.4015467118631574e-08,
"loss": 1.8269477844238282,
"step": 5610
},
{
"epoch": 0.9685897712094446,
"grad_norm": 6.21875,
"learning_rate": 3.06025875681637e-08,
"loss": 1.8041257858276367,
"step": 5620
},
{
"epoch": 0.9703132405532336,
"grad_norm": 225.0,
"learning_rate": 2.736956546699754e-08,
"loss": 1.8447729110717774,
"step": 5630
},
{
"epoch": 0.9720367098970227,
"grad_norm": 4.375,
"learning_rate": 2.4316517827934204e-08,
"loss": 1.831043815612793,
"step": 5640
},
{
"epoch": 0.9737601792408117,
"grad_norm": 5.375,
"learning_rate": 2.1443555149957552e-08,
"loss": 1.8120197296142577,
"step": 5650
},
{
"epoch": 0.9754836485846008,
"grad_norm": 5.4375,
"learning_rate": 1.8750781414232923e-08,
"loss": 1.7766189575195312,
"step": 5660
},
{
"epoch": 0.9772071179283899,
"grad_norm": 14.25,
"learning_rate": 1.6238294080347382e-08,
"loss": 1.8399539947509767,
"step": 5670
},
{
"epoch": 0.9789305872721789,
"grad_norm": 7.78125,
"learning_rate": 1.3906184082779218e-08,
"loss": 1.7913579940795898,
"step": 5680
},
{
"epoch": 0.9806540566159679,
"grad_norm": 5.09375,
"learning_rate": 1.1754535827608327e-08,
"loss": 1.8301204681396483,
"step": 5690
},
{
"epoch": 0.982377525959757,
"grad_norm": 10.1875,
"learning_rate": 9.783427189462013e-09,
"loss": 1.8386709213256835,
"step": 5700
},
{
"epoch": 0.984100995303546,
"grad_norm": 8.8125,
"learning_rate": 7.992929508692793e-09,
"loss": 1.8085201263427735,
"step": 5710
},
{
"epoch": 0.9858244646473351,
"grad_norm": 5.90625,
"learning_rate": 6.383107588802673e-09,
"loss": 1.7927364349365233,
"step": 5720
},
{
"epoch": 0.9875479339911242,
"grad_norm": 19.0,
"learning_rate": 4.95401969409115e-09,
"loss": 1.8080327987670899,
"step": 5730
},
{
"epoch": 0.9892714033349131,
"grad_norm": 15.0,
"learning_rate": 3.70571754755078e-09,
"loss": 1.832293701171875,
"step": 5740
},
{
"epoch": 0.9909948726787022,
"grad_norm": 4.34375,
"learning_rate": 2.6382463289931215e-09,
"loss": 1.833485221862793,
"step": 5750
},
{
"epoch": 0.9927183420224913,
"grad_norm": 5.625,
"learning_rate": 1.7516446734150427e-09,
"loss": 1.8248113632202148,
"step": 5760
},
{
"epoch": 0.9944418113662803,
"grad_norm": 6.25,
"learning_rate": 1.0459446695981756e-09,
"loss": 1.8026580810546875,
"step": 5770
},
{
"epoch": 0.9961652807100694,
"grad_norm": 5.5625,
"learning_rate": 5.211718589498427e-10,
"loss": 1.8091909408569335,
"step": 5780
},
{
"epoch": 0.9978887500538585,
"grad_norm": 4.3125,
"learning_rate": 1.7734523457824116e-10,
"loss": 1.8309267044067383,
"step": 5790
},
{
"epoch": 0.9996122193976474,
"grad_norm": 9.375,
"learning_rate": 1.4477240602439601e-11,
"loss": 1.8328081130981446,
"step": 5800
},
{
"epoch": 1.0,
"eval_loss": 1.8212566375732422,
"eval_runtime": 189.0392,
"eval_samples_per_second": 25.053,
"eval_steps_per_second": 3.132,
"step": 5803
},
{
"epoch": 1.0,
"step": 5803,
"total_flos": 2.9588344254445286e+18,
"train_loss": 1.8961432821972912,
"train_runtime": 37256.7001,
"train_samples_per_second": 6.229,
"train_steps_per_second": 0.156
}
],
"logging_steps": 10,
"max_steps": 5803,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 2.9588344254445286e+18,
"train_batch_size": 10,
"trial_name": null,
"trial_params": null
}