{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 406,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024630541871921183,
      "grad_norm": 0.16799156367778778,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.8257,
      "step": 1
    },
    {
      "epoch": 0.012315270935960592,
      "grad_norm": 0.15671788156032562,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.7908,
      "step": 5
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 0.21884536743164062,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.8166,
      "step": 10
    },
    {
      "epoch": 0.03694581280788178,
      "grad_norm": 0.19219553470611572,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.7766,
      "step": 15
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 0.15735943615436554,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.7749,
      "step": 20
    },
    {
      "epoch": 0.06157635467980296,
      "grad_norm": 0.11656388640403748,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.754,
      "step": 25
    },
    {
      "epoch": 0.07389162561576355,
      "grad_norm": 0.11298099905252457,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.7451,
      "step": 30
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.11875681579113007,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7433,
      "step": 35
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.10648073256015778,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7462,
      "step": 40
    },
    {
      "epoch": 0.11083743842364532,
      "grad_norm": 0.10487455129623413,
      "learning_rate": 0.0001999407400739705,
      "loss": 0.7533,
      "step": 45
    },
    {
      "epoch": 0.12315270935960591,
      "grad_norm": 0.11339645087718964,
      "learning_rate": 0.00019970011699250152,
      "loss": 0.7331,
      "step": 50
    },
    {
      "epoch": 0.1354679802955665,
      "grad_norm": 0.11415703594684601,
      "learning_rate": 0.00019927487224577402,
      "loss": 0.7473,
      "step": 55
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 0.10474668443202972,
      "learning_rate": 0.0001986657932891657,
      "loss": 0.7294,
      "step": 60
    },
    {
      "epoch": 0.16009852216748768,
      "grad_norm": 0.11136909574270248,
      "learning_rate": 0.00019787400799669154,
      "loss": 0.7503,
      "step": 65
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.10277216881513596,
      "learning_rate": 0.00019690098257244064,
      "loss": 0.733,
      "step": 70
    },
    {
      "epoch": 0.18472906403940886,
      "grad_norm": 0.10170916467905045,
      "learning_rate": 0.00019574851883550395,
      "loss": 0.7473,
      "step": 75
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.09841552376747131,
      "learning_rate": 0.00019441875088341997,
      "loss": 0.7401,
      "step": 80
    },
    {
      "epoch": 0.20935960591133004,
      "grad_norm": 0.09754014015197754,
      "learning_rate": 0.00019291414114031743,
      "loss": 0.7451,
      "step": 85
    },
    {
      "epoch": 0.22167487684729065,
      "grad_norm": 0.10321612656116486,
      "learning_rate": 0.00019123747579707275,
      "loss": 0.7398,
      "step": 90
    },
    {
      "epoch": 0.23399014778325122,
      "grad_norm": 0.10410084575414658,
      "learning_rate": 0.0001893918596519257,
      "loss": 0.7282,
      "step": 95
    },
    {
      "epoch": 0.24630541871921183,
      "grad_norm": 0.10551038384437561,
      "learning_rate": 0.00018738071036110808,
      "loss": 0.7164,
      "step": 100
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.09691344201564789,
      "learning_rate": 0.00018520775211013093,
      "loss": 0.7194,
      "step": 105
    },
    {
      "epoch": 0.270935960591133,
      "grad_norm": 0.10166921466588974,
      "learning_rate": 0.00018287700871745036,
      "loss": 0.7343,
      "step": 110
    },
    {
      "epoch": 0.2832512315270936,
      "grad_norm": 0.10552408546209335,
      "learning_rate": 0.00018039279618328212,
      "loss": 0.7539,
      "step": 115
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.12299532443284988,
      "learning_rate": 0.0001777597146973627,
      "loss": 0.7591,
      "step": 120
    },
    {
      "epoch": 0.3078817733990148,
      "grad_norm": 0.10212723165750504,
      "learning_rate": 0.00017498264012045687,
      "loss": 0.7412,
      "step": 125
    },
    {
      "epoch": 0.32019704433497537,
      "grad_norm": 0.10583320260047913,
      "learning_rate": 0.00017206671495538612,
      "loss": 0.7416,
      "step": 130
    },
    {
      "epoch": 0.33251231527093594,
      "grad_norm": 0.09599178284406662,
      "learning_rate": 0.0001690173388242972,
      "loss": 0.7352,
      "step": 135
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.10376348346471786,
      "learning_rate": 0.0001658401584698049,
      "loss": 0.7307,
      "step": 140
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.10012812167406082,
      "learning_rate": 0.00016254105729852464,
      "loss": 0.7561,
      "step": 145
    },
    {
      "epoch": 0.3694581280788177,
      "grad_norm": 0.09958042204380035,
      "learning_rate": 0.00015912614448635782,
      "loss": 0.7327,
      "step": 150
    },
    {
      "epoch": 0.3817733990147783,
      "grad_norm": 0.10132339596748352,
      "learning_rate": 0.00015560174366570446,
      "loss": 0.7233,
      "step": 155
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.09845075756311417,
      "learning_rate": 0.0001519743812155516,
      "loss": 0.7478,
      "step": 160
    },
    {
      "epoch": 0.4064039408866995,
      "grad_norm": 0.10067222267389297,
      "learning_rate": 0.00014825077417612186,
      "loss": 0.7427,
      "step": 165
    },
    {
      "epoch": 0.4187192118226601,
      "grad_norm": 0.09790223836898804,
      "learning_rate": 0.00014443781781046136,
      "loss": 0.7338,
      "step": 170
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.10275407880544662,
      "learning_rate": 0.00014054257283599973,
      "loss": 0.7406,
      "step": 175
    },
    {
      "epoch": 0.4433497536945813,
      "grad_norm": 0.09913714975118637,
      "learning_rate": 0.00013657225234972695,
      "loss": 0.7315,
      "step": 180
    },
    {
      "epoch": 0.45566502463054187,
      "grad_norm": 0.09389715641736984,
      "learning_rate": 0.00013253420847119803,
      "loss": 0.7503,
      "step": 185
    },
    {
      "epoch": 0.46798029556650245,
      "grad_norm": 0.10459800809621811,
      "learning_rate": 0.0001284359187281004,
      "loss": 0.7327,
      "step": 190
    },
    {
      "epoch": 0.4802955665024631,
      "grad_norm": 0.11382940411567688,
      "learning_rate": 0.0001242849722095936,
      "loss": 0.7303,
      "step": 195
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.11223295331001282,
      "learning_rate": 0.00012008905551306356,
      "loss": 0.7081,
      "step": 200
    },
    {
      "epoch": 0.5049261083743842,
      "grad_norm": 0.10458631068468094,
      "learning_rate": 0.00011585593851031347,
      "loss": 0.7293,
      "step": 205
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.11634813249111176,
      "learning_rate": 0.00011159345995955006,
      "loss": 0.7379,
      "step": 210
    },
    {
      "epoch": 0.5295566502463054,
      "grad_norm": 0.0983707383275032,
      "learning_rate": 0.00010730951298980776,
      "loss": 0.7405,
      "step": 215
    },
    {
      "epoch": 0.541871921182266,
      "grad_norm": 0.10358725488185883,
      "learning_rate": 0.00010301203048469083,
      "loss": 0.7399,
      "step": 220
    },
    {
      "epoch": 0.5541871921182266,
      "grad_norm": 0.10414719581604004,
      "learning_rate": 9.870897039249911e-05,
      "loss": 0.7263,
      "step": 225
    },
    {
      "epoch": 0.5665024630541872,
      "grad_norm": 0.10104504227638245,
      "learning_rate": 9.440830098993969e-05,
      "loss": 0.7339,
      "step": 230
    },
    {
      "epoch": 0.5788177339901478,
      "grad_norm": 0.10356930643320084,
      "learning_rate": 9.011798612671286e-05,
      "loss": 0.7361,
      "step": 235
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.0979054793715477,
      "learning_rate": 8.58459704782957e-05,
      "loss": 0.7392,
      "step": 240
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.10039085149765015,
      "learning_rate": 8.160016483423199e-05,
      "loss": 0.7433,
      "step": 245
    },
    {
      "epoch": 0.6157635467980296,
      "grad_norm": 0.1000097244977951,
      "learning_rate": 7.738843144917119e-05,
      "loss": 0.7296,
      "step": 250
    },
    {
      "epoch": 0.6280788177339901,
      "grad_norm": 0.10497615486383438,
      "learning_rate": 7.321856948378259e-05,
      "loss": 0.7244,
      "step": 255
    },
    {
      "epoch": 0.6403940886699507,
      "grad_norm": 0.09603270888328552,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.7364,
      "step": 260
    },
    {
      "epoch": 0.6527093596059114,
      "grad_norm": 0.099782295525074,
      "learning_rate": 6.503525447487715e-05,
      "loss": 0.7129,
      "step": 265
    },
    {
      "epoch": 0.6650246305418719,
      "grad_norm": 0.11032257229089737,
      "learning_rate": 6.103695504692122e-05,
      "loss": 0.7131,
      "step": 270
    },
    {
      "epoch": 0.6773399014778325,
      "grad_norm": 0.09867917001247406,
      "learning_rate": 5.7110806208751655e-05,
      "loss": 0.7369,
      "step": 275
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.10074910521507263,
      "learning_rate": 5.326407828419979e-05,
      "loss": 0.7263,
      "step": 280
    },
    {
      "epoch": 0.7019704433497537,
      "grad_norm": 0.09996320307254791,
      "learning_rate": 4.9503894527847964e-05,
      "loss": 0.7246,
      "step": 285
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.10240605473518372,
      "learning_rate": 4.583721793440188e-05,
      "loss": 0.7616,
      "step": 290
    },
    {
      "epoch": 0.7266009852216748,
      "grad_norm": 0.09451171010732651,
      "learning_rate": 4.227083834482728e-05,
      "loss": 0.7278,
      "step": 295
    },
    {
      "epoch": 0.7389162561576355,
      "grad_norm": 0.09990745037794113,
      "learning_rate": 3.881135987312757e-05,
      "loss": 0.7312,
      "step": 300
    },
    {
      "epoch": 0.7512315270935961,
      "grad_norm": 0.10192150622606277,
      "learning_rate": 3.546518867704499e-05,
      "loss": 0.7413,
      "step": 305
    },
    {
      "epoch": 0.7635467980295566,
      "grad_norm": 0.10223990678787231,
      "learning_rate": 3.223852109533112e-05,
      "loss": 0.7329,
      "step": 310
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.1019340381026268,
      "learning_rate": 2.9137332173554043e-05,
      "loss": 0.7184,
      "step": 315
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.1070074737071991,
      "learning_rate": 2.616736459968936e-05,
      "loss": 0.7209,
      "step": 320
    },
    {
      "epoch": 0.8004926108374384,
      "grad_norm": 0.09866880625486374,
      "learning_rate": 2.33341180699841e-05,
      "loss": 0.725,
      "step": 325
    },
    {
      "epoch": 0.812807881773399,
      "grad_norm": 0.09677723795175552,
      "learning_rate": 2.0642839104785272e-05,
      "loss": 0.7291,
      "step": 330
    },
    {
      "epoch": 0.8251231527093597,
      "grad_norm": 0.10278508812189102,
      "learning_rate": 1.8098511333192024e-05,
      "loss": 0.746,
      "step": 335
    },
    {
      "epoch": 0.8374384236453202,
      "grad_norm": 0.09942112863063812,
      "learning_rate": 1.570584626452173e-05,
      "loss": 0.7322,
      "step": 340
    },
    {
      "epoch": 0.8497536945812808,
      "grad_norm": 0.0949101597070694,
      "learning_rate": 1.3469274563679402e-05,
      "loss": 0.7159,
      "step": 345
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.10628760606050491,
      "learning_rate": 1.1392937846586215e-05,
      "loss": 0.7314,
      "step": 350
    },
    {
      "epoch": 0.874384236453202,
      "grad_norm": 0.09933866560459137,
      "learning_rate": 9.48068101086026e-06,
      "loss": 0.7284,
      "step": 355
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.09737644344568253,
      "learning_rate": 7.736045115951251e-06,
      "loss": 0.7392,
      "step": 360
    },
    {
      "epoch": 0.8990147783251231,
      "grad_norm": 0.1012764498591423,
      "learning_rate": 6.16226082591359e-06,
      "loss": 0.7201,
      "step": 365
    },
    {
      "epoch": 0.9113300492610837,
      "grad_norm": 0.10004229843616486,
      "learning_rate": 4.762242426960262e-06,
      "loss": 0.7329,
      "step": 370
    },
    {
      "epoch": 0.9236453201970444,
      "grad_norm": 0.10334964096546173,
      "learning_rate": 3.5385824308756587e-06,
      "loss": 0.7102,
      "step": 375
    },
    {
      "epoch": 0.9359605911330049,
      "grad_norm": 0.10853207111358643,
      "learning_rate": 2.493546774280531e-06,
      "loss": 0.7394,
      "step": 380
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.10269072651863098,
      "learning_rate": 1.6290706226390285e-06,
      "loss": 0.7248,
      "step": 385
    },
    {
      "epoch": 0.9605911330049262,
      "grad_norm": 0.10327539592981339,
      "learning_rate": 9.46754786777726e-07,
      "loss": 0.7131,
      "step": 390
    },
    {
      "epoch": 0.9729064039408867,
      "grad_norm": 0.09245247393846512,
      "learning_rate": 4.4786275855247527e-07,
      "loss": 0.7229,
      "step": 395
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.0999683290719986,
      "learning_rate": 1.333183711524133e-07,
      "loss": 0.7208,
      "step": 400
    },
    {
      "epoch": 0.9975369458128078,
      "grad_norm": 0.09550279378890991,
      "learning_rate": 3.7040883734462683e-09,
      "loss": 0.7017,
      "step": 405
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 951.7122,
      "eval_samples_per_second": 1.214,
      "eval_steps_per_second": 0.304,
      "step": 406
    },
    {
      "epoch": 1.0,
      "step": 406,
      "total_flos": 2.1037204062286643e+18,
      "train_loss": 0.18958791855520804,
      "train_runtime": 18340.7521,
      "train_samples_per_second": 5.667,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 5,
  "max_steps": 406,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1037204062286643e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}