GIST-small-format / trainer_state.json
agentlans's picture
Upload 11 files
ed0aabd verified
Raw History Blame Contribute Delete
53 kB
{
"best_global_step": 136686,
"best_metric": 0.8518024169356405,
"best_model_checkpoint": "./GIST-small-format/checkpoint-136686",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 136686,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010974057328475484,
"grad_norm": 6.6852498054504395,
"learning_rate": 4.981746484643636e-05,
"loss": 1.731101806640625,
"step": 500
},
{
"epoch": 0.021948114656950967,
"grad_norm": 3.2897143363952637,
"learning_rate": 4.963456389096176e-05,
"loss": 1.01430029296875,
"step": 1000
},
{
"epoch": 0.03292217198542645,
"grad_norm": 8.402548789978027,
"learning_rate": 4.945166293548718e-05,
"loss": 0.881885498046875,
"step": 1500
},
{
"epoch": 0.043896229313901934,
"grad_norm": 6.612447261810303,
"learning_rate": 4.9268761980012585e-05,
"loss": 0.69460986328125,
"step": 2000
},
{
"epoch": 0.05487028664237742,
"grad_norm": 12.039176940917969,
"learning_rate": 4.908586102453799e-05,
"loss": 0.6732612915039062,
"step": 2500
},
{
"epoch": 0.0658443439708529,
"grad_norm": 2.494370937347412,
"learning_rate": 4.89029600690634e-05,
"loss": 0.6471351318359375,
"step": 3000
},
{
"epoch": 0.07681840129932839,
"grad_norm": 21.64371109008789,
"learning_rate": 4.8720059113588815e-05,
"loss": 0.582156494140625,
"step": 3500
},
{
"epoch": 0.08779245862780387,
"grad_norm": 14.828876495361328,
"learning_rate": 4.853715815811422e-05,
"loss": 0.5588424072265625,
"step": 4000
},
{
"epoch": 0.09876651595627936,
"grad_norm": 1.5009714365005493,
"learning_rate": 4.835425720263963e-05,
"loss": 0.5702305908203125,
"step": 4500
},
{
"epoch": 0.10974057328475484,
"grad_norm": 34.568260192871094,
"learning_rate": 4.817135624716504e-05,
"loss": 0.5573681640625,
"step": 5000
},
{
"epoch": 0.12071463061323032,
"grad_norm": 12.301100730895996,
"learning_rate": 4.7988455291690446e-05,
"loss": 0.5319334106445313,
"step": 5500
},
{
"epoch": 0.1316886879417058,
"grad_norm": 6.479952335357666,
"learning_rate": 4.780555433621585e-05,
"loss": 0.546407958984375,
"step": 6000
},
{
"epoch": 0.1426627452701813,
"grad_norm": 30.429779052734375,
"learning_rate": 4.762265338074126e-05,
"loss": 0.5369138793945313,
"step": 6500
},
{
"epoch": 0.15363680259865678,
"grad_norm": 9.562945365905762,
"learning_rate": 4.743975242526667e-05,
"loss": 0.4968977355957031,
"step": 7000
},
{
"epoch": 0.16461085992713226,
"grad_norm": 6.738670825958252,
"learning_rate": 4.7256851469792076e-05,
"loss": 0.5199419555664062,
"step": 7500
},
{
"epoch": 0.17558491725560774,
"grad_norm": 20.670921325683594,
"learning_rate": 4.707395051431749e-05,
"loss": 0.48726055908203125,
"step": 8000
},
{
"epoch": 0.18655897458408321,
"grad_norm": 28.577016830444336,
"learning_rate": 4.68910495588429e-05,
"loss": 0.48510040283203126,
"step": 8500
},
{
"epoch": 0.19753303191255872,
"grad_norm": 22.50349235534668,
"learning_rate": 4.6708148603368306e-05,
"loss": 0.49556842041015625,
"step": 9000
},
{
"epoch": 0.2085070892410342,
"grad_norm": 0.931214451789856,
"learning_rate": 4.6525247647893714e-05,
"loss": 0.45953961181640623,
"step": 9500
},
{
"epoch": 0.21948114656950968,
"grad_norm": 23.271512985229492,
"learning_rate": 4.634234669241913e-05,
"loss": 0.4892506408691406,
"step": 10000
},
{
"epoch": 0.23045520389798516,
"grad_norm": 16.353809356689453,
"learning_rate": 4.6159445736944536e-05,
"loss": 0.4712514953613281,
"step": 10500
},
{
"epoch": 0.24142926122646063,
"grad_norm": 6.07758903503418,
"learning_rate": 4.597654478146994e-05,
"loss": 0.4706602783203125,
"step": 11000
},
{
"epoch": 0.25240331855493614,
"grad_norm": 10.723750114440918,
"learning_rate": 4.5793643825995345e-05,
"loss": 0.4377469177246094,
"step": 11500
},
{
"epoch": 0.2633773758834116,
"grad_norm": 8.667707443237305,
"learning_rate": 4.561074287052076e-05,
"loss": 0.49056134033203125,
"step": 12000
},
{
"epoch": 0.2743514332118871,
"grad_norm": 14.63868522644043,
"learning_rate": 4.542784191504617e-05,
"loss": 0.4677280883789062,
"step": 12500
},
{
"epoch": 0.2853254905403626,
"grad_norm": 28.209775924682617,
"learning_rate": 4.5244940959571575e-05,
"loss": 0.47199853515625,
"step": 13000
},
{
"epoch": 0.29629954786883805,
"grad_norm": 16.671207427978516,
"learning_rate": 4.506204000409698e-05,
"loss": 0.47259246826171875,
"step": 13500
},
{
"epoch": 0.30727360519731356,
"grad_norm": 7.109496116638184,
"learning_rate": 4.487913904862239e-05,
"loss": 0.470185791015625,
"step": 14000
},
{
"epoch": 0.318247662525789,
"grad_norm": 4.374630451202393,
"learning_rate": 4.4696238093147805e-05,
"loss": 0.45671673583984373,
"step": 14500
},
{
"epoch": 0.3292217198542645,
"grad_norm": 61.96080780029297,
"learning_rate": 4.451333713767321e-05,
"loss": 0.433604248046875,
"step": 15000
},
{
"epoch": 0.34019577718274,
"grad_norm": 21.4468936920166,
"learning_rate": 4.433043618219862e-05,
"loss": 0.4195879516601563,
"step": 15500
},
{
"epoch": 0.3511698345112155,
"grad_norm": 12.094574928283691,
"learning_rate": 4.414753522672402e-05,
"loss": 0.47797442626953124,
"step": 16000
},
{
"epoch": 0.362143891839691,
"grad_norm": 0.06602894514799118,
"learning_rate": 4.3964634271249435e-05,
"loss": 0.4752947692871094,
"step": 16500
},
{
"epoch": 0.37311794916816643,
"grad_norm": 24.168350219726562,
"learning_rate": 4.378173331577484e-05,
"loss": 0.4525231628417969,
"step": 17000
},
{
"epoch": 0.38409200649664194,
"grad_norm": 5.945094585418701,
"learning_rate": 4.359883236030025e-05,
"loss": 0.42800213623046873,
"step": 17500
},
{
"epoch": 0.39506606382511744,
"grad_norm": 3.3805999755859375,
"learning_rate": 4.341593140482566e-05,
"loss": 0.4128626708984375,
"step": 18000
},
{
"epoch": 0.4060401211535929,
"grad_norm": 0.3303009271621704,
"learning_rate": 4.3233030449351066e-05,
"loss": 0.45289547729492186,
"step": 18500
},
{
"epoch": 0.4170141784820684,
"grad_norm": 7.178033351898193,
"learning_rate": 4.305012949387648e-05,
"loss": 0.4623618774414063,
"step": 19000
},
{
"epoch": 0.42798823581054385,
"grad_norm": 0.13193656504154205,
"learning_rate": 4.286722853840189e-05,
"loss": 0.42712686157226565,
"step": 19500
},
{
"epoch": 0.43896229313901935,
"grad_norm": 3.611271858215332,
"learning_rate": 4.2684327582927296e-05,
"loss": 0.41502728271484374,
"step": 20000
},
{
"epoch": 0.44993635046749486,
"grad_norm": 22.556659698486328,
"learning_rate": 4.2501426627452704e-05,
"loss": 0.4233431396484375,
"step": 20500
},
{
"epoch": 0.4609104077959703,
"grad_norm": 19.0096378326416,
"learning_rate": 4.231852567197811e-05,
"loss": 0.4352963256835938,
"step": 21000
},
{
"epoch": 0.4718844651244458,
"grad_norm": 12.138071060180664,
"learning_rate": 4.213562471650352e-05,
"loss": 0.433427490234375,
"step": 21500
},
{
"epoch": 0.48285852245292127,
"grad_norm": 2.0555145740509033,
"learning_rate": 4.195272376102893e-05,
"loss": 0.4031333923339844,
"step": 22000
},
{
"epoch": 0.4938325797813968,
"grad_norm": 2.4884192943573,
"learning_rate": 4.1769822805554335e-05,
"loss": 0.4010719604492187,
"step": 22500
},
{
"epoch": 0.5048066371098723,
"grad_norm": 0.3784475028514862,
"learning_rate": 4.158692185007975e-05,
"loss": 0.4136856689453125,
"step": 23000
},
{
"epoch": 0.5157806944383477,
"grad_norm": 20.747249603271484,
"learning_rate": 4.140402089460516e-05,
"loss": 0.4478377075195312,
"step": 23500
},
{
"epoch": 0.5267547517668232,
"grad_norm": 30.383005142211914,
"learning_rate": 4.1221119939130565e-05,
"loss": 0.41568099975585937,
"step": 24000
},
{
"epoch": 0.5377288090952987,
"grad_norm": 16.23149299621582,
"learning_rate": 4.103821898365597e-05,
"loss": 0.4275780944824219,
"step": 24500
},
{
"epoch": 0.5487028664237742,
"grad_norm": 0.1475469321012497,
"learning_rate": 4.085531802818138e-05,
"loss": 0.4123694458007813,
"step": 25000
},
{
"epoch": 0.5596769237522496,
"grad_norm": 2.036740779876709,
"learning_rate": 4.0672417072706794e-05,
"loss": 0.40654916381835937,
"step": 25500
},
{
"epoch": 0.5706509810807252,
"grad_norm": 1.523879051208496,
"learning_rate": 4.0489516117232195e-05,
"loss": 0.433327392578125,
"step": 26000
},
{
"epoch": 0.5816250384092007,
"grad_norm": 0.9519908428192139,
"learning_rate": 4.03066151617576e-05,
"loss": 0.409821533203125,
"step": 26500
},
{
"epoch": 0.5925990957376761,
"grad_norm": 7.078254699707031,
"learning_rate": 4.012371420628301e-05,
"loss": 0.4090614318847656,
"step": 27000
},
{
"epoch": 0.6035731530661517,
"grad_norm": 8.405106544494629,
"learning_rate": 3.9940813250808425e-05,
"loss": 0.4346309204101563,
"step": 27500
},
{
"epoch": 0.6145472103946271,
"grad_norm": 10.549320220947266,
"learning_rate": 3.975791229533383e-05,
"loss": 0.40631097412109374,
"step": 28000
},
{
"epoch": 0.6255212677231026,
"grad_norm": 7.929631233215332,
"learning_rate": 3.957501133985924e-05,
"loss": 0.41491552734375,
"step": 28500
},
{
"epoch": 0.636495325051578,
"grad_norm": 27.06610870361328,
"learning_rate": 3.939211038438465e-05,
"loss": 0.4144559326171875,
"step": 29000
},
{
"epoch": 0.6474693823800536,
"grad_norm": 20.29384422302246,
"learning_rate": 3.920920942891006e-05,
"loss": 0.39838357543945313,
"step": 29500
},
{
"epoch": 0.658443439708529,
"grad_norm": 15.49613094329834,
"learning_rate": 3.902630847343547e-05,
"loss": 0.41126773071289063,
"step": 30000
},
{
"epoch": 0.6694174970370045,
"grad_norm": 13.434142112731934,
"learning_rate": 3.884340751796088e-05,
"loss": 0.41314010620117186,
"step": 30500
},
{
"epoch": 0.68039155436548,
"grad_norm": 23.377010345458984,
"learning_rate": 3.866050656248628e-05,
"loss": 0.4113868103027344,
"step": 31000
},
{
"epoch": 0.6913656116939555,
"grad_norm": 4.771722793579102,
"learning_rate": 3.8477605607011694e-05,
"loss": 0.39154055786132813,
"step": 31500
},
{
"epoch": 0.702339669022431,
"grad_norm": 26.069446563720703,
"learning_rate": 3.82947046515371e-05,
"loss": 0.41785919189453125,
"step": 32000
},
{
"epoch": 0.7133137263509065,
"grad_norm": 29.206588745117188,
"learning_rate": 3.811180369606251e-05,
"loss": 0.3831887512207031,
"step": 32500
},
{
"epoch": 0.724287783679382,
"grad_norm": 14.96133804321289,
"learning_rate": 3.792890274058792e-05,
"loss": 0.3826472473144531,
"step": 33000
},
{
"epoch": 0.7352618410078574,
"grad_norm": 15.803548812866211,
"learning_rate": 3.7746001785113325e-05,
"loss": 0.3715686950683594,
"step": 33500
},
{
"epoch": 0.7462358983363329,
"grad_norm": 8.521240234375,
"learning_rate": 3.756310082963874e-05,
"loss": 0.3826586608886719,
"step": 34000
},
{
"epoch": 0.7572099556648084,
"grad_norm": 12.95479679107666,
"learning_rate": 3.738019987416415e-05,
"loss": 0.38898123168945314,
"step": 34500
},
{
"epoch": 0.7681840129932839,
"grad_norm": 26.654850006103516,
"learning_rate": 3.7197298918689554e-05,
"loss": 0.4050979919433594,
"step": 35000
},
{
"epoch": 0.7791580703217593,
"grad_norm": 32.3937873840332,
"learning_rate": 3.701439796321496e-05,
"loss": 0.40102090454101563,
"step": 35500
},
{
"epoch": 0.7901321276502349,
"grad_norm": 10.174785614013672,
"learning_rate": 3.683149700774037e-05,
"loss": 0.3961770935058594,
"step": 36000
},
{
"epoch": 0.8011061849787103,
"grad_norm": 16.819910049438477,
"learning_rate": 3.664859605226578e-05,
"loss": 0.365343994140625,
"step": 36500
},
{
"epoch": 0.8120802423071858,
"grad_norm": 22.253021240234375,
"learning_rate": 3.6465695096791185e-05,
"loss": 0.4085382385253906,
"step": 37000
},
{
"epoch": 0.8230542996356613,
"grad_norm": 0.653167188167572,
"learning_rate": 3.628279414131659e-05,
"loss": 0.3887478942871094,
"step": 37500
},
{
"epoch": 0.8340283569641368,
"grad_norm": 7.46025276184082,
"learning_rate": 3.609989318584201e-05,
"loss": 0.42551852416992186,
"step": 38000
},
{
"epoch": 0.8450024142926122,
"grad_norm": 3.8886020183563232,
"learning_rate": 3.5916992230367415e-05,
"loss": 0.376479248046875,
"step": 38500
},
{
"epoch": 0.8559764716210877,
"grad_norm": 23.658897399902344,
"learning_rate": 3.573409127489282e-05,
"loss": 0.3964391174316406,
"step": 39000
},
{
"epoch": 0.8669505289495633,
"grad_norm": 56.36935043334961,
"learning_rate": 3.555119031941823e-05,
"loss": 0.3848704833984375,
"step": 39500
},
{
"epoch": 0.8779245862780387,
"grad_norm": 15.337593078613281,
"learning_rate": 3.536828936394364e-05,
"loss": 0.3928073425292969,
"step": 40000
},
{
"epoch": 0.8888986436065142,
"grad_norm": 16.32798957824707,
"learning_rate": 3.518538840846905e-05,
"loss": 0.38851931762695313,
"step": 40500
},
{
"epoch": 0.8998727009349897,
"grad_norm": 1.66266667842865,
"learning_rate": 3.5002487452994454e-05,
"loss": 0.3637700500488281,
"step": 41000
},
{
"epoch": 0.9108467582634652,
"grad_norm": 26.03211212158203,
"learning_rate": 3.481958649751986e-05,
"loss": 0.37883843994140626,
"step": 41500
},
{
"epoch": 0.9218208155919406,
"grad_norm": 0.10503211617469788,
"learning_rate": 3.463668554204527e-05,
"loss": 0.384486083984375,
"step": 42000
},
{
"epoch": 0.9327948729204162,
"grad_norm": 0.09833603352308273,
"learning_rate": 3.4453784586570684e-05,
"loss": 0.39695626831054687,
"step": 42500
},
{
"epoch": 0.9437689302488916,
"grad_norm": 13.514938354492188,
"learning_rate": 3.427088363109609e-05,
"loss": 0.3914007568359375,
"step": 43000
},
{
"epoch": 0.9547429875773671,
"grad_norm": 4.098175525665283,
"learning_rate": 3.40879826756215e-05,
"loss": 0.38088681030273436,
"step": 43500
},
{
"epoch": 0.9657170449058425,
"grad_norm": 14.520209312438965,
"learning_rate": 3.390508172014691e-05,
"loss": 0.3855673828125,
"step": 44000
},
{
"epoch": 0.9766911022343181,
"grad_norm": 35.712867736816406,
"learning_rate": 3.3722180764672314e-05,
"loss": 0.361778076171875,
"step": 44500
},
{
"epoch": 0.9876651595627935,
"grad_norm": 10.093748092651367,
"learning_rate": 3.353927980919773e-05,
"loss": 0.37317227172851564,
"step": 45000
},
{
"epoch": 0.998639216891269,
"grad_norm": 4.401282787322998,
"learning_rate": 3.3356378853723137e-05,
"loss": 0.35951104736328127,
"step": 45500
},
{
"epoch": 1.0,
"eval_f1": 0.7906041351717196,
"eval_loss": 0.3376215994358063,
"eval_runtime": 21.7159,
"eval_samples_per_second": 1864.991,
"eval_steps_per_second": 233.147,
"step": 45562
},
{
"epoch": 1.0096132742197446,
"grad_norm": 0.07860906422138214,
"learning_rate": 3.317347789824854e-05,
"loss": 0.29326309204101564,
"step": 46000
},
{
"epoch": 1.02058733154822,
"grad_norm": 39.632415771484375,
"learning_rate": 3.299057694277395e-05,
"loss": 0.28309921264648436,
"step": 46500
},
{
"epoch": 1.0315613888766955,
"grad_norm": 1.5844589471817017,
"learning_rate": 3.280767598729936e-05,
"loss": 0.2768072509765625,
"step": 47000
},
{
"epoch": 1.042535446205171,
"grad_norm": 0.07393167912960052,
"learning_rate": 3.262477503182477e-05,
"loss": 0.29472137451171876,
"step": 47500
},
{
"epoch": 1.0535095035336464,
"grad_norm": 0.903986394405365,
"learning_rate": 3.2441874076350175e-05,
"loss": 0.30162600708007814,
"step": 48000
},
{
"epoch": 1.064483560862122,
"grad_norm": 12.462333679199219,
"learning_rate": 3.225897312087558e-05,
"loss": 0.28875408935546876,
"step": 48500
},
{
"epoch": 1.0754576181905975,
"grad_norm": 26.5993595123291,
"learning_rate": 3.2076072165401e-05,
"loss": 0.26983624267578127,
"step": 49000
},
{
"epoch": 1.0864316755190728,
"grad_norm": 4.48448371887207,
"learning_rate": 3.1893171209926405e-05,
"loss": 0.3015690612792969,
"step": 49500
},
{
"epoch": 1.0974057328475484,
"grad_norm": 1.3335434198379517,
"learning_rate": 3.171027025445181e-05,
"loss": 0.27986233520507814,
"step": 50000
},
{
"epoch": 1.108379790176024,
"grad_norm": 55.16224670410156,
"learning_rate": 3.152736929897722e-05,
"loss": 0.30360482788085935,
"step": 50500
},
{
"epoch": 1.1193538475044993,
"grad_norm": 0.1195051297545433,
"learning_rate": 3.134446834350263e-05,
"loss": 0.29728253173828123,
"step": 51000
},
{
"epoch": 1.1303279048329749,
"grad_norm": 15.035134315490723,
"learning_rate": 3.1161567388028036e-05,
"loss": 0.293227294921875,
"step": 51500
},
{
"epoch": 1.1413019621614504,
"grad_norm": 7.07342529296875,
"learning_rate": 3.0978666432553443e-05,
"loss": 0.2788831176757812,
"step": 52000
},
{
"epoch": 1.1522760194899258,
"grad_norm": 2.034162998199463,
"learning_rate": 3.079576547707885e-05,
"loss": 0.3180224609375,
"step": 52500
},
{
"epoch": 1.1632500768184013,
"grad_norm": 3.3663501739501953,
"learning_rate": 3.061286452160426e-05,
"loss": 0.2868128967285156,
"step": 53000
},
{
"epoch": 1.1742241341468769,
"grad_norm": 2.8967697620391846,
"learning_rate": 3.042996356612967e-05,
"loss": 0.30618685913085936,
"step": 53500
},
{
"epoch": 1.1851981914753522,
"grad_norm": 10.053667068481445,
"learning_rate": 3.024706261065508e-05,
"loss": 0.30812335205078123,
"step": 54000
},
{
"epoch": 1.1961722488038278,
"grad_norm": 4.651602268218994,
"learning_rate": 3.006416165518049e-05,
"loss": 0.2754173278808594,
"step": 54500
},
{
"epoch": 1.2071463061323033,
"grad_norm": 14.591957092285156,
"learning_rate": 2.98812606997059e-05,
"loss": 0.3053521728515625,
"step": 55000
},
{
"epoch": 1.2181203634607787,
"grad_norm": 4.575090408325195,
"learning_rate": 2.9698359744231308e-05,
"loss": 0.29722467041015627,
"step": 55500
},
{
"epoch": 1.2290944207892542,
"grad_norm": 0.7045038342475891,
"learning_rate": 2.9515458788756712e-05,
"loss": 0.30476104736328125,
"step": 56000
},
{
"epoch": 1.2400684781177298,
"grad_norm": 8.57973575592041,
"learning_rate": 2.933255783328212e-05,
"loss": 0.2778677062988281,
"step": 56500
},
{
"epoch": 1.2510425354462051,
"grad_norm": 27.191518783569336,
"learning_rate": 2.914965687780753e-05,
"loss": 0.2781588134765625,
"step": 57000
},
{
"epoch": 1.2620165927746807,
"grad_norm": 15.524397850036621,
"learning_rate": 2.896675592233294e-05,
"loss": 0.31154220581054687,
"step": 57500
},
{
"epoch": 1.2729906501031563,
"grad_norm": 0.02379167452454567,
"learning_rate": 2.878385496685835e-05,
"loss": 0.27608938598632815,
"step": 58000
},
{
"epoch": 1.2839647074316316,
"grad_norm": 6.567012310028076,
"learning_rate": 2.8600954011383757e-05,
"loss": 0.28701922607421876,
"step": 58500
},
{
"epoch": 1.2949387647601072,
"grad_norm": 6.408507823944092,
"learning_rate": 2.8418053055909165e-05,
"loss": 0.29671533203125,
"step": 59000
},
{
"epoch": 1.3059128220885827,
"grad_norm": 4.476773262023926,
"learning_rate": 2.8235152100434576e-05,
"loss": 0.2844156494140625,
"step": 59500
},
{
"epoch": 1.316886879417058,
"grad_norm": 0.4284241795539856,
"learning_rate": 2.8052251144959984e-05,
"loss": 0.28753970336914064,
"step": 60000
},
{
"epoch": 1.3278609367455336,
"grad_norm": 45.82956314086914,
"learning_rate": 2.7869350189485395e-05,
"loss": 0.2997920227050781,
"step": 60500
},
{
"epoch": 1.338834994074009,
"grad_norm": 5.1805830001831055,
"learning_rate": 2.7686449234010796e-05,
"loss": 0.2731007995605469,
"step": 61000
},
{
"epoch": 1.3498090514024845,
"grad_norm": 44.71467971801758,
"learning_rate": 2.7503548278536207e-05,
"loss": 0.29412890625,
"step": 61500
},
{
"epoch": 1.36078310873096,
"grad_norm": 0.03455616533756256,
"learning_rate": 2.7320647323061614e-05,
"loss": 0.28992022705078124,
"step": 62000
},
{
"epoch": 1.3717571660594354,
"grad_norm": 0.10311322659254074,
"learning_rate": 2.7137746367587026e-05,
"loss": 0.304996337890625,
"step": 62500
},
{
"epoch": 1.382731223387911,
"grad_norm": 16.59219741821289,
"learning_rate": 2.6954845412112433e-05,
"loss": 0.29500704956054685,
"step": 63000
},
{
"epoch": 1.3937052807163863,
"grad_norm": 0.035255905240774155,
"learning_rate": 2.6771944456637844e-05,
"loss": 0.2860797119140625,
"step": 63500
},
{
"epoch": 1.404679338044862,
"grad_norm": 7.428912162780762,
"learning_rate": 2.6589043501163252e-05,
"loss": 0.2652564697265625,
"step": 64000
},
{
"epoch": 1.4156533953733375,
"grad_norm": 38.300662994384766,
"learning_rate": 2.640614254568866e-05,
"loss": 0.27488351440429687,
"step": 64500
},
{
"epoch": 1.4266274527018128,
"grad_norm": 34.766117095947266,
"learning_rate": 2.622324159021407e-05,
"loss": 0.2906384582519531,
"step": 65000
},
{
"epoch": 1.4376015100302884,
"grad_norm": 29.75716781616211,
"learning_rate": 2.604034063473948e-05,
"loss": 0.2712423400878906,
"step": 65500
},
{
"epoch": 1.448575567358764,
"grad_norm": 0.031717050820589066,
"learning_rate": 2.5857439679264883e-05,
"loss": 0.3094512634277344,
"step": 66000
},
{
"epoch": 1.4595496246872393,
"grad_norm": 17.38152503967285,
"learning_rate": 2.5674538723790294e-05,
"loss": 0.3181193542480469,
"step": 66500
},
{
"epoch": 1.4705236820157148,
"grad_norm": 27.521625518798828,
"learning_rate": 2.54916377683157e-05,
"loss": 0.2543564910888672,
"step": 67000
},
{
"epoch": 1.4814977393441904,
"grad_norm": 0.038084983825683594,
"learning_rate": 2.530873681284111e-05,
"loss": 0.25035408020019534,
"step": 67500
},
{
"epoch": 1.4924717966726657,
"grad_norm": 21.655553817749023,
"learning_rate": 2.512583585736652e-05,
"loss": 0.30128500366210936,
"step": 68000
},
{
"epoch": 1.5034458540011413,
"grad_norm": 0.062355488538742065,
"learning_rate": 2.4942934901891928e-05,
"loss": 0.2950963745117188,
"step": 68500
},
{
"epoch": 1.5144199113296168,
"grad_norm": 9.434773445129395,
"learning_rate": 2.476003394641734e-05,
"loss": 0.2821864318847656,
"step": 69000
},
{
"epoch": 1.5253939686580922,
"grad_norm": 0.027533777058124542,
"learning_rate": 2.4577132990942747e-05,
"loss": 0.24817718505859376,
"step": 69500
},
{
"epoch": 1.5363680259865677,
"grad_norm": 17.45857810974121,
"learning_rate": 2.4394232035468155e-05,
"loss": 0.2706839294433594,
"step": 70000
},
{
"epoch": 1.5473420833150433,
"grad_norm": 0.7203682065010071,
"learning_rate": 2.4211331079993562e-05,
"loss": 0.26013385009765627,
"step": 70500
},
{
"epoch": 1.5583161406435186,
"grad_norm": 20.325897216796875,
"learning_rate": 2.4028430124518973e-05,
"loss": 0.3072607421875,
"step": 71000
},
{
"epoch": 1.5692901979719942,
"grad_norm": 0.8252955079078674,
"learning_rate": 2.384552916904438e-05,
"loss": 0.28147393798828124,
"step": 71500
},
{
"epoch": 1.5802642553004698,
"grad_norm": 0.5657853484153748,
"learning_rate": 2.366262821356979e-05,
"loss": 0.25868719482421876,
"step": 72000
},
{
"epoch": 1.591238312628945,
"grad_norm": 0.08703117072582245,
"learning_rate": 2.3479727258095197e-05,
"loss": 0.28247900390625,
"step": 72500
},
{
"epoch": 1.6022123699574207,
"grad_norm": 29.79605484008789,
"learning_rate": 2.3296826302620604e-05,
"loss": 0.29211328125,
"step": 73000
},
{
"epoch": 1.6131864272858962,
"grad_norm": 0.18891900777816772,
"learning_rate": 2.3113925347146015e-05,
"loss": 0.2774709777832031,
"step": 73500
},
{
"epoch": 1.6241604846143716,
"grad_norm": 0.024532776325941086,
"learning_rate": 2.2931024391671423e-05,
"loss": 0.26110531616210936,
"step": 74000
},
{
"epoch": 1.6351345419428471,
"grad_norm": 23.57233428955078,
"learning_rate": 2.274812343619683e-05,
"loss": 0.2656497802734375,
"step": 74500
},
{
"epoch": 1.6461085992713227,
"grad_norm": 5.525993347167969,
"learning_rate": 2.256522248072224e-05,
"loss": 0.27565005493164063,
"step": 75000
},
{
"epoch": 1.657082656599798,
"grad_norm": 31.11590576171875,
"learning_rate": 2.238232152524765e-05,
"loss": 0.257364013671875,
"step": 75500
},
{
"epoch": 1.6680567139282736,
"grad_norm": 24.173105239868164,
"learning_rate": 2.2199420569773057e-05,
"loss": 0.28741323852539064,
"step": 76000
},
{
"epoch": 1.6790307712567492,
"grad_norm": 0.019840441644191742,
"learning_rate": 2.201651961429847e-05,
"loss": 0.2506680450439453,
"step": 76500
},
{
"epoch": 1.6900048285852245,
"grad_norm": 32.793251037597656,
"learning_rate": 2.1833618658823873e-05,
"loss": 0.2620893249511719,
"step": 77000
},
{
"epoch": 1.7009788859137,
"grad_norm": 50.69339370727539,
"learning_rate": 2.1650717703349284e-05,
"loss": 0.2703638305664062,
"step": 77500
},
{
"epoch": 1.7119529432421756,
"grad_norm": 40.141910552978516,
"learning_rate": 2.146781674787469e-05,
"loss": 0.27476327514648435,
"step": 78000
},
{
"epoch": 1.722927000570651,
"grad_norm": 0.18374653160572052,
"learning_rate": 2.12849157924001e-05,
"loss": 0.2705036926269531,
"step": 78500
},
{
"epoch": 1.7339010578991265,
"grad_norm": 46.508514404296875,
"learning_rate": 2.110201483692551e-05,
"loss": 0.3062447509765625,
"step": 79000
},
{
"epoch": 1.744875115227602,
"grad_norm": 29.72620964050293,
"learning_rate": 2.0919113881450918e-05,
"loss": 0.29800909423828126,
"step": 79500
},
{
"epoch": 1.7558491725560774,
"grad_norm": 10.616799354553223,
"learning_rate": 2.0736212925976326e-05,
"loss": 0.2787916259765625,
"step": 80000
},
{
"epoch": 1.7668232298845528,
"grad_norm": 16.61284637451172,
"learning_rate": 2.0553311970501733e-05,
"loss": 0.25415122985839844,
"step": 80500
},
{
"epoch": 1.7777972872130285,
"grad_norm": 5.203902244567871,
"learning_rate": 2.0370411015027145e-05,
"loss": 0.2742305297851563,
"step": 81000
},
{
"epoch": 1.7887713445415039,
"grad_norm": 17.70701026916504,
"learning_rate": 2.0187510059552552e-05,
"loss": 0.2559151611328125,
"step": 81500
},
{
"epoch": 1.7997454018699792,
"grad_norm": 6.252378940582275,
"learning_rate": 2.000460910407796e-05,
"loss": 0.28050296020507814,
"step": 82000
},
{
"epoch": 1.810719459198455,
"grad_norm": 31.440832138061523,
"learning_rate": 1.9821708148603368e-05,
"loss": 0.2572430419921875,
"step": 82500
},
{
"epoch": 1.8216935165269303,
"grad_norm": 16.332443237304688,
"learning_rate": 1.963880719312878e-05,
"loss": 0.2700733642578125,
"step": 83000
},
{
"epoch": 1.8326675738554057,
"grad_norm": 0.33748501539230347,
"learning_rate": 1.9455906237654186e-05,
"loss": 0.2636079711914063,
"step": 83500
},
{
"epoch": 1.8436416311838815,
"grad_norm": 0.13300059735774994,
"learning_rate": 1.9273005282179598e-05,
"loss": 0.2723955078125,
"step": 84000
},
{
"epoch": 1.8546156885123568,
"grad_norm": 28.147356033325195,
"learning_rate": 1.9090104326705002e-05,
"loss": 0.26517648315429687,
"step": 84500
},
{
"epoch": 1.8655897458408321,
"grad_norm": 17.65765953063965,
"learning_rate": 1.8907203371230413e-05,
"loss": 0.2603927001953125,
"step": 85000
},
{
"epoch": 1.8765638031693077,
"grad_norm": 40.015869140625,
"learning_rate": 1.872430241575582e-05,
"loss": 0.2619692993164062,
"step": 85500
},
{
"epoch": 1.8875378604977833,
"grad_norm": 12.848860740661621,
"learning_rate": 1.854140146028123e-05,
"loss": 0.25935647583007815,
"step": 86000
},
{
"epoch": 1.8985119178262586,
"grad_norm": 0.14966364204883575,
"learning_rate": 1.835850050480664e-05,
"loss": 0.2609214782714844,
"step": 86500
},
{
"epoch": 1.9094859751547342,
"grad_norm": 0.24382130801677704,
"learning_rate": 1.8175599549332044e-05,
"loss": 0.27692413330078125,
"step": 87000
},
{
"epoch": 1.9204600324832097,
"grad_norm": 33.56360626220703,
"learning_rate": 1.7992698593857455e-05,
"loss": 0.2803267211914062,
"step": 87500
},
{
"epoch": 1.931434089811685,
"grad_norm": 0.04589025303721428,
"learning_rate": 1.7809797638382863e-05,
"loss": 0.2634629821777344,
"step": 88000
},
{
"epoch": 1.9424081471401606,
"grad_norm": 18.453758239746094,
"learning_rate": 1.7626896682908274e-05,
"loss": 0.2758912353515625,
"step": 88500
},
{
"epoch": 1.9533822044686362,
"grad_norm": 29.018585205078125,
"learning_rate": 1.744399572743368e-05,
"loss": 0.26687152099609374,
"step": 89000
},
{
"epoch": 1.9643562617971115,
"grad_norm": 0.32755419611930847,
"learning_rate": 1.726109477195909e-05,
"loss": 0.28869473266601564,
"step": 89500
},
{
"epoch": 1.975330319125587,
"grad_norm": 0.00812600925564766,
"learning_rate": 1.7078193816484497e-05,
"loss": 0.2838319091796875,
"step": 90000
},
{
"epoch": 1.9863043764540627,
"grad_norm": 22.876619338989258,
"learning_rate": 1.6895292861009908e-05,
"loss": 0.24822427368164063,
"step": 90500
},
{
"epoch": 1.997278433782538,
"grad_norm": 29.792329788208008,
"learning_rate": 1.6712391905535316e-05,
"loss": 0.23443959045410157,
"step": 91000
},
{
"epoch": 2.0,
"eval_f1": 0.8288003736916,
"eval_loss": 0.356448233127594,
"eval_runtime": 22.1665,
"eval_samples_per_second": 1827.08,
"eval_steps_per_second": 228.408,
"step": 91124
},
{
"epoch": 2.008252491111014,
"grad_norm": 0.019856004044413567,
"learning_rate": 1.6529490950060723e-05,
"loss": 0.18815164184570313,
"step": 91500
},
{
"epoch": 2.019226548439489,
"grad_norm": 22.867015838623047,
"learning_rate": 1.634658999458613e-05,
"loss": 0.1597985076904297,
"step": 92000
},
{
"epoch": 2.0302006057679645,
"grad_norm": 0.14189456403255463,
"learning_rate": 1.616368903911154e-05,
"loss": 0.1571758575439453,
"step": 92500
},
{
"epoch": 2.04117466309644,
"grad_norm": 0.006348753347992897,
"learning_rate": 1.598078808363695e-05,
"loss": 0.16454287719726562,
"step": 93000
},
{
"epoch": 2.0521487204249156,
"grad_norm": 13.350561141967773,
"learning_rate": 1.5797887128162357e-05,
"loss": 0.17085581970214844,
"step": 93500
},
{
"epoch": 2.063122777753391,
"grad_norm": 0.04752154275774956,
"learning_rate": 1.561498617268777e-05,
"loss": 0.1648643035888672,
"step": 94000
},
{
"epoch": 2.0740968350818663,
"grad_norm": 8.686612129211426,
"learning_rate": 1.5432085217213173e-05,
"loss": 0.15125572204589843,
"step": 94500
},
{
"epoch": 2.085070892410342,
"grad_norm": 0.04292794689536095,
"learning_rate": 1.5249184261738584e-05,
"loss": 0.1467701416015625,
"step": 95000
},
{
"epoch": 2.0960449497388174,
"grad_norm": 43.54441452026367,
"learning_rate": 1.5066283306263992e-05,
"loss": 0.20134834289550782,
"step": 95500
},
{
"epoch": 2.1070190070672927,
"grad_norm": 0.18904000520706177,
"learning_rate": 1.4883382350789401e-05,
"loss": 0.181921875,
"step": 96000
},
{
"epoch": 2.1179930643957685,
"grad_norm": 0.3301223814487457,
"learning_rate": 1.470048139531481e-05,
"loss": 0.1817462158203125,
"step": 96500
},
{
"epoch": 2.128967121724244,
"grad_norm": 0.1473444551229477,
"learning_rate": 1.4517580439840216e-05,
"loss": 0.18687117004394532,
"step": 97000
},
{
"epoch": 2.139941179052719,
"grad_norm": 7.679690837860107,
"learning_rate": 1.4334679484365626e-05,
"loss": 0.16395710754394532,
"step": 97500
},
{
"epoch": 2.150915236381195,
"grad_norm": 35.09670639038086,
"learning_rate": 1.4151778528891035e-05,
"loss": 0.17217919921875,
"step": 98000
},
{
"epoch": 2.1618892937096703,
"grad_norm": 0.019701849669218063,
"learning_rate": 1.3968877573416445e-05,
"loss": 0.17984617614746093,
"step": 98500
},
{
"epoch": 2.1728633510381457,
"grad_norm": 0.20285935699939728,
"learning_rate": 1.3785976617941854e-05,
"loss": 0.16325213623046875,
"step": 99000
},
{
"epoch": 2.1838374083666214,
"grad_norm": 34.028297424316406,
"learning_rate": 1.360307566246726e-05,
"loss": 0.18122135925292968,
"step": 99500
},
{
"epoch": 2.1948114656950968,
"grad_norm": 0.05509435012936592,
"learning_rate": 1.342017470699267e-05,
"loss": 0.17191763305664062,
"step": 100000
},
{
"epoch": 2.205785523023572,
"grad_norm": 1.59047269821167,
"learning_rate": 1.3237273751518079e-05,
"loss": 0.15562428283691407,
"step": 100500
},
{
"epoch": 2.216759580352048,
"grad_norm": 30.329383850097656,
"learning_rate": 1.3054372796043488e-05,
"loss": 0.20622531127929689,
"step": 101000
},
{
"epoch": 2.2277336376805232,
"grad_norm": 0.020468488335609436,
"learning_rate": 1.2871471840568896e-05,
"loss": 0.16413253784179688,
"step": 101500
},
{
"epoch": 2.2387076950089986,
"grad_norm": 0.00997017603367567,
"learning_rate": 1.2688570885094304e-05,
"loss": 0.1655951690673828,
"step": 102000
},
{
"epoch": 2.2496817523374744,
"grad_norm": 0.1387864202260971,
"learning_rate": 1.2505669929619711e-05,
"loss": 0.16392440795898439,
"step": 102500
},
{
"epoch": 2.2606558096659497,
"grad_norm": 0.03306190297007561,
"learning_rate": 1.232276897414512e-05,
"loss": 0.17298390197753907,
"step": 103000
},
{
"epoch": 2.271629866994425,
"grad_norm": 0.010001047514379025,
"learning_rate": 1.213986801867053e-05,
"loss": 0.1894729461669922,
"step": 103500
},
{
"epoch": 2.282603924322901,
"grad_norm": 81.1466064453125,
"learning_rate": 1.1956967063195938e-05,
"loss": 0.17070208740234374,
"step": 104000
},
{
"epoch": 2.293577981651376,
"grad_norm": 0.02159142680466175,
"learning_rate": 1.1774066107721347e-05,
"loss": 0.18507080078125,
"step": 104500
},
{
"epoch": 2.3045520389798515,
"grad_norm": 0.054674021899700165,
"learning_rate": 1.1591165152246757e-05,
"loss": 0.17819773864746094,
"step": 105000
},
{
"epoch": 2.3155260963083273,
"grad_norm": 2.9571499824523926,
"learning_rate": 1.1408264196772164e-05,
"loss": 0.17032832336425782,
"step": 105500
},
{
"epoch": 2.3265001536368026,
"grad_norm": 1.2494076490402222,
"learning_rate": 1.1225363241297574e-05,
"loss": 0.1580600128173828,
"step": 106000
},
{
"epoch": 2.337474210965278,
"grad_norm": 0.3068596422672272,
"learning_rate": 1.1042462285822981e-05,
"loss": 0.16479891967773438,
"step": 106500
},
{
"epoch": 2.3484482682937537,
"grad_norm": 38.06135559082031,
"learning_rate": 1.0859561330348391e-05,
"loss": 0.19860018920898437,
"step": 107000
},
{
"epoch": 2.359422325622229,
"grad_norm": 16.392892837524414,
"learning_rate": 1.06766603748738e-05,
"loss": 0.17994320678710937,
"step": 107500
},
{
"epoch": 2.3703963829507044,
"grad_norm": 1.3012549877166748,
"learning_rate": 1.0493759419399208e-05,
"loss": 0.16105982971191407,
"step": 108000
},
{
"epoch": 2.38137044027918,
"grad_norm": 0.16427138447761536,
"learning_rate": 1.0310858463924616e-05,
"loss": 0.16437882995605468,
"step": 108500
},
{
"epoch": 2.3923444976076556,
"grad_norm": 0.008658411912620068,
"learning_rate": 1.0127957508450023e-05,
"loss": 0.14569871520996094,
"step": 109000
},
{
"epoch": 2.403318554936131,
"grad_norm": 0.1301782727241516,
"learning_rate": 9.945056552975433e-06,
"loss": 0.14984918212890624,
"step": 109500
},
{
"epoch": 2.4142926122646067,
"grad_norm": 3.813662528991699,
"learning_rate": 9.762155597500842e-06,
"loss": 0.18121104431152343,
"step": 110000
},
{
"epoch": 2.425266669593082,
"grad_norm": 2.6495282649993896,
"learning_rate": 9.57925464202625e-06,
"loss": 0.18369952392578126,
"step": 110500
},
{
"epoch": 2.4362407269215574,
"grad_norm": 3.705036163330078,
"learning_rate": 9.39635368655166e-06,
"loss": 0.16695921325683594,
"step": 111000
},
{
"epoch": 2.4472147842500327,
"grad_norm": 0.678033709526062,
"learning_rate": 9.213452731077067e-06,
"loss": 0.17362081909179689,
"step": 111500
},
{
"epoch": 2.4581888415785085,
"grad_norm": 50.983375549316406,
"learning_rate": 9.030551775602476e-06,
"loss": 0.16382778930664063,
"step": 112000
},
{
"epoch": 2.469162898906984,
"grad_norm": 29.069177627563477,
"learning_rate": 8.847650820127886e-06,
"loss": 0.16594575500488282,
"step": 112500
},
{
"epoch": 2.4801369562354596,
"grad_norm": 13.098567962646484,
"learning_rate": 8.664749864653293e-06,
"loss": 0.1821525115966797,
"step": 113000
},
{
"epoch": 2.491111013563935,
"grad_norm": 64.5162353515625,
"learning_rate": 8.481848909178703e-06,
"loss": 0.15829127502441406,
"step": 113500
},
{
"epoch": 2.5020850708924103,
"grad_norm": 2.7032110691070557,
"learning_rate": 8.29894795370411e-06,
"loss": 0.1485829620361328,
"step": 114000
},
{
"epoch": 2.5130591282208856,
"grad_norm": 40.1707878112793,
"learning_rate": 8.11604699822952e-06,
"loss": 0.1723223876953125,
"step": 114500
},
{
"epoch": 2.5240331855493614,
"grad_norm": 0.07498432695865631,
"learning_rate": 7.933146042754928e-06,
"loss": 0.15050241088867186,
"step": 115000
},
{
"epoch": 2.5350072428778367,
"grad_norm": 26.58846664428711,
"learning_rate": 7.750245087280335e-06,
"loss": 0.15875759887695312,
"step": 115500
},
{
"epoch": 2.5459813002063125,
"grad_norm": 0.05308910831809044,
"learning_rate": 7.567344131805746e-06,
"loss": 0.1401026611328125,
"step": 116000
},
{
"epoch": 2.556955357534788,
"grad_norm": 45.850929260253906,
"learning_rate": 7.384443176331153e-06,
"loss": 0.15721929931640624,
"step": 116500
},
{
"epoch": 2.567929414863263,
"grad_norm": 45.02235412597656,
"learning_rate": 7.201542220856562e-06,
"loss": 0.19153817749023438,
"step": 117000
},
{
"epoch": 2.5789034721917385,
"grad_norm": 0.04809782654047012,
"learning_rate": 7.018641265381971e-06,
"loss": 0.1555188446044922,
"step": 117500
},
{
"epoch": 2.5898775295202143,
"grad_norm": 0.008281511254608631,
"learning_rate": 6.835740309907379e-06,
"loss": 0.17925529479980468,
"step": 118000
},
{
"epoch": 2.6008515868486897,
"grad_norm": 23.324901580810547,
"learning_rate": 6.652839354432788e-06,
"loss": 0.167087158203125,
"step": 118500
},
{
"epoch": 2.6118256441771655,
"grad_norm": 19.250812530517578,
"learning_rate": 6.469938398958196e-06,
"loss": 0.14051246643066406,
"step": 119000
},
{
"epoch": 2.622799701505641,
"grad_norm": 0.014977659098803997,
"learning_rate": 6.2870374434836055e-06,
"loss": 0.1504051513671875,
"step": 119500
},
{
"epoch": 2.633773758834116,
"grad_norm": 23.393903732299805,
"learning_rate": 6.104136488009013e-06,
"loss": 0.1683112335205078,
"step": 120000
},
{
"epoch": 2.6447478161625915,
"grad_norm": 0.09205972403287888,
"learning_rate": 5.921235532534422e-06,
"loss": 0.15621336364746094,
"step": 120500
},
{
"epoch": 2.6557218734910673,
"grad_norm": 0.5144221782684326,
"learning_rate": 5.73833457705983e-06,
"loss": 0.1647897491455078,
"step": 121000
},
{
"epoch": 2.6666959308195426,
"grad_norm": 0.00860594492405653,
"learning_rate": 5.55543362158524e-06,
"loss": 0.15313204956054688,
"step": 121500
},
{
"epoch": 2.677669988148018,
"grad_norm": 2.207170248031616,
"learning_rate": 5.372532666110648e-06,
"loss": 0.15816647338867187,
"step": 122000
},
{
"epoch": 2.6886440454764937,
"grad_norm": 0.018872277811169624,
"learning_rate": 5.189631710636057e-06,
"loss": 0.1415150146484375,
"step": 122500
},
{
"epoch": 2.699618102804969,
"grad_norm": 0.011648227460682392,
"learning_rate": 5.006730755161465e-06,
"loss": 0.13911293029785157,
"step": 123000
},
{
"epoch": 2.7105921601334444,
"grad_norm": 0.09587373584508896,
"learning_rate": 4.823829799686874e-06,
"loss": 0.13494076538085936,
"step": 123500
},
{
"epoch": 2.72156621746192,
"grad_norm": 0.04641059786081314,
"learning_rate": 4.6409288442122825e-06,
"loss": 0.17721914672851563,
"step": 124000
},
{
"epoch": 2.7325402747903955,
"grad_norm": 0.011687349528074265,
"learning_rate": 4.458027888737691e-06,
"loss": 0.16873222351074219,
"step": 124500
},
{
"epoch": 2.743514332118871,
"grad_norm": 118.11669158935547,
"learning_rate": 4.2751269332630996e-06,
"loss": 0.15355369567871094,
"step": 125000
},
{
"epoch": 2.7544883894473466,
"grad_norm": 0.481996089220047,
"learning_rate": 4.092225977788508e-06,
"loss": 0.13936019897460938,
"step": 125500
},
{
"epoch": 2.765462446775822,
"grad_norm": 0.19096533954143524,
"learning_rate": 3.909325022313917e-06,
"loss": 0.17287538146972656,
"step": 126000
},
{
"epoch": 2.7764365041042973,
"grad_norm": 67.1457748413086,
"learning_rate": 3.7264240668393257e-06,
"loss": 0.15823133850097656,
"step": 126500
},
{
"epoch": 2.7874105614327727,
"grad_norm": 15.519521713256836,
"learning_rate": 3.543523111364734e-06,
"loss": 0.17597552490234375,
"step": 127000
},
{
"epoch": 2.7983846187612484,
"grad_norm": 0.021220775321125984,
"learning_rate": 3.3606221558901423e-06,
"loss": 0.15953814697265625,
"step": 127500
},
{
"epoch": 2.809358676089724,
"grad_norm": 0.008825136348605156,
"learning_rate": 3.177721200415551e-06,
"loss": 0.16651971435546875,
"step": 128000
},
{
"epoch": 2.8203327334181996,
"grad_norm": 0.20404738187789917,
"learning_rate": 2.99482024494096e-06,
"loss": 0.1628278350830078,
"step": 128500
},
{
"epoch": 2.831306790746675,
"grad_norm": 0.009165110997855663,
"learning_rate": 2.8119192894663684e-06,
"loss": 0.1425828094482422,
"step": 129000
},
{
"epoch": 2.8422808480751502,
"grad_norm": 0.008576123043894768,
"learning_rate": 2.629018333991777e-06,
"loss": 0.16400938415527344,
"step": 129500
},
{
"epoch": 2.8532549054036256,
"grad_norm": 37.710914611816406,
"learning_rate": 2.4461173785171855e-06,
"loss": 0.15623898315429688,
"step": 130000
},
{
"epoch": 2.8642289627321014,
"grad_norm": 11.700338363647461,
"learning_rate": 2.263216423042594e-06,
"loss": 0.1631771545410156,
"step": 130500
},
{
"epoch": 2.8752030200605767,
"grad_norm": 1.506538987159729,
"learning_rate": 2.0803154675680026e-06,
"loss": 0.15615669250488282,
"step": 131000
},
{
"epoch": 2.8861770773890525,
"grad_norm": 33.31697082519531,
"learning_rate": 1.8974145120934112e-06,
"loss": 0.1537679138183594,
"step": 131500
},
{
"epoch": 2.897151134717528,
"grad_norm": 38.086795806884766,
"learning_rate": 1.71451355661882e-06,
"loss": 0.16492466735839845,
"step": 132000
},
{
"epoch": 2.908125192046003,
"grad_norm": 0.02016337588429451,
"learning_rate": 1.5316126011442285e-06,
"loss": 0.15764328002929687,
"step": 132500
},
{
"epoch": 2.9190992493744785,
"grad_norm": 0.06843503564596176,
"learning_rate": 1.348711645669637e-06,
"loss": 0.14805685424804688,
"step": 133000
},
{
"epoch": 2.9300733067029543,
"grad_norm": 0.006283937953412533,
"learning_rate": 1.1658106901950456e-06,
"loss": 0.1535034637451172,
"step": 133500
},
{
"epoch": 2.9410473640314296,
"grad_norm": 0.0035067277494817972,
"learning_rate": 9.829097347204541e-07,
"loss": 0.15516947937011719,
"step": 134000
},
{
"epoch": 2.9520214213599054,
"grad_norm": 0.023081157356500626,
"learning_rate": 8.000087792458628e-07,
"loss": 0.15423509216308592,
"step": 134500
},
{
"epoch": 2.9629954786883808,
"grad_norm": 13.908537864685059,
"learning_rate": 6.171078237712715e-07,
"loss": 0.14795904541015625,
"step": 135000
},
{
"epoch": 2.973969536016856,
"grad_norm": 0.019963253289461136,
"learning_rate": 4.3420686829668e-07,
"loss": 0.15023118591308593,
"step": 135500
},
{
"epoch": 2.9849435933453314,
"grad_norm": 20.809101104736328,
"learning_rate": 2.513059128220886e-07,
"loss": 0.1423495330810547,
"step": 136000
},
{
"epoch": 2.995917650673807,
"grad_norm": 26.06735610961914,
"learning_rate": 6.840495734749718e-08,
"loss": 0.15201040649414063,
"step": 136500
},
{
"epoch": 3.0,
"eval_f1": 0.8518024169356405,
"eval_loss": 0.38094356656074524,
"eval_runtime": 21.6505,
"eval_samples_per_second": 1870.627,
"eval_steps_per_second": 233.851,
"step": 136686
},
{
"epoch": 3.0,
"step": 136686,
"total_flos": 1.801472479969075e+16,
"train_loss": 0.3033465779127858,
"train_runtime": 2259.7352,
"train_samples_per_second": 483.897,
"train_steps_per_second": 60.488
}
],
"logging_steps": 500,
"max_steps": 136686,
"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": true
},
"attributes": {}
}
},
"total_flos": 1.801472479969075e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}