{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 561,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05351170568561873,
      "grad_norm": 1.2401437759399414,
      "learning_rate": 3.157894736842105e-05,
      "loss": 3.5023,
      "step": 10
    },
    {
      "epoch": 0.10702341137123746,
      "grad_norm": 1.08428955078125,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.3947,
      "step": 20
    },
    {
      "epoch": 0.1605351170568562,
      "grad_norm": 1.0022192001342773,
      "learning_rate": 0.0001017543859649123,
      "loss": 3.2935,
      "step": 30
    },
    {
      "epoch": 0.2140468227424749,
      "grad_norm": 0.9494397044181824,
      "learning_rate": 0.0001368421052631579,
      "loss": 3.2952,
      "step": 40
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 0.8602828979492188,
      "learning_rate": 0.00017192982456140353,
      "loss": 3.3231,
      "step": 50
    },
    {
      "epoch": 0.3210702341137124,
      "grad_norm": 0.9193262457847595,
      "learning_rate": 0.0001999922292480975,
      "loss": 3.2551,
      "step": 60
    },
    {
      "epoch": 0.3745819397993311,
      "grad_norm": 0.8206238150596619,
      "learning_rate": 0.00019972037971811802,
      "loss": 3.2773,
      "step": 70
    },
    {
      "epoch": 0.4280936454849498,
      "grad_norm": 0.8329986929893494,
      "learning_rate": 0.0001990611994413053,
      "loss": 3.3447,
      "step": 80
    },
    {
      "epoch": 0.4816053511705686,
      "grad_norm": 0.9009258151054382,
      "learning_rate": 0.00019801724878485438,
      "loss": 3.3449,
      "step": 90
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 0.7764396667480469,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.3038,
      "step": 100
    },
    {
      "epoch": 0.5886287625418061,
      "grad_norm": 0.8236237168312073,
      "learning_rate": 0.0001947927346167132,
      "loss": 3.3162,
      "step": 110
    },
    {
      "epoch": 0.6421404682274248,
      "grad_norm": 0.7898942232131958,
      "learning_rate": 0.0001926246956610309,
      "loss": 3.2868,
      "step": 120
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.7577053308486938,
      "learning_rate": 0.0001900968867902419,
      "loss": 3.2781,
      "step": 130
    },
    {
      "epoch": 0.7491638795986622,
      "grad_norm": 0.7448907494544983,
      "learning_rate": 0.00018721912643966055,
      "loss": 3.2776,
      "step": 140
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.7627265453338623,
      "learning_rate": 0.00018400259231507717,
      "loss": 3.2989,
      "step": 150
    },
    {
      "epoch": 0.8561872909698997,
      "grad_norm": 0.7306041121482849,
      "learning_rate": 0.00018045977797666684,
      "loss": 3.3012,
      "step": 160
    },
    {
      "epoch": 0.9096989966555183,
      "grad_norm": 0.7832388281822205,
      "learning_rate": 0.0001766044443118978,
      "loss": 3.2706,
      "step": 170
    },
    {
      "epoch": 0.9632107023411371,
      "grad_norm": 0.8290534019470215,
      "learning_rate": 0.00017245156608592727,
      "loss": 3.383,
      "step": 180
    },
    {
      "epoch": 1.0160535117056857,
      "grad_norm": 0.7920368909835815,
      "learning_rate": 0.00016801727377709194,
      "loss": 3.1903,
      "step": 190
    },
    {
      "epoch": 1.0695652173913044,
      "grad_norm": 0.91294926404953,
      "learning_rate": 0.000163318790923414,
      "loss": 3.0714,
      "step": 200
    },
    {
      "epoch": 1.123076923076923,
      "grad_norm": 0.9004078507423401,
      "learning_rate": 0.000158374367223479,
      "loss": 3.0892,
      "step": 210
    },
    {
      "epoch": 1.1765886287625418,
      "grad_norm": 0.8549134135246277,
      "learning_rate": 0.00015320320765153367,
      "loss": 3.0669,
      "step": 220
    },
    {
      "epoch": 1.2301003344481605,
      "grad_norm": 0.8814137578010559,
      "learning_rate": 0.00014782539786213183,
      "loss": 3.0504,
      "step": 230
    },
    {
      "epoch": 1.2836120401337792,
      "grad_norm": 0.8694167733192444,
      "learning_rate": 0.00014226182617406996,
      "loss": 3.0227,
      "step": 240
    },
    {
      "epoch": 1.3371237458193979,
      "grad_norm": 0.8546176552772522,
      "learning_rate": 0.00013653410243663952,
      "loss": 3.0313,
      "step": 250
    },
    {
      "epoch": 1.3906354515050168,
      "grad_norm": 0.9608170390129089,
      "learning_rate": 0.00013066447409333345,
      "loss": 3.0832,
      "step": 260
    },
    {
      "epoch": 1.4441471571906355,
      "grad_norm": 0.938625693321228,
      "learning_rate": 0.00012467573976902935,
      "loss": 3.0271,
      "step": 270
    },
    {
      "epoch": 1.4976588628762542,
      "grad_norm": 0.9460514187812805,
      "learning_rate": 0.00011859116071629149,
      "loss": 3.0237,
      "step": 280
    },
    {
      "epoch": 1.551170568561873,
      "grad_norm": 0.9218224883079529,
      "learning_rate": 0.00011243437046474853,
      "loss": 3.0411,
      "step": 290
    },
    {
      "epoch": 1.6046822742474918,
      "grad_norm": 0.9326902627944946,
      "learning_rate": 0.00010622928302448523,
      "loss": 3.0379,
      "step": 300
    },
    {
      "epoch": 1.6581939799331105,
      "grad_norm": 0.8940379619598389,
      "learning_rate": 0.0001,
      "loss": 3.0212,
      "step": 310
    },
    {
      "epoch": 1.7117056856187292,
      "grad_norm": 0.9038141965866089,
      "learning_rate": 9.37707169755148e-05,
      "loss": 3.0407,
      "step": 320
    },
    {
      "epoch": 1.7652173913043478,
      "grad_norm": 0.9220936894416809,
      "learning_rate": 8.756562953525152e-05,
      "loss": 3.0481,
      "step": 330
    },
    {
      "epoch": 1.8187290969899665,
      "grad_norm": 0.8182596564292908,
      "learning_rate": 8.140883928370855e-05,
      "loss": 3.0711,
      "step": 340
    },
    {
      "epoch": 1.8722408026755852,
      "grad_norm": 0.9355226755142212,
      "learning_rate": 7.532426023097063e-05,
      "loss": 3.1391,
      "step": 350
    },
    {
      "epoch": 1.925752508361204,
      "grad_norm": 0.9329375624656677,
      "learning_rate": 6.933552590666659e-05,
      "loss": 3.0399,
      "step": 360
    },
    {
      "epoch": 1.9792642140468226,
      "grad_norm": 0.9382308721542358,
      "learning_rate": 6.34658975633605e-05,
      "loss": 3.015,
      "step": 370
    },
    {
      "epoch": 2.0321070234113714,
      "grad_norm": 0.982527494430542,
      "learning_rate": 5.773817382593008e-05,
      "loss": 2.8628,
      "step": 380
    },
    {
      "epoch": 2.08561872909699,
      "grad_norm": 1.1158782243728638,
      "learning_rate": 5.217460213786821e-05,
      "loss": 2.7862,
      "step": 390
    },
    {
      "epoch": 2.139130434782609,
      "grad_norm": 1.0975059270858765,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 2.8002,
      "step": 400
    },
    {
      "epoch": 2.1926421404682275,
      "grad_norm": 0.9911369681358337,
      "learning_rate": 4.1625632776521037e-05,
      "loss": 2.7731,
      "step": 410
    },
    {
      "epoch": 2.246153846153846,
      "grad_norm": 1.120684027671814,
      "learning_rate": 3.668120907658603e-05,
      "loss": 2.7325,
      "step": 420
    },
    {
      "epoch": 2.299665551839465,
      "grad_norm": 1.149767518043518,
      "learning_rate": 3.198272622290804e-05,
      "loss": 2.7713,
      "step": 430
    },
    {
      "epoch": 2.3531772575250836,
      "grad_norm": 1.0604385137557983,
      "learning_rate": 2.7548433914072734e-05,
      "loss": 2.74,
      "step": 440
    },
    {
      "epoch": 2.4066889632107022,
      "grad_norm": 1.0821083784103394,
      "learning_rate": 2.339555568810221e-05,
      "loss": 2.7514,
      "step": 450
    },
    {
      "epoch": 2.460200668896321,
      "grad_norm": 1.0802868604660034,
      "learning_rate": 1.9540222023333166e-05,
      "loss": 2.7896,
      "step": 460
    },
    {
      "epoch": 2.5137123745819396,
      "grad_norm": 1.0751402378082275,
      "learning_rate": 1.5997407684922862e-05,
      "loss": 2.7561,
      "step": 470
    },
    {
      "epoch": 2.5672240802675583,
      "grad_norm": 1.1360961198806763,
      "learning_rate": 1.2780873560339468e-05,
      "loss": 2.7271,
      "step": 480
    },
    {
      "epoch": 2.620735785953177,
      "grad_norm": 1.1104183197021484,
      "learning_rate": 9.903113209758096e-06,
      "loss": 2.7425,
      "step": 490
    },
    {
      "epoch": 2.6742474916387957,
      "grad_norm": 1.1601494550704956,
      "learning_rate": 7.375304338969136e-06,
      "loss": 2.7524,
      "step": 500
    },
    {
      "epoch": 2.727759197324415,
      "grad_norm": 1.121878743171692,
      "learning_rate": 5.20726538328683e-06,
      "loss": 2.7738,
      "step": 510
    },
    {
      "epoch": 2.7812709030100335,
      "grad_norm": 1.1342693567276,
      "learning_rate": 3.40741737109318e-06,
      "loss": 2.7854,
      "step": 520
    },
    {
      "epoch": 2.8347826086956522,
      "grad_norm": 1.1444578170776367,
      "learning_rate": 1.9827512151456173e-06,
      "loss": 2.7591,
      "step": 530
    },
    {
      "epoch": 2.888294314381271,
      "grad_norm": 1.1180880069732666,
      "learning_rate": 9.388005586947191e-07,
      "loss": 2.7576,
      "step": 540
    },
    {
      "epoch": 2.9418060200668896,
      "grad_norm": 1.117174506187439,
      "learning_rate": 2.7962028188198706e-07,
      "loss": 2.7276,
      "step": 550
    },
    {
      "epoch": 2.9953177257525083,
      "grad_norm": 1.159109354019165,
      "learning_rate": 7.770751902513862e-09,
      "loss": 2.7297,
      "step": 560
    }
  ],
  "logging_steps": 10,
  "max_steps": 561,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9811509803003904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}