{
  "best_global_step": 17094,
  "best_metric": 0.9845099349219312,
  "best_model_checkpoint": "./xlmr-language-identification/checkpoint-17094",
  "epoch": 2.0,
  "eval_steps": 2500,
  "global_step": 17094,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011701304695473546,
      "grad_norm": 0.9905334711074829,
      "learning_rate": 4.971042471042471e-05,
      "loss": 16.156219482421875,
      "step": 100
    },
    {
      "epoch": 0.023402609390947092,
      "grad_norm": 1.069915533065796,
      "learning_rate": 4.941792441792442e-05,
      "loss": 5.045557556152343,
      "step": 200
    },
    {
      "epoch": 0.035103914086420634,
      "grad_norm": 1.8720062971115112,
      "learning_rate": 4.912542412542413e-05,
      "loss": 4.602024841308594,
      "step": 300
    },
    {
      "epoch": 0.046805218781894184,
      "grad_norm": 2.246952772140503,
      "learning_rate": 4.883292383292383e-05,
      "loss": 2.9484735107421876,
      "step": 400
    },
    {
      "epoch": 0.058506523477367726,
      "grad_norm": 1.7273783683776855,
      "learning_rate": 4.8540423540423544e-05,
      "loss": 1.8604541015625,
      "step": 500
    },
    {
      "epoch": 0.07020782817284127,
      "grad_norm": 1.871302843093872,
      "learning_rate": 4.824792324792325e-05,
      "loss": 1.2988777160644531,
      "step": 600
    },
    {
      "epoch": 0.08190913286831482,
      "grad_norm": 1.9515539407730103,
      "learning_rate": 4.7955422955422954e-05,
      "loss": 0.9935964965820312,
      "step": 700
    },
    {
      "epoch": 0.09361043756378837,
      "grad_norm": 1.469983696937561,
      "learning_rate": 4.7662922662922666e-05,
      "loss": 0.803764877319336,
      "step": 800
    },
    {
      "epoch": 0.1053117422592619,
      "grad_norm": 1.6788742542266846,
      "learning_rate": 4.737042237042237e-05,
      "loss": 0.6818081665039063,
      "step": 900
    },
    {
      "epoch": 0.11701304695473545,
      "grad_norm": 1.4318715333938599,
      "learning_rate": 4.707792207792208e-05,
      "loss": 0.5820805740356445,
      "step": 1000
    },
    {
      "epoch": 0.128714351650209,
      "grad_norm": 1.9161852598190308,
      "learning_rate": 4.678542178542179e-05,
      "loss": 0.5121846389770508,
      "step": 1100
    },
    {
      "epoch": 0.14041565634568254,
      "grad_norm": 1.6554639339447021,
      "learning_rate": 4.6492921492921494e-05,
      "loss": 0.4561897277832031,
      "step": 1200
    },
    {
      "epoch": 0.1521169610411561,
      "grad_norm": 1.839687466621399,
      "learning_rate": 4.62004212004212e-05,
      "loss": 0.4188547134399414,
      "step": 1300
    },
    {
      "epoch": 0.16381826573662964,
      "grad_norm": 1.735112190246582,
      "learning_rate": 4.590792090792091e-05,
      "loss": 0.3874264144897461,
      "step": 1400
    },
    {
      "epoch": 0.17551957043210317,
      "grad_norm": 2.1364924907684326,
      "learning_rate": 4.5615420615420616e-05,
      "loss": 0.36660758972167967,
      "step": 1500
    },
    {
      "epoch": 0.18722087512757674,
      "grad_norm": 1.5190038681030273,
      "learning_rate": 4.532292032292033e-05,
      "loss": 0.3320538330078125,
      "step": 1600
    },
    {
      "epoch": 0.19892217982305027,
      "grad_norm": 1.4698094129562378,
      "learning_rate": 4.503042003042003e-05,
      "loss": 0.3180769729614258,
      "step": 1700
    },
    {
      "epoch": 0.2106234845185238,
      "grad_norm": 1.4362446069717407,
      "learning_rate": 4.4737919737919745e-05,
      "loss": 0.3039104461669922,
      "step": 1800
    },
    {
      "epoch": 0.22232478921399737,
      "grad_norm": 1.5884244441986084,
      "learning_rate": 4.444541944541944e-05,
      "loss": 0.2853180694580078,
      "step": 1900
    },
    {
      "epoch": 0.2340260939094709,
      "grad_norm": 1.14271879196167,
      "learning_rate": 4.4152919152919155e-05,
      "loss": 0.2749899673461914,
      "step": 2000
    },
    {
      "epoch": 0.24572739860494444,
      "grad_norm": 1.3998445272445679,
      "learning_rate": 4.386041886041886e-05,
      "loss": 0.2584847450256348,
      "step": 2100
    },
    {
      "epoch": 0.257428703300418,
      "grad_norm": 1.126080870628357,
      "learning_rate": 4.356791856791857e-05,
      "loss": 0.2443878746032715,
      "step": 2200
    },
    {
      "epoch": 0.26913000799589154,
      "grad_norm": 1.6860474348068237,
      "learning_rate": 4.327541827541828e-05,
      "loss": 0.23169761657714844,
      "step": 2300
    },
    {
      "epoch": 0.2808313126913651,
      "grad_norm": 1.8752473592758179,
      "learning_rate": 4.298291798291799e-05,
      "loss": 0.22600336074829103,
      "step": 2400
    },
    {
      "epoch": 0.2925326173868386,
      "grad_norm": 1.6066241264343262,
      "learning_rate": 4.2690417690417694e-05,
      "loss": 0.2185952568054199,
      "step": 2500
    },
    {
      "epoch": 0.2925326173868386,
      "eval_accuracy": 0.8560363636363636,
      "eval_f1": 0.9651478556858426,
      "eval_loss": 0.039476945996284485,
      "eval_precision": 0.9777755239169846,
      "eval_recall": 0.9528421936966432,
      "eval_runtime": 165.9297,
      "eval_samples_per_second": 165.733,
      "eval_steps_per_second": 5.183,
      "step": 2500
    },
    {
      "epoch": 0.3042339220823122,
      "grad_norm": 1.2747637033462524,
      "learning_rate": 4.2397917397917406e-05,
      "loss": 0.22376758575439454,
      "step": 2600
    },
    {
      "epoch": 0.31593522677778574,
      "grad_norm": 1.5281429290771484,
      "learning_rate": 4.2105417105417104e-05,
      "loss": 0.21567138671875,
      "step": 2700
    },
    {
      "epoch": 0.3276365314732593,
      "grad_norm": 1.0241914987564087,
      "learning_rate": 4.1812916812916816e-05,
      "loss": 0.20220571517944336,
      "step": 2800
    },
    {
      "epoch": 0.3393378361687328,
      "grad_norm": 1.9281812906265259,
      "learning_rate": 4.152041652041652e-05,
      "loss": 0.19900651931762695,
      "step": 2900
    },
    {
      "epoch": 0.35103914086420634,
      "grad_norm": 1.0900094509124756,
      "learning_rate": 4.122791622791623e-05,
      "loss": 0.19108434677124023,
      "step": 3000
    },
    {
      "epoch": 0.3627404455596799,
      "grad_norm": 1.9392260313034058,
      "learning_rate": 4.093541593541594e-05,
      "loss": 0.1862166404724121,
      "step": 3100
    },
    {
      "epoch": 0.37444175025515347,
      "grad_norm": 1.4907201528549194,
      "learning_rate": 4.064291564291564e-05,
      "loss": 0.18224323272705079,
      "step": 3200
    },
    {
      "epoch": 0.386143054950627,
      "grad_norm": 1.0142017602920532,
      "learning_rate": 4.0350415350415355e-05,
      "loss": 0.17916433334350587,
      "step": 3300
    },
    {
      "epoch": 0.39784435964610054,
      "grad_norm": 1.3136364221572876,
      "learning_rate": 4.005791505791506e-05,
      "loss": 0.17482011795043945,
      "step": 3400
    },
    {
      "epoch": 0.4095456643415741,
      "grad_norm": 1.7887938022613525,
      "learning_rate": 3.9765414765414765e-05,
      "loss": 0.16918930053710937,
      "step": 3500
    },
    {
      "epoch": 0.4212469690370476,
      "grad_norm": 1.368762731552124,
      "learning_rate": 3.947291447291447e-05,
      "loss": 0.1643056869506836,
      "step": 3600
    },
    {
      "epoch": 0.43294827373252115,
      "grad_norm": 1.666864275932312,
      "learning_rate": 3.918041418041418e-05,
      "loss": 0.16255182266235352,
      "step": 3700
    },
    {
      "epoch": 0.44464957842799474,
      "grad_norm": 1.4107720851898193,
      "learning_rate": 3.888791388791389e-05,
      "loss": 0.15760359764099122,
      "step": 3800
    },
    {
      "epoch": 0.4563508831234683,
      "grad_norm": 1.6475497484207153,
      "learning_rate": 3.85954135954136e-05,
      "loss": 0.1564300537109375,
      "step": 3900
    },
    {
      "epoch": 0.4680521878189418,
      "grad_norm": 1.3566536903381348,
      "learning_rate": 3.8302913302913305e-05,
      "loss": 0.15231061935424806,
      "step": 4000
    },
    {
      "epoch": 0.47975349251441535,
      "grad_norm": 0.9237350225448608,
      "learning_rate": 3.801041301041301e-05,
      "loss": 0.14665995597839354,
      "step": 4100
    },
    {
      "epoch": 0.4914547972098889,
      "grad_norm": 2.0160303115844727,
      "learning_rate": 3.7717912717912715e-05,
      "loss": 0.1439968776702881,
      "step": 4200
    },
    {
      "epoch": 0.5031561019053624,
      "grad_norm": 1.495821237564087,
      "learning_rate": 3.742541242541243e-05,
      "loss": 0.14349424362182617,
      "step": 4300
    },
    {
      "epoch": 0.514857406600836,
      "grad_norm": 1.1643633842468262,
      "learning_rate": 3.713291213291213e-05,
      "loss": 0.1439281463623047,
      "step": 4400
    },
    {
      "epoch": 0.5265587112963095,
      "grad_norm": 1.2707788944244385,
      "learning_rate": 3.6840411840411844e-05,
      "loss": 0.14324712753295898,
      "step": 4500
    },
    {
      "epoch": 0.5382600159917831,
      "grad_norm": 0.9467172026634216,
      "learning_rate": 3.654791154791155e-05,
      "loss": 0.136934118270874,
      "step": 4600
    },
    {
      "epoch": 0.5499613206872567,
      "grad_norm": 1.4451957941055298,
      "learning_rate": 3.625541125541126e-05,
      "loss": 0.13631460189819336,
      "step": 4700
    },
    {
      "epoch": 0.5616626253827302,
      "grad_norm": 1.1038591861724854,
      "learning_rate": 3.5962910962910966e-05,
      "loss": 0.13634085655212402,
      "step": 4800
    },
    {
      "epoch": 0.5733639300782037,
      "grad_norm": 1.2149685621261597,
      "learning_rate": 3.567041067041067e-05,
      "loss": 0.13158455848693848,
      "step": 4900
    },
    {
      "epoch": 0.5850652347736772,
      "grad_norm": 1.421316146850586,
      "learning_rate": 3.5377910377910376e-05,
      "loss": 0.13308174133300782,
      "step": 5000
    },
    {
      "epoch": 0.5850652347736772,
      "eval_accuracy": 0.9069818181818182,
      "eval_f1": 0.9759635668726578,
      "eval_loss": 0.02319982275366783,
      "eval_precision": 0.9802819359100597,
      "eval_recall": 0.971683077797408,
      "eval_runtime": 164.1216,
      "eval_samples_per_second": 167.559,
      "eval_steps_per_second": 5.24,
      "step": 5000
    },
    {
      "epoch": 0.5967665394691508,
      "grad_norm": 1.9884291887283325,
      "learning_rate": 3.508541008541009e-05,
      "loss": 0.12942585945129395,
      "step": 5100
    },
    {
      "epoch": 0.6084678441646244,
      "grad_norm": 1.1202914714813232,
      "learning_rate": 3.479290979290979e-05,
      "loss": 0.12913961410522462,
      "step": 5200
    },
    {
      "epoch": 0.6201691488600979,
      "grad_norm": 1.470561146736145,
      "learning_rate": 3.4500409500409505e-05,
      "loss": 0.12901023864746095,
      "step": 5300
    },
    {
      "epoch": 0.6318704535555715,
      "grad_norm": 0.930363655090332,
      "learning_rate": 3.420790920790921e-05,
      "loss": 0.12278788566589355,
      "step": 5400
    },
    {
      "epoch": 0.643571758251045,
      "grad_norm": 1.7242929935455322,
      "learning_rate": 3.391540891540892e-05,
      "loss": 0.12592774391174316,
      "step": 5500
    },
    {
      "epoch": 0.6552730629465185,
      "grad_norm": 1.8954977989196777,
      "learning_rate": 3.362290862290862e-05,
      "loss": 0.12447975158691406,
      "step": 5600
    },
    {
      "epoch": 0.666974367641992,
      "grad_norm": 1.352124571800232,
      "learning_rate": 3.333040833040833e-05,
      "loss": 0.1232685947418213,
      "step": 5700
    },
    {
      "epoch": 0.6786756723374656,
      "grad_norm": 1.2466479539871216,
      "learning_rate": 3.303790803790804e-05,
      "loss": 0.11894026756286621,
      "step": 5800
    },
    {
      "epoch": 0.6903769770329392,
      "grad_norm": 1.429012656211853,
      "learning_rate": 3.274540774540775e-05,
      "loss": 0.11655033111572266,
      "step": 5900
    },
    {
      "epoch": 0.7020782817284127,
      "grad_norm": 1.4804608821868896,
      "learning_rate": 3.2452907452907454e-05,
      "loss": 0.11837745666503906,
      "step": 6000
    },
    {
      "epoch": 0.7137795864238863,
      "grad_norm": 1.3687437772750854,
      "learning_rate": 3.2160407160407166e-05,
      "loss": 0.11587305068969726,
      "step": 6100
    },
    {
      "epoch": 0.7254808911193598,
      "grad_norm": 1.4826337099075317,
      "learning_rate": 3.186790686790687e-05,
      "loss": 0.11750144958496093,
      "step": 6200
    },
    {
      "epoch": 0.7371821958148334,
      "grad_norm": 0.959021270275116,
      "learning_rate": 3.1575406575406577e-05,
      "loss": 0.11341402053833008,
      "step": 6300
    },
    {
      "epoch": 0.7488835005103069,
      "grad_norm": 0.8908078670501709,
      "learning_rate": 3.128290628290628e-05,
      "loss": 0.11524638175964355,
      "step": 6400
    },
    {
      "epoch": 0.7605848052057804,
      "grad_norm": 0.9967349171638489,
      "learning_rate": 3.0990405990405994e-05,
      "loss": 0.1124759292602539,
      "step": 6500
    },
    {
      "epoch": 0.772286109901254,
      "grad_norm": 1.4200743436813354,
      "learning_rate": 3.06979056979057e-05,
      "loss": 0.10863906860351563,
      "step": 6600
    },
    {
      "epoch": 0.7839874145967275,
      "grad_norm": 1.6694557666778564,
      "learning_rate": 3.0405405405405407e-05,
      "loss": 0.11165953636169433,
      "step": 6700
    },
    {
      "epoch": 0.7956887192922011,
      "grad_norm": 1.0781575441360474,
      "learning_rate": 3.0112905112905116e-05,
      "loss": 0.1116695213317871,
      "step": 6800
    },
    {
      "epoch": 0.8073900239876747,
      "grad_norm": 1.3060591220855713,
      "learning_rate": 2.9820404820404824e-05,
      "loss": 0.1075587272644043,
      "step": 6900
    },
    {
      "epoch": 0.8190913286831482,
      "grad_norm": 1.448541283607483,
      "learning_rate": 2.9527904527904533e-05,
      "loss": 0.11105222702026367,
      "step": 7000
    },
    {
      "epoch": 0.8307926333786217,
      "grad_norm": 1.8385331630706787,
      "learning_rate": 2.9235404235404234e-05,
      "loss": 0.10690691947937012,
      "step": 7100
    },
    {
      "epoch": 0.8424939380740952,
      "grad_norm": 1.4097715616226196,
      "learning_rate": 2.8942903942903943e-05,
      "loss": 0.10494094848632812,
      "step": 7200
    },
    {
      "epoch": 0.8541952427695688,
      "grad_norm": 1.7280794382095337,
      "learning_rate": 2.865040365040365e-05,
      "loss": 0.10908853530883789,
      "step": 7300
    },
    {
      "epoch": 0.8658965474650423,
      "grad_norm": 1.0693798065185547,
      "learning_rate": 2.835790335790336e-05,
      "loss": 0.10775123596191406,
      "step": 7400
    },
    {
      "epoch": 0.8775978521605159,
      "grad_norm": 1.5537015199661255,
      "learning_rate": 2.806540306540307e-05,
      "loss": 0.10442270278930664,
      "step": 7500
    },
    {
      "epoch": 0.8775978521605159,
      "eval_accuracy": 0.9217818181818181,
      "eval_f1": 0.9801159592655914,
      "eval_loss": 0.017201833426952362,
      "eval_precision": 0.982831231753525,
      "eval_recall": 0.9774156484352801,
      "eval_runtime": 185.5814,
      "eval_samples_per_second": 148.183,
      "eval_steps_per_second": 4.634,
      "step": 7500
    },
    {
      "epoch": 0.8892991568559895,
      "grad_norm": 1.0237928628921509,
      "learning_rate": 2.7772902772902777e-05,
      "loss": 0.10509194374084473,
      "step": 7600
    },
    {
      "epoch": 0.901000461551463,
      "grad_norm": 1.5233043432235718,
      "learning_rate": 2.7480402480402486e-05,
      "loss": 0.10594425201416016,
      "step": 7700
    },
    {
      "epoch": 0.9127017662469366,
      "grad_norm": 0.8517800569534302,
      "learning_rate": 2.7187902187902187e-05,
      "loss": 0.10539012908935547,
      "step": 7800
    },
    {
      "epoch": 0.92440307094241,
      "grad_norm": 1.3082163333892822,
      "learning_rate": 2.6895401895401896e-05,
      "loss": 0.09960749626159668,
      "step": 7900
    },
    {
      "epoch": 0.9361043756378836,
      "grad_norm": 0.8803576827049255,
      "learning_rate": 2.6602901602901604e-05,
      "loss": 0.10325809478759766,
      "step": 8000
    },
    {
      "epoch": 0.9478056803333572,
      "grad_norm": 1.5242176055908203,
      "learning_rate": 2.6310401310401313e-05,
      "loss": 0.10169939041137695,
      "step": 8100
    },
    {
      "epoch": 0.9595069850288307,
      "grad_norm": 1.2510749101638794,
      "learning_rate": 2.601790101790102e-05,
      "loss": 0.100986909866333,
      "step": 8200
    },
    {
      "epoch": 0.9712082897243043,
      "grad_norm": 1.4342858791351318,
      "learning_rate": 2.5725400725400726e-05,
      "loss": 0.09906567573547363,
      "step": 8300
    },
    {
      "epoch": 0.9829095944197778,
      "grad_norm": 1.1943491697311401,
      "learning_rate": 2.5432900432900435e-05,
      "loss": 0.09981002807617187,
      "step": 8400
    },
    {
      "epoch": 0.9946108991152514,
      "grad_norm": 1.0533969402313232,
      "learning_rate": 2.5140400140400143e-05,
      "loss": 0.10099024772644043,
      "step": 8500
    },
    {
      "epoch": 1.006201691488601,
      "grad_norm": 0.952810525894165,
      "learning_rate": 2.484789984789985e-05,
      "loss": 0.09148699760437012,
      "step": 8600
    },
    {
      "epoch": 1.0179029961840744,
      "grad_norm": 0.9051135182380676,
      "learning_rate": 2.4555399555399554e-05,
      "loss": 0.08493613243103028,
      "step": 8700
    },
    {
      "epoch": 1.0296043008795481,
      "grad_norm": 1.4660611152648926,
      "learning_rate": 2.4262899262899262e-05,
      "loss": 0.08283645629882813,
      "step": 8800
    },
    {
      "epoch": 1.0413056055750216,
      "grad_norm": 1.2308636903762817,
      "learning_rate": 2.397039897039897e-05,
      "loss": 0.08224470138549805,
      "step": 8900
    },
    {
      "epoch": 1.053006910270495,
      "grad_norm": 1.180936574935913,
      "learning_rate": 2.367789867789868e-05,
      "loss": 0.08456890106201172,
      "step": 9000
    },
    {
      "epoch": 1.0647082149659688,
      "grad_norm": 1.1681982278823853,
      "learning_rate": 2.3385398385398384e-05,
      "loss": 0.08683476448059083,
      "step": 9100
    },
    {
      "epoch": 1.0764095196614423,
      "grad_norm": 1.1853655576705933,
      "learning_rate": 2.3092898092898093e-05,
      "loss": 0.08339482307434082,
      "step": 9200
    },
    {
      "epoch": 1.0881108243569158,
      "grad_norm": 0.7993655204772949,
      "learning_rate": 2.28003978003978e-05,
      "loss": 0.08154037475585937,
      "step": 9300
    },
    {
      "epoch": 1.0998121290523892,
      "grad_norm": 1.3015902042388916,
      "learning_rate": 2.250789750789751e-05,
      "loss": 0.0843494701385498,
      "step": 9400
    },
    {
      "epoch": 1.111513433747863,
      "grad_norm": 0.927474319934845,
      "learning_rate": 2.2215397215397215e-05,
      "loss": 0.08107766151428222,
      "step": 9500
    },
    {
      "epoch": 1.1232147384433364,
      "grad_norm": 1.2510508298873901,
      "learning_rate": 2.1922896922896923e-05,
      "loss": 0.08390594482421875,
      "step": 9600
    },
    {
      "epoch": 1.13491604313881,
      "grad_norm": 1.012722373008728,
      "learning_rate": 2.1630396630396632e-05,
      "loss": 0.08134162902832032,
      "step": 9700
    },
    {
      "epoch": 1.1466173478342836,
      "grad_norm": 1.8160477876663208,
      "learning_rate": 2.1337896337896337e-05,
      "loss": 0.08689288139343261,
      "step": 9800
    },
    {
      "epoch": 1.158318652529757,
      "grad_norm": 1.6144487857818604,
      "learning_rate": 2.1045396045396046e-05,
      "loss": 0.08774213790893555,
      "step": 9900
    },
    {
      "epoch": 1.1700199572252306,
      "grad_norm": 1.088478922843933,
      "learning_rate": 2.0752895752895754e-05,
      "loss": 0.08510435104370118,
      "step": 10000
    },
    {
      "epoch": 1.1700199572252306,
      "eval_accuracy": 0.9310545454545455,
      "eval_f1": 0.9822452239157081,
      "eval_loss": 0.0149807995185256,
      "eval_precision": 0.9843658878562654,
      "eval_recall": 0.9801336776170297,
      "eval_runtime": 187.3637,
      "eval_samples_per_second": 146.773,
      "eval_steps_per_second": 4.59,
      "step": 10000
    },
    {
      "epoch": 1.1817212619207043,
      "grad_norm": 1.2410812377929688,
      "learning_rate": 2.0460395460395463e-05,
      "loss": 0.08356905937194824,
      "step": 10100
    },
    {
      "epoch": 1.1934225666161777,
      "grad_norm": 0.9291555881500244,
      "learning_rate": 2.0167895167895168e-05,
      "loss": 0.08259629249572754,
      "step": 10200
    },
    {
      "epoch": 1.2051238713116512,
      "grad_norm": 1.146966576576233,
      "learning_rate": 1.9875394875394876e-05,
      "loss": 0.08215347290039063,
      "step": 10300
    },
    {
      "epoch": 1.2168251760071247,
      "grad_norm": 0.9125510454177856,
      "learning_rate": 1.9582894582894585e-05,
      "loss": 0.08209040641784668,
      "step": 10400
    },
    {
      "epoch": 1.2285264807025984,
      "grad_norm": 0.906428337097168,
      "learning_rate": 1.9290394290394293e-05,
      "loss": 0.08041071891784668,
      "step": 10500
    },
    {
      "epoch": 1.2402277853980719,
      "grad_norm": 1.0091209411621094,
      "learning_rate": 1.8997893997894e-05,
      "loss": 0.07910086631774903,
      "step": 10600
    },
    {
      "epoch": 1.2519290900935454,
      "grad_norm": 0.9152646660804749,
      "learning_rate": 1.8705393705393707e-05,
      "loss": 0.08119074821472168,
      "step": 10700
    },
    {
      "epoch": 1.2636303947890188,
      "grad_norm": 1.0613765716552734,
      "learning_rate": 1.8412893412893415e-05,
      "loss": 0.07813576221466065,
      "step": 10800
    },
    {
      "epoch": 1.2753316994844925,
      "grad_norm": 0.7284146547317505,
      "learning_rate": 1.8120393120393124e-05,
      "loss": 0.08263915061950683,
      "step": 10900
    },
    {
      "epoch": 1.287033004179966,
      "grad_norm": 0.8245161771774292,
      "learning_rate": 1.782789282789283e-05,
      "loss": 0.07991621494293213,
      "step": 11000
    },
    {
      "epoch": 1.2987343088754395,
      "grad_norm": 0.9131597876548767,
      "learning_rate": 1.7535392535392538e-05,
      "loss": 0.08203693389892579,
      "step": 11100
    },
    {
      "epoch": 1.3104356135709132,
      "grad_norm": 1.4919288158416748,
      "learning_rate": 1.7242892242892246e-05,
      "loss": 0.07703531742095947,
      "step": 11200
    },
    {
      "epoch": 1.3221369182663867,
      "grad_norm": 0.9880580306053162,
      "learning_rate": 1.695039195039195e-05,
      "loss": 0.07978516101837158,
      "step": 11300
    },
    {
      "epoch": 1.3338382229618602,
      "grad_norm": 1.483494758605957,
      "learning_rate": 1.665789165789166e-05,
      "loss": 0.0792800235748291,
      "step": 11400
    },
    {
      "epoch": 1.3455395276573339,
      "grad_norm": 1.2706217765808105,
      "learning_rate": 1.6365391365391368e-05,
      "loss": 0.08085798263549805,
      "step": 11500
    },
    {
      "epoch": 1.3572408323528073,
      "grad_norm": 0.9506115913391113,
      "learning_rate": 1.6072891072891073e-05,
      "loss": 0.0732752513885498,
      "step": 11600
    },
    {
      "epoch": 1.3689421370482808,
      "grad_norm": 0.7671661972999573,
      "learning_rate": 1.5780390780390782e-05,
      "loss": 0.07732769966125488,
      "step": 11700
    },
    {
      "epoch": 1.3806434417437545,
      "grad_norm": 1.3610262870788574,
      "learning_rate": 1.5487890487890487e-05,
      "loss": 0.07633553028106689,
      "step": 11800
    },
    {
      "epoch": 1.392344746439228,
      "grad_norm": 1.1439802646636963,
      "learning_rate": 1.5195390195390197e-05,
      "loss": 0.07713084220886231,
      "step": 11900
    },
    {
      "epoch": 1.4040460511347015,
      "grad_norm": 1.389791488647461,
      "learning_rate": 1.4902889902889906e-05,
      "loss": 0.0749136209487915,
      "step": 12000
    },
    {
      "epoch": 1.4157473558301752,
      "grad_norm": 0.6515536308288574,
      "learning_rate": 1.461038961038961e-05,
      "loss": 0.07383899688720703,
      "step": 12100
    },
    {
      "epoch": 1.4274486605256487,
      "grad_norm": 0.7534876465797424,
      "learning_rate": 1.431788931788932e-05,
      "loss": 0.07853510379791259,
      "step": 12200
    },
    {
      "epoch": 1.4391499652211222,
      "grad_norm": 0.6730746626853943,
      "learning_rate": 1.4025389025389026e-05,
      "loss": 0.0697617483139038,
      "step": 12300
    },
    {
      "epoch": 1.4508512699165956,
      "grad_norm": 1.8400371074676514,
      "learning_rate": 1.3732888732888733e-05,
      "loss": 0.07848044872283935,
      "step": 12400
    },
    {
      "epoch": 1.4625525746120691,
      "grad_norm": 1.2114777565002441,
      "learning_rate": 1.3440388440388441e-05,
      "loss": 0.0783261775970459,
      "step": 12500
    },
    {
      "epoch": 1.4625525746120691,
      "eval_accuracy": 0.9353818181818182,
      "eval_f1": 0.9834085799751036,
      "eval_loss": 0.013636507093906403,
      "eval_precision": 0.9859303596264654,
      "eval_recall": 0.9808996676591591,
      "eval_runtime": 167.3633,
      "eval_samples_per_second": 164.313,
      "eval_steps_per_second": 5.139,
      "step": 12500
    },
    {
      "epoch": 1.4742538793075428,
      "grad_norm": 1.7295293807983398,
      "learning_rate": 1.3147888147888148e-05,
      "loss": 0.074767746925354,
      "step": 12600
    },
    {
      "epoch": 1.4859551840030163,
      "grad_norm": 1.08072030544281,
      "learning_rate": 1.2855387855387857e-05,
      "loss": 0.07684030532836914,
      "step": 12700
    },
    {
      "epoch": 1.4976564886984898,
      "grad_norm": 1.334511637687683,
      "learning_rate": 1.2562887562887562e-05,
      "loss": 0.07815152645111084,
      "step": 12800
    },
    {
      "epoch": 1.5093577933939635,
      "grad_norm": 0.8732834458351135,
      "learning_rate": 1.227038727038727e-05,
      "loss": 0.07617097854614258,
      "step": 12900
    },
    {
      "epoch": 1.521059098089437,
      "grad_norm": 1.038492202758789,
      "learning_rate": 1.1977886977886979e-05,
      "loss": 0.07482788562774659,
      "step": 13000
    },
    {
      "epoch": 1.5327604027849104,
      "grad_norm": 1.1699777841567993,
      "learning_rate": 1.1685386685386686e-05,
      "loss": 0.07500550746917725,
      "step": 13100
    },
    {
      "epoch": 1.5444617074803841,
      "grad_norm": 1.1473757028579712,
      "learning_rate": 1.1392886392886394e-05,
      "loss": 0.07690254688262939,
      "step": 13200
    },
    {
      "epoch": 1.5561630121758576,
      "grad_norm": 1.6335910558700562,
      "learning_rate": 1.1100386100386101e-05,
      "loss": 0.07375136375427246,
      "step": 13300
    },
    {
      "epoch": 1.567864316871331,
      "grad_norm": 0.9858669638633728,
      "learning_rate": 1.0807885807885808e-05,
      "loss": 0.07300055027008057,
      "step": 13400
    },
    {
      "epoch": 1.5795656215668048,
      "grad_norm": 1.1223580837249756,
      "learning_rate": 1.0515385515385516e-05,
      "loss": 0.07348923683166504,
      "step": 13500
    },
    {
      "epoch": 1.5912669262622783,
      "grad_norm": 0.8121886253356934,
      "learning_rate": 1.0222885222885223e-05,
      "loss": 0.0721654510498047,
      "step": 13600
    },
    {
      "epoch": 1.6029682309577518,
      "grad_norm": 1.125582218170166,
      "learning_rate": 9.930384930384932e-06,
      "loss": 0.07356025695800782,
      "step": 13700
    },
    {
      "epoch": 1.6146695356532255,
      "grad_norm": 0.9660710692405701,
      "learning_rate": 9.637884637884638e-06,
      "loss": 0.07352369308471679,
      "step": 13800
    },
    {
      "epoch": 1.6263708403486987,
      "grad_norm": 0.9546118378639221,
      "learning_rate": 9.345384345384347e-06,
      "loss": 0.07006223201751709,
      "step": 13900
    },
    {
      "epoch": 1.6380721450441724,
      "grad_norm": 1.2664750814437866,
      "learning_rate": 9.052884052884054e-06,
      "loss": 0.07232100963592529,
      "step": 14000
    },
    {
      "epoch": 1.6497734497396461,
      "grad_norm": 1.087778925895691,
      "learning_rate": 8.76038376038376e-06,
      "loss": 0.07518599510192871,
      "step": 14100
    },
    {
      "epoch": 1.6614747544351194,
      "grad_norm": 1.0009450912475586,
      "learning_rate": 8.467883467883467e-06,
      "loss": 0.07395988464355469,
      "step": 14200
    },
    {
      "epoch": 1.673176059130593,
      "grad_norm": 1.052869200706482,
      "learning_rate": 8.175383175383176e-06,
      "loss": 0.07117973327636719,
      "step": 14300
    },
    {
      "epoch": 1.6848773638260666,
      "grad_norm": 0.9935372471809387,
      "learning_rate": 7.882882882882883e-06,
      "loss": 0.07157835006713867,
      "step": 14400
    },
    {
      "epoch": 1.69657866852154,
      "grad_norm": 0.8762065768241882,
      "learning_rate": 7.59038259038259e-06,
      "loss": 0.07200119018554688,
      "step": 14500
    },
    {
      "epoch": 1.7082799732170137,
      "grad_norm": 1.1860989332199097,
      "learning_rate": 7.297882297882298e-06,
      "loss": 0.06994849681854248,
      "step": 14600
    },
    {
      "epoch": 1.7199812779124872,
      "grad_norm": 0.7438328862190247,
      "learning_rate": 7.005382005382005e-06,
      "loss": 0.06839815139770508,
      "step": 14700
    },
    {
      "epoch": 1.7316825826079607,
      "grad_norm": 1.6703062057495117,
      "learning_rate": 6.712881712881713e-06,
      "loss": 0.07001969337463379,
      "step": 14800
    },
    {
      "epoch": 1.7433838873034344,
      "grad_norm": 1.143515706062317,
      "learning_rate": 6.42038142038142e-06,
      "loss": 0.07166263103485107,
      "step": 14900
    },
    {
      "epoch": 1.755085191998908,
      "grad_norm": 1.0320720672607422,
      "learning_rate": 6.127881127881129e-06,
      "loss": 0.0704725456237793,
      "step": 15000
    },
    {
      "epoch": 1.755085191998908,
      "eval_accuracy": 0.9399272727272727,
      "eval_f1": 0.9843185306203277,
      "eval_loss": 0.012572239153087139,
      "eval_precision": 0.9860882072137978,
      "eval_recall": 0.9825551945244066,
      "eval_runtime": 207.4736,
      "eval_samples_per_second": 132.547,
      "eval_steps_per_second": 4.145,
      "step": 15000
    },
    {
      "epoch": 1.7667864966943814,
      "grad_norm": 0.8305580019950867,
      "learning_rate": 5.8353808353808354e-06,
      "loss": 0.07156490802764892,
      "step": 15100
    },
    {
      "epoch": 1.778487801389855,
      "grad_norm": 1.298708438873291,
      "learning_rate": 5.542880542880543e-06,
      "loss": 0.06973484516143799,
      "step": 15200
    },
    {
      "epoch": 1.7901891060853286,
      "grad_norm": 0.8593277931213379,
      "learning_rate": 5.250380250380251e-06,
      "loss": 0.06879038333892823,
      "step": 15300
    },
    {
      "epoch": 1.801890410780802,
      "grad_norm": 0.732769787311554,
      "learning_rate": 4.9578799578799576e-06,
      "loss": 0.06908240318298339,
      "step": 15400
    },
    {
      "epoch": 1.8135917154762757,
      "grad_norm": 1.3583112955093384,
      "learning_rate": 4.665379665379665e-06,
      "loss": 0.07114370822906495,
      "step": 15500
    },
    {
      "epoch": 1.825293020171749,
      "grad_norm": 0.9253562092781067,
      "learning_rate": 4.372879372879373e-06,
      "loss": 0.07082613945007324,
      "step": 15600
    },
    {
      "epoch": 1.8369943248672227,
      "grad_norm": 1.340505599975586,
      "learning_rate": 4.0803790803790806e-06,
      "loss": 0.06995931625366211,
      "step": 15700
    },
    {
      "epoch": 1.8486956295626964,
      "grad_norm": 0.9078701734542847,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.06670016288757324,
      "step": 15800
    },
    {
      "epoch": 1.8603969342581697,
      "grad_norm": 1.2157623767852783,
      "learning_rate": 3.495378495378496e-06,
      "loss": 0.0690723991394043,
      "step": 15900
    },
    {
      "epoch": 1.8720982389536434,
      "grad_norm": 1.7708772420883179,
      "learning_rate": 3.202878202878203e-06,
      "loss": 0.06770940780639649,
      "step": 16000
    },
    {
      "epoch": 1.8837995436491168,
      "grad_norm": 0.976672887802124,
      "learning_rate": 2.9103779103779103e-06,
      "loss": 0.0646241569519043,
      "step": 16100
    },
    {
      "epoch": 1.8955008483445903,
      "grad_norm": 1.7383304834365845,
      "learning_rate": 2.617877617877618e-06,
      "loss": 0.06627600193023682,
      "step": 16200
    },
    {
      "epoch": 1.907202153040064,
      "grad_norm": 0.8907257318496704,
      "learning_rate": 2.3253773253773257e-06,
      "loss": 0.06847190380096435,
      "step": 16300
    },
    {
      "epoch": 1.9189034577355375,
      "grad_norm": 0.7403037548065186,
      "learning_rate": 2.032877032877033e-06,
      "loss": 0.06623115539550781,
      "step": 16400
    },
    {
      "epoch": 1.930604762431011,
      "grad_norm": 1.0598572492599487,
      "learning_rate": 1.7403767403767406e-06,
      "loss": 0.06684101104736329,
      "step": 16500
    },
    {
      "epoch": 1.9423060671264847,
      "grad_norm": 1.2067943811416626,
      "learning_rate": 1.447876447876448e-06,
      "loss": 0.06935319423675537,
      "step": 16600
    },
    {
      "epoch": 1.9540073718219582,
      "grad_norm": 0.9936091899871826,
      "learning_rate": 1.1553761553761555e-06,
      "loss": 0.06889093399047852,
      "step": 16700
    },
    {
      "epoch": 1.9657086765174316,
      "grad_norm": 1.5107425451278687,
      "learning_rate": 8.628758628758629e-07,
      "loss": 0.07209495544433593,
      "step": 16800
    },
    {
      "epoch": 1.9774099812129053,
      "grad_norm": 1.0668072700500488,
      "learning_rate": 5.703755703755704e-07,
      "loss": 0.06988236904144288,
      "step": 16900
    },
    {
      "epoch": 1.9891112859083788,
      "grad_norm": 1.113166093826294,
      "learning_rate": 2.7787527787527786e-07,
      "loss": 0.06924228668212891,
      "step": 17000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9411636363636363,
      "eval_f1": 0.9845099349219312,
      "eval_loss": 0.012292231433093548,
      "eval_precision": 0.9859127008710089,
      "eval_recall": 0.9831111550388555,
      "eval_runtime": 183.6292,
      "eval_samples_per_second": 149.758,
      "eval_steps_per_second": 4.683,
      "step": 17094
    },
    {
      "epoch": 2.0,
      "step": 17094,
      "total_flos": 1.9402797892099978e+18,
      "train_loss": 0.08505657710317173,
      "train_runtime": 156175.5955,
      "train_samples_per_second": 63.038,
      "train_steps_per_second": 0.109
    }
  ],
  "logging_steps": 100,
  "max_steps": 17094,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9402797892099978e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}