{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 398,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01256281407035176,
      "grad_norm": 41.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.908399200439453,
      "step": 5
    },
    {
      "epoch": 0.02512562814070352,
      "grad_norm": 10.25,
      "learning_rate": 9e-06,
      "loss": 2.7105648040771486,
      "step": 10
    },
    {
      "epoch": 0.03768844221105527,
      "grad_norm": 7.5625,
      "learning_rate": 1.4e-05,
      "loss": 2.501449775695801,
      "step": 15
    },
    {
      "epoch": 0.05025125628140704,
      "grad_norm": 3.875,
      "learning_rate": 1.9e-05,
      "loss": 2.185238838195801,
      "step": 20
    },
    {
      "epoch": 0.06281407035175879,
      "grad_norm": 3.578125,
      "learning_rate": 1.978835978835979e-05,
      "loss": 1.959276008605957,
      "step": 25
    },
    {
      "epoch": 0.07537688442211055,
      "grad_norm": 2.5625,
      "learning_rate": 1.9523809523809524e-05,
      "loss": 1.8451156616210938,
      "step": 30
    },
    {
      "epoch": 0.08793969849246232,
      "grad_norm": 2.34375,
      "learning_rate": 1.925925925925926e-05,
      "loss": 1.7816888809204101,
      "step": 35
    },
    {
      "epoch": 0.10050251256281408,
      "grad_norm": 3.046875,
      "learning_rate": 1.8994708994708996e-05,
      "loss": 1.721405601501465,
      "step": 40
    },
    {
      "epoch": 0.11306532663316583,
      "grad_norm": 2.5,
      "learning_rate": 1.8730158730158732e-05,
      "loss": 1.7366134643554687,
      "step": 45
    },
    {
      "epoch": 0.12562814070351758,
      "grad_norm": 2.109375,
      "learning_rate": 1.8465608465608468e-05,
      "loss": 1.678215217590332,
      "step": 50
    },
    {
      "epoch": 0.13819095477386933,
      "grad_norm": 2.703125,
      "learning_rate": 1.82010582010582e-05,
      "loss": 1.6803802490234374,
      "step": 55
    },
    {
      "epoch": 0.1507537688442211,
      "grad_norm": 2.109375,
      "learning_rate": 1.7936507936507937e-05,
      "loss": 1.6128549575805664,
      "step": 60
    },
    {
      "epoch": 0.16331658291457288,
      "grad_norm": 2.484375,
      "learning_rate": 1.7671957671957673e-05,
      "loss": 1.6951425552368165,
      "step": 65
    },
    {
      "epoch": 0.17587939698492464,
      "grad_norm": 2.078125,
      "learning_rate": 1.740740740740741e-05,
      "loss": 1.662872886657715,
      "step": 70
    },
    {
      "epoch": 0.1884422110552764,
      "grad_norm": 2.296875,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 1.6751840591430665,
      "step": 75
    },
    {
      "epoch": 0.20100502512562815,
      "grad_norm": 2.859375,
      "learning_rate": 1.687830687830688e-05,
      "loss": 1.7192909240722656,
      "step": 80
    },
    {
      "epoch": 0.2135678391959799,
      "grad_norm": 2.59375,
      "learning_rate": 1.6613756613756614e-05,
      "loss": 1.5769388198852539,
      "step": 85
    },
    {
      "epoch": 0.22613065326633167,
      "grad_norm": 2.390625,
      "learning_rate": 1.634920634920635e-05,
      "loss": 1.5676084518432618,
      "step": 90
    },
    {
      "epoch": 0.23869346733668342,
      "grad_norm": 2.5625,
      "learning_rate": 1.6084656084656086e-05,
      "loss": 1.6453401565551757,
      "step": 95
    },
    {
      "epoch": 0.25125628140703515,
      "grad_norm": 2.375,
      "learning_rate": 1.5820105820105822e-05,
      "loss": 1.5511817932128906,
      "step": 100
    },
    {
      "epoch": 0.2638190954773869,
      "grad_norm": 2.546875,
      "learning_rate": 1.555555555555556e-05,
      "loss": 1.5268743515014649,
      "step": 105
    },
    {
      "epoch": 0.27638190954773867,
      "grad_norm": 2.828125,
      "learning_rate": 1.529100529100529e-05,
      "loss": 1.530481719970703,
      "step": 110
    },
    {
      "epoch": 0.2889447236180904,
      "grad_norm": 2.234375,
      "learning_rate": 1.5026455026455027e-05,
      "loss": 1.5688664436340332,
      "step": 115
    },
    {
      "epoch": 0.3015075376884422,
      "grad_norm": 2.359375,
      "learning_rate": 1.4761904761904763e-05,
      "loss": 1.5435178756713868,
      "step": 120
    },
    {
      "epoch": 0.314070351758794,
      "grad_norm": 1.9609375,
      "learning_rate": 1.44973544973545e-05,
      "loss": 1.622827911376953,
      "step": 125
    },
    {
      "epoch": 0.32663316582914576,
      "grad_norm": 2.421875,
      "learning_rate": 1.4232804232804234e-05,
      "loss": 1.534958839416504,
      "step": 130
    },
    {
      "epoch": 0.3391959798994975,
      "grad_norm": 2.328125,
      "learning_rate": 1.3968253968253968e-05,
      "loss": 1.5641840934753417,
      "step": 135
    },
    {
      "epoch": 0.35175879396984927,
      "grad_norm": 1.8359375,
      "learning_rate": 1.3703703703703706e-05,
      "loss": 1.6128816604614258,
      "step": 140
    },
    {
      "epoch": 0.36432160804020103,
      "grad_norm": 1.96875,
      "learning_rate": 1.343915343915344e-05,
      "loss": 1.5031535148620605,
      "step": 145
    },
    {
      "epoch": 0.3768844221105528,
      "grad_norm": 2.40625,
      "learning_rate": 1.3174603174603176e-05,
      "loss": 1.5201923370361328,
      "step": 150
    },
    {
      "epoch": 0.38944723618090454,
      "grad_norm": 2.171875,
      "learning_rate": 1.291005291005291e-05,
      "loss": 1.5293109893798829,
      "step": 155
    },
    {
      "epoch": 0.4020100502512563,
      "grad_norm": 2.375,
      "learning_rate": 1.2645502645502647e-05,
      "loss": 1.532673454284668,
      "step": 160
    },
    {
      "epoch": 0.41457286432160806,
      "grad_norm": 2.046875,
      "learning_rate": 1.2380952380952383e-05,
      "loss": 1.5430846214294434,
      "step": 165
    },
    {
      "epoch": 0.4271356783919598,
      "grad_norm": 2.15625,
      "learning_rate": 1.2116402116402117e-05,
      "loss": 1.5211373329162599,
      "step": 170
    },
    {
      "epoch": 0.4396984924623116,
      "grad_norm": 2.328125,
      "learning_rate": 1.1851851851851852e-05,
      "loss": 1.5185907363891602,
      "step": 175
    },
    {
      "epoch": 0.45226130653266333,
      "grad_norm": 2.234375,
      "learning_rate": 1.158730158730159e-05,
      "loss": 1.4886056900024414,
      "step": 180
    },
    {
      "epoch": 0.4648241206030151,
      "grad_norm": 2.28125,
      "learning_rate": 1.1322751322751324e-05,
      "loss": 1.4682801246643067,
      "step": 185
    },
    {
      "epoch": 0.47738693467336685,
      "grad_norm": 4.34375,
      "learning_rate": 1.105820105820106e-05,
      "loss": 1.5117271423339844,
      "step": 190
    },
    {
      "epoch": 0.4899497487437186,
      "grad_norm": 2.265625,
      "learning_rate": 1.0793650793650794e-05,
      "loss": 1.544318389892578,
      "step": 195
    },
    {
      "epoch": 0.5025125628140703,
      "grad_norm": 2.21875,
      "learning_rate": 1.052910052910053e-05,
      "loss": 1.5679922103881836,
      "step": 200
    },
    {
      "epoch": 0.5150753768844221,
      "grad_norm": 2.1875,
      "learning_rate": 1.0264550264550266e-05,
      "loss": 1.5708157539367675,
      "step": 205
    },
    {
      "epoch": 0.5276381909547738,
      "grad_norm": 2.703125,
      "learning_rate": 1e-05,
      "loss": 1.449632453918457,
      "step": 210
    },
    {
      "epoch": 0.5402010050251256,
      "grad_norm": 2.03125,
      "learning_rate": 9.735449735449735e-06,
      "loss": 1.4999945640563965,
      "step": 215
    },
    {
      "epoch": 0.5527638190954773,
      "grad_norm": 2.4375,
      "learning_rate": 9.470899470899471e-06,
      "loss": 1.5098167419433595,
      "step": 220
    },
    {
      "epoch": 0.5653266331658291,
      "grad_norm": 1.8984375,
      "learning_rate": 9.206349206349207e-06,
      "loss": 1.4984207153320312,
      "step": 225
    },
    {
      "epoch": 0.5778894472361809,
      "grad_norm": 2.125,
      "learning_rate": 8.941798941798942e-06,
      "loss": 1.4724366188049316,
      "step": 230
    },
    {
      "epoch": 0.5904522613065326,
      "grad_norm": 2.09375,
      "learning_rate": 8.677248677248678e-06,
      "loss": 1.486234474182129,
      "step": 235
    },
    {
      "epoch": 0.6030150753768844,
      "grad_norm": 2.828125,
      "learning_rate": 8.412698412698414e-06,
      "loss": 1.5106399536132813,
      "step": 240
    },
    {
      "epoch": 0.6155778894472361,
      "grad_norm": 2.0625,
      "learning_rate": 8.148148148148148e-06,
      "loss": 1.5564719200134278,
      "step": 245
    },
    {
      "epoch": 0.628140703517588,
      "grad_norm": 2.25,
      "learning_rate": 7.883597883597884e-06,
      "loss": 1.480449390411377,
      "step": 250
    },
    {
      "epoch": 0.6407035175879398,
      "grad_norm": 2.046875,
      "learning_rate": 7.61904761904762e-06,
      "loss": 1.4469252586364747,
      "step": 255
    },
    {
      "epoch": 0.6532663316582915,
      "grad_norm": 1.75,
      "learning_rate": 7.354497354497355e-06,
      "loss": 1.4990968704223633,
      "step": 260
    },
    {
      "epoch": 0.6658291457286433,
      "grad_norm": 2.75,
      "learning_rate": 7.08994708994709e-06,
      "loss": 1.448952579498291,
      "step": 265
    },
    {
      "epoch": 0.678391959798995,
      "grad_norm": 2.359375,
      "learning_rate": 6.825396825396826e-06,
      "loss": 1.4773205757141112,
      "step": 270
    },
    {
      "epoch": 0.6909547738693468,
      "grad_norm": 2.6875,
      "learning_rate": 6.560846560846561e-06,
      "loss": 1.485036277770996,
      "step": 275
    },
    {
      "epoch": 0.7035175879396985,
      "grad_norm": 1.9140625,
      "learning_rate": 6.296296296296297e-06,
      "loss": 1.4918421745300292,
      "step": 280
    },
    {
      "epoch": 0.7160804020100503,
      "grad_norm": 2.1875,
      "learning_rate": 6.031746031746032e-06,
      "loss": 1.4894933700561523,
      "step": 285
    },
    {
      "epoch": 0.7286432160804021,
      "grad_norm": 2.578125,
      "learning_rate": 5.767195767195768e-06,
      "loss": 1.4480770111083985,
      "step": 290
    },
    {
      "epoch": 0.7412060301507538,
      "grad_norm": 1.9765625,
      "learning_rate": 5.502645502645503e-06,
      "loss": 1.4752997398376464,
      "step": 295
    },
    {
      "epoch": 0.7537688442211056,
      "grad_norm": 2.171875,
      "learning_rate": 5.2380952380952384e-06,
      "loss": 1.4711036682128906,
      "step": 300
    },
    {
      "epoch": 0.7663316582914573,
      "grad_norm": 3.109375,
      "learning_rate": 4.973544973544974e-06,
      "loss": 1.4894997596740722,
      "step": 305
    },
    {
      "epoch": 0.7788944723618091,
      "grad_norm": 1.921875,
      "learning_rate": 4.708994708994709e-06,
      "loss": 1.4980501174926757,
      "step": 310
    },
    {
      "epoch": 0.7914572864321608,
      "grad_norm": 2.046875,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.4688381195068358,
      "step": 315
    },
    {
      "epoch": 0.8040201005025126,
      "grad_norm": 2.546875,
      "learning_rate": 4.17989417989418e-06,
      "loss": 1.4227490425109863,
      "step": 320
    },
    {
      "epoch": 0.8165829145728644,
      "grad_norm": 2.359375,
      "learning_rate": 3.9153439153439155e-06,
      "loss": 1.5430548667907715,
      "step": 325
    },
    {
      "epoch": 0.8291457286432161,
      "grad_norm": 1.9921875,
      "learning_rate": 3.6507936507936507e-06,
      "loss": 1.4949950218200683,
      "step": 330
    },
    {
      "epoch": 0.8417085427135679,
      "grad_norm": 2.09375,
      "learning_rate": 3.3862433862433864e-06,
      "loss": 1.508356475830078,
      "step": 335
    },
    {
      "epoch": 0.8542713567839196,
      "grad_norm": 2.0625,
      "learning_rate": 3.1216931216931216e-06,
      "loss": 1.4609917640686034,
      "step": 340
    },
    {
      "epoch": 0.8668341708542714,
      "grad_norm": 2.15625,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.4494487762451171,
      "step": 345
    },
    {
      "epoch": 0.8793969849246231,
      "grad_norm": 2.1875,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 1.5313102722167968,
      "step": 350
    },
    {
      "epoch": 0.8919597989949749,
      "grad_norm": 2.265625,
      "learning_rate": 2.328042328042328e-06,
      "loss": 1.4682437896728515,
      "step": 355
    },
    {
      "epoch": 0.9045226130653267,
      "grad_norm": 2.125,
      "learning_rate": 2.0634920634920634e-06,
      "loss": 1.5278240203857423,
      "step": 360
    },
    {
      "epoch": 0.9170854271356784,
      "grad_norm": 2.25,
      "learning_rate": 1.798941798941799e-06,
      "loss": 1.4803818702697753,
      "step": 365
    },
    {
      "epoch": 0.9296482412060302,
      "grad_norm": 1.90625,
      "learning_rate": 1.5343915343915345e-06,
      "loss": 1.4913017272949218,
      "step": 370
    },
    {
      "epoch": 0.9422110552763819,
      "grad_norm": 2.421875,
      "learning_rate": 1.26984126984127e-06,
      "loss": 1.4437126159667968,
      "step": 375
    },
    {
      "epoch": 0.9547738693467337,
      "grad_norm": 2.4375,
      "learning_rate": 1.0052910052910054e-06,
      "loss": 1.4650879859924317,
      "step": 380
    },
    {
      "epoch": 0.9673366834170855,
      "grad_norm": 2.140625,
      "learning_rate": 7.407407407407407e-07,
      "loss": 1.54934663772583,
      "step": 385
    },
    {
      "epoch": 0.9798994974874372,
      "grad_norm": 2.984375,
      "learning_rate": 4.7619047619047623e-07,
      "loss": 1.4588896751403808,
      "step": 390
    },
    {
      "epoch": 0.992462311557789,
      "grad_norm": 2.578125,
      "learning_rate": 2.1164021164021165e-07,
      "loss": 1.4410962104797362,
      "step": 395
    },
    {
      "epoch": 1.0,
      "step": 398,
      "total_flos": 1.9165347193492685e+17,
      "train_loss": 1.5956898921698182,
      "train_runtime": 3205.1567,
      "train_samples_per_second": 0.497,
      "train_steps_per_second": 0.124
    }
  ],
  "logging_steps": 5,
  "max_steps": 398,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.9165347193492685e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}