{
  "best_global_step": 8000,
  "best_metric": 0.09730422496795654,
  "best_model_checkpoint": "./mt5_latin_punctuator_large/checkpoint-8000",
  "epoch": 1.6045835213880948,
  "eval_steps": 1000,
  "global_step": 8000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020059174564966652,
      "grad_norm": 13.09343147277832,
      "learning_rate": 4.9669073405535504e-05,
      "loss": 15.4848,
      "step": 100
    },
    {
      "epoch": 0.040118349129933305,
      "grad_norm": 0.4526735842227936,
      "learning_rate": 4.9334804118197625e-05,
      "loss": 0.66,
      "step": 200
    },
    {
      "epoch": 0.060177523694899954,
      "grad_norm": 0.4390902817249298,
      "learning_rate": 4.900053483085975e-05,
      "loss": 0.385,
      "step": 300
    },
    {
      "epoch": 0.08023669825986661,
      "grad_norm": 0.3624674677848816,
      "learning_rate": 4.866626554352187e-05,
      "loss": 0.3017,
      "step": 400
    },
    {
      "epoch": 0.10029587282483325,
      "grad_norm": 0.2848065197467804,
      "learning_rate": 4.833199625618399e-05,
      "loss": 0.2648,
      "step": 500
    },
    {
      "epoch": 0.12035504738979991,
      "grad_norm": 0.2836224138736725,
      "learning_rate": 4.7997726968846105e-05,
      "loss": 0.2419,
      "step": 600
    },
    {
      "epoch": 0.14041422195476655,
      "grad_norm": 0.3000536561012268,
      "learning_rate": 4.7663457681508226e-05,
      "loss": 0.2238,
      "step": 700
    },
    {
      "epoch": 0.16047339651973322,
      "grad_norm": 0.6995307803153992,
      "learning_rate": 4.732918839417035e-05,
      "loss": 0.2157,
      "step": 800
    },
    {
      "epoch": 0.18053257108469986,
      "grad_norm": 0.1916164755821228,
      "learning_rate": 4.699491910683247e-05,
      "loss": 0.2061,
      "step": 900
    },
    {
      "epoch": 0.2005917456496665,
      "grad_norm": 0.3005019426345825,
      "learning_rate": 4.666064981949459e-05,
      "loss": 0.2001,
      "step": 1000
    },
    {
      "epoch": 0.2005917456496665,
      "eval_loss": 0.1447821706533432,
      "eval_runtime": 687.5913,
      "eval_samples_per_second": 25.778,
      "eval_steps_per_second": 6.446,
      "step": 1000
    },
    {
      "epoch": 0.22065092021463317,
      "grad_norm": 0.34013351798057556,
      "learning_rate": 4.632638053215671e-05,
      "loss": 0.1911,
      "step": 1100
    },
    {
      "epoch": 0.24071009477959981,
      "grad_norm": 0.19066131114959717,
      "learning_rate": 4.5992111244818834e-05,
      "loss": 0.1868,
      "step": 1200
    },
    {
      "epoch": 0.26076926934456646,
      "grad_norm": 0.1935589760541916,
      "learning_rate": 4.565784195748095e-05,
      "loss": 0.1828,
      "step": 1300
    },
    {
      "epoch": 0.2808284439095331,
      "grad_norm": 0.31047841906547546,
      "learning_rate": 4.532357267014307e-05,
      "loss": 0.1798,
      "step": 1400
    },
    {
      "epoch": 0.3008876184744998,
      "grad_norm": 0.24223153293132782,
      "learning_rate": 4.498930338280519e-05,
      "loss": 0.1751,
      "step": 1500
    },
    {
      "epoch": 0.32094679303946644,
      "grad_norm": 1.5393741130828857,
      "learning_rate": 4.465503409546731e-05,
      "loss": 0.1704,
      "step": 1600
    },
    {
      "epoch": 0.3410059676044331,
      "grad_norm": 0.21514640748500824,
      "learning_rate": 4.4320764808129435e-05,
      "loss": 0.1689,
      "step": 1700
    },
    {
      "epoch": 0.3610651421693997,
      "grad_norm": 0.17480678856372833,
      "learning_rate": 4.3986495520791556e-05,
      "loss": 0.1664,
      "step": 1800
    },
    {
      "epoch": 0.38112431673436636,
      "grad_norm": 0.1928788721561432,
      "learning_rate": 4.365222623345368e-05,
      "loss": 0.1646,
      "step": 1900
    },
    {
      "epoch": 0.401183491299333,
      "grad_norm": 0.20150336623191833,
      "learning_rate": 4.331795694611579e-05,
      "loss": 0.1616,
      "step": 2000
    },
    {
      "epoch": 0.401183491299333,
      "eval_loss": 0.11908746510744095,
      "eval_runtime": 687.2579,
      "eval_samples_per_second": 25.791,
      "eval_steps_per_second": 6.449,
      "step": 2000
    },
    {
      "epoch": 0.4212426658642997,
      "grad_norm": 0.17183753848075867,
      "learning_rate": 4.2983687658777914e-05,
      "loss": 0.1632,
      "step": 2100
    },
    {
      "epoch": 0.44130184042926635,
      "grad_norm": 0.2742299735546112,
      "learning_rate": 4.2649418371440035e-05,
      "loss": 0.1578,
      "step": 2200
    },
    {
      "epoch": 0.461361014994233,
      "grad_norm": 0.22588330507278442,
      "learning_rate": 4.231514908410216e-05,
      "loss": 0.1563,
      "step": 2300
    },
    {
      "epoch": 0.48142018955919963,
      "grad_norm": 0.25857874751091003,
      "learning_rate": 4.198087979676428e-05,
      "loss": 0.1536,
      "step": 2400
    },
    {
      "epoch": 0.5014793641241663,
      "grad_norm": 0.2725016474723816,
      "learning_rate": 4.16466105094264e-05,
      "loss": 0.155,
      "step": 2500
    },
    {
      "epoch": 0.5215385386891329,
      "grad_norm": 0.14976142346858978,
      "learning_rate": 4.131234122208852e-05,
      "loss": 0.1507,
      "step": 2600
    },
    {
      "epoch": 0.5415977132540996,
      "grad_norm": 0.16467268764972687,
      "learning_rate": 4.0978071934750636e-05,
      "loss": 0.1505,
      "step": 2700
    },
    {
      "epoch": 0.5616568878190662,
      "grad_norm": 0.16063468158245087,
      "learning_rate": 4.064380264741276e-05,
      "loss": 0.147,
      "step": 2800
    },
    {
      "epoch": 0.581716062384033,
      "grad_norm": 0.23703046143054962,
      "learning_rate": 4.030953336007488e-05,
      "loss": 0.1445,
      "step": 2900
    },
    {
      "epoch": 0.6017752369489996,
      "grad_norm": 0.194139301776886,
      "learning_rate": 3.9975264072737e-05,
      "loss": 0.1444,
      "step": 3000
    },
    {
      "epoch": 0.6017752369489996,
      "eval_loss": 0.11365870386362076,
      "eval_runtime": 687.3052,
      "eval_samples_per_second": 25.789,
      "eval_steps_per_second": 6.448,
      "step": 3000
    },
    {
      "epoch": 0.6218344115139662,
      "grad_norm": 0.2936673164367676,
      "learning_rate": 3.964099478539912e-05,
      "loss": 0.1443,
      "step": 3100
    },
    {
      "epoch": 0.6418935860789329,
      "grad_norm": 0.15139873325824738,
      "learning_rate": 3.9306725498061244e-05,
      "loss": 0.1415,
      "step": 3200
    },
    {
      "epoch": 0.6619527606438995,
      "grad_norm": 0.22842614352703094,
      "learning_rate": 3.8972456210723365e-05,
      "loss": 0.141,
      "step": 3300
    },
    {
      "epoch": 0.6820119352088662,
      "grad_norm": 0.17998695373535156,
      "learning_rate": 3.863818692338548e-05,
      "loss": 0.1423,
      "step": 3400
    },
    {
      "epoch": 0.7020711097738328,
      "grad_norm": 0.18952590227127075,
      "learning_rate": 3.83039176360476e-05,
      "loss": 0.1388,
      "step": 3500
    },
    {
      "epoch": 0.7221302843387994,
      "grad_norm": 0.11938633769750595,
      "learning_rate": 3.796964834870972e-05,
      "loss": 0.1378,
      "step": 3600
    },
    {
      "epoch": 0.7421894589037661,
      "grad_norm": 0.1671166867017746,
      "learning_rate": 3.7635379061371845e-05,
      "loss": 0.1389,
      "step": 3700
    },
    {
      "epoch": 0.7622486334687327,
      "grad_norm": 0.1272394061088562,
      "learning_rate": 3.7301109774033966e-05,
      "loss": 0.1362,
      "step": 3800
    },
    {
      "epoch": 0.7823078080336994,
      "grad_norm": 0.19626741111278534,
      "learning_rate": 3.696684048669609e-05,
      "loss": 0.1377,
      "step": 3900
    },
    {
      "epoch": 0.802366982598666,
      "grad_norm": 0.3008900284767151,
      "learning_rate": 3.663257119935821e-05,
      "loss": 0.1347,
      "step": 4000
    },
    {
      "epoch": 0.802366982598666,
      "eval_loss": 0.10825913399457932,
      "eval_runtime": 687.2417,
      "eval_samples_per_second": 25.792,
      "eval_steps_per_second": 6.449,
      "step": 4000
    },
    {
      "epoch": 0.8224261571636328,
      "grad_norm": 0.45567601919174194,
      "learning_rate": 3.6298301912020324e-05,
      "loss": 0.1363,
      "step": 4100
    },
    {
      "epoch": 0.8424853317285994,
      "grad_norm": 0.17759402096271515,
      "learning_rate": 3.5964032624682446e-05,
      "loss": 0.1358,
      "step": 4200
    },
    {
      "epoch": 0.862544506293566,
      "grad_norm": 0.15186358988285065,
      "learning_rate": 3.562976333734457e-05,
      "loss": 0.1365,
      "step": 4300
    },
    {
      "epoch": 0.8826036808585327,
      "grad_norm": 0.20942702889442444,
      "learning_rate": 3.529549405000669e-05,
      "loss": 0.1341,
      "step": 4400
    },
    {
      "epoch": 0.9026628554234993,
      "grad_norm": 0.37031808495521545,
      "learning_rate": 3.496122476266881e-05,
      "loss": 0.1325,
      "step": 4500
    },
    {
      "epoch": 0.922722029988466,
      "grad_norm": 0.13902556896209717,
      "learning_rate": 3.462695547533093e-05,
      "loss": 0.1305,
      "step": 4600
    },
    {
      "epoch": 0.9427812045534326,
      "grad_norm": 0.48744386434555054,
      "learning_rate": 3.429268618799305e-05,
      "loss": 0.1315,
      "step": 4700
    },
    {
      "epoch": 0.9628403791183993,
      "grad_norm": 0.164585679769516,
      "learning_rate": 3.395841690065517e-05,
      "loss": 0.1307,
      "step": 4800
    },
    {
      "epoch": 0.9828995536833659,
      "grad_norm": 0.2665926218032837,
      "learning_rate": 3.362414761331729e-05,
      "loss": 0.1295,
      "step": 4900
    },
    {
      "epoch": 1.0028082844390953,
      "grad_norm": 0.16074395179748535,
      "learning_rate": 3.328987832597941e-05,
      "loss": 0.1285,
      "step": 5000
    },
    {
      "epoch": 1.0028082844390953,
      "eval_loss": 0.1043267473578453,
      "eval_runtime": 687.1542,
      "eval_samples_per_second": 25.795,
      "eval_steps_per_second": 6.45,
      "step": 5000
    },
    {
      "epoch": 1.022867459004062,
      "grad_norm": 0.20015545189380646,
      "learning_rate": 3.295560903864153e-05,
      "loss": 0.1275,
      "step": 5100
    },
    {
      "epoch": 1.0429266335690286,
      "grad_norm": 0.13576115667819977,
      "learning_rate": 3.2621339751303654e-05,
      "loss": 0.1269,
      "step": 5200
    },
    {
      "epoch": 1.0629858081339953,
      "grad_norm": 0.12735939025878906,
      "learning_rate": 3.2287070463965776e-05,
      "loss": 0.1265,
      "step": 5300
    },
    {
      "epoch": 1.0830449826989619,
      "grad_norm": 0.13942281901836395,
      "learning_rate": 3.19528011766279e-05,
      "loss": 0.1264,
      "step": 5400
    },
    {
      "epoch": 1.1031041572639286,
      "grad_norm": 0.15262341499328613,
      "learning_rate": 3.161853188929001e-05,
      "loss": 0.1253,
      "step": 5500
    },
    {
      "epoch": 1.1231633318288952,
      "grad_norm": 0.1289774477481842,
      "learning_rate": 3.1284262601952133e-05,
      "loss": 0.1252,
      "step": 5600
    },
    {
      "epoch": 1.143222506393862,
      "grad_norm": 0.13571390509605408,
      "learning_rate": 3.0949993314614255e-05,
      "loss": 0.1239,
      "step": 5700
    },
    {
      "epoch": 1.1632816809588284,
      "grad_norm": 0.13661526143550873,
      "learning_rate": 3.0615724027276377e-05,
      "loss": 0.125,
      "step": 5800
    },
    {
      "epoch": 1.1833408555237952,
      "grad_norm": 0.20611687004566193,
      "learning_rate": 3.0281454739938498e-05,
      "loss": 0.1242,
      "step": 5900
    },
    {
      "epoch": 1.203400030088762,
      "grad_norm": 0.12380609661340714,
      "learning_rate": 2.994718545260062e-05,
      "loss": 0.1231,
      "step": 6000
    },
    {
      "epoch": 1.203400030088762,
      "eval_loss": 0.10073110461235046,
      "eval_runtime": 687.1346,
      "eval_samples_per_second": 25.796,
      "eval_steps_per_second": 6.45,
      "step": 6000
    },
    {
      "epoch": 1.2234592046537285,
      "grad_norm": 0.1408674120903015,
      "learning_rate": 2.9612916165262738e-05,
      "loss": 0.1245,
      "step": 6100
    },
    {
      "epoch": 1.2435183792186952,
      "grad_norm": 0.14142949879169464,
      "learning_rate": 2.927864687792486e-05,
      "loss": 0.1218,
      "step": 6200
    },
    {
      "epoch": 1.2635775537836618,
      "grad_norm": 0.13047949969768524,
      "learning_rate": 2.894437759058698e-05,
      "loss": 0.121,
      "step": 6300
    },
    {
      "epoch": 1.2836367283486285,
      "grad_norm": 5.7425217628479,
      "learning_rate": 2.86101083032491e-05,
      "loss": 0.1207,
      "step": 6400
    },
    {
      "epoch": 1.303695902913595,
      "grad_norm": 0.28052738308906555,
      "learning_rate": 2.827583901591122e-05,
      "loss": 0.12,
      "step": 6500
    },
    {
      "epoch": 1.3237550774785618,
      "grad_norm": 0.13514311611652374,
      "learning_rate": 2.7941569728573342e-05,
      "loss": 0.1199,
      "step": 6600
    },
    {
      "epoch": 1.3438142520435283,
      "grad_norm": 0.14283640682697296,
      "learning_rate": 2.7607300441235463e-05,
      "loss": 0.1197,
      "step": 6700
    },
    {
      "epoch": 1.363873426608495,
      "grad_norm": 0.14133544266223907,
      "learning_rate": 2.727303115389758e-05,
      "loss": 0.1201,
      "step": 6800
    },
    {
      "epoch": 1.3839326011734618,
      "grad_norm": 0.20595553517341614,
      "learning_rate": 2.6938761866559703e-05,
      "loss": 0.1213,
      "step": 6900
    },
    {
      "epoch": 1.4039917757384284,
      "grad_norm": 0.133372962474823,
      "learning_rate": 2.6604492579221825e-05,
      "loss": 0.118,
      "step": 7000
    },
    {
      "epoch": 1.4039917757384284,
      "eval_loss": 0.09819206595420837,
      "eval_runtime": 687.1022,
      "eval_samples_per_second": 25.797,
      "eval_steps_per_second": 6.45,
      "step": 7000
    },
    {
      "epoch": 1.424050950303395,
      "grad_norm": 0.21542303264141083,
      "learning_rate": 2.6270223291883943e-05,
      "loss": 0.1215,
      "step": 7100
    },
    {
      "epoch": 1.4441101248683617,
      "grad_norm": 0.24275696277618408,
      "learning_rate": 2.5935954004546064e-05,
      "loss": 0.1187,
      "step": 7200
    },
    {
      "epoch": 1.4641692994333284,
      "grad_norm": 0.14183971285820007,
      "learning_rate": 2.5601684717208186e-05,
      "loss": 0.1173,
      "step": 7300
    },
    {
      "epoch": 1.484228473998295,
      "grad_norm": 0.11123021692037582,
      "learning_rate": 2.5267415429870307e-05,
      "loss": 0.1167,
      "step": 7400
    },
    {
      "epoch": 1.5042876485632615,
      "grad_norm": 0.1129390299320221,
      "learning_rate": 2.4933146142532426e-05,
      "loss": 0.1196,
      "step": 7500
    },
    {
      "epoch": 1.5243468231282282,
      "grad_norm": 0.1165638417005539,
      "learning_rate": 2.4598876855194547e-05,
      "loss": 0.1186,
      "step": 7600
    },
    {
      "epoch": 1.544405997693195,
      "grad_norm": 0.3278215527534485,
      "learning_rate": 2.426460756785667e-05,
      "loss": 0.1161,
      "step": 7700
    },
    {
      "epoch": 1.5644651722581617,
      "grad_norm": 0.2158752679824829,
      "learning_rate": 2.3930338280518787e-05,
      "loss": 0.1184,
      "step": 7800
    },
    {
      "epoch": 1.5845243468231283,
      "grad_norm": 0.16784250736236572,
      "learning_rate": 2.3596068993180908e-05,
      "loss": 0.118,
      "step": 7900
    },
    {
      "epoch": 1.6045835213880948,
      "grad_norm": 0.16192170977592468,
      "learning_rate": 2.326179970584303e-05,
      "loss": 0.1154,
      "step": 8000
    },
    {
      "epoch": 1.6045835213880948,
      "eval_loss": 0.09730422496795654,
      "eval_runtime": 687.1621,
      "eval_samples_per_second": 25.794,
      "eval_steps_per_second": 6.45,
      "step": 8000
    }
  ],
  "logging_steps": 100,
  "max_steps": 14958,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5259044426479616e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}