{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9954170485792853,
  "eval_steps": 500,
  "global_step": 816,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03666361136571952,
      "grad_norm": 10.920966734668648,
      "learning_rate": 5e-06,
      "loss": 1.033,
      "step": 10
    },
    {
      "epoch": 0.07332722273143905,
      "grad_norm": 2.445980198452297,
      "learning_rate": 5e-06,
      "loss": 0.9011,
      "step": 20
    },
    {
      "epoch": 0.10999083409715857,
      "grad_norm": 1.5424232386159482,
      "learning_rate": 5e-06,
      "loss": 0.8764,
      "step": 30
    },
    {
      "epoch": 0.1466544454628781,
      "grad_norm": 1.1797649838046136,
      "learning_rate": 5e-06,
      "loss": 0.8446,
      "step": 40
    },
    {
      "epoch": 0.18331805682859761,
      "grad_norm": 1.0295589020655365,
      "learning_rate": 5e-06,
      "loss": 0.8204,
      "step": 50
    },
    {
      "epoch": 0.21998166819431714,
      "grad_norm": 1.2160434357225554,
      "learning_rate": 5e-06,
      "loss": 0.8104,
      "step": 60
    },
    {
      "epoch": 0.2566452795600367,
      "grad_norm": 1.2135493715768004,
      "learning_rate": 5e-06,
      "loss": 0.7968,
      "step": 70
    },
    {
      "epoch": 0.2933088909257562,
      "grad_norm": 0.7594488712178804,
      "learning_rate": 5e-06,
      "loss": 0.7836,
      "step": 80
    },
    {
      "epoch": 0.32997250229147573,
      "grad_norm": 0.8913076302913621,
      "learning_rate": 5e-06,
      "loss": 0.7781,
      "step": 90
    },
    {
      "epoch": 0.36663611365719523,
      "grad_norm": 1.126183659145103,
      "learning_rate": 5e-06,
      "loss": 0.7732,
      "step": 100
    },
    {
      "epoch": 0.4032997250229148,
      "grad_norm": 0.7476760341544976,
      "learning_rate": 5e-06,
      "loss": 0.7711,
      "step": 110
    },
    {
      "epoch": 0.4399633363886343,
      "grad_norm": 0.828783632948725,
      "learning_rate": 5e-06,
      "loss": 0.7637,
      "step": 120
    },
    {
      "epoch": 0.4766269477543538,
      "grad_norm": 0.7005369874659794,
      "learning_rate": 5e-06,
      "loss": 0.7617,
      "step": 130
    },
    {
      "epoch": 0.5132905591200734,
      "grad_norm": 0.6781356553576761,
      "learning_rate": 5e-06,
      "loss": 0.7562,
      "step": 140
    },
    {
      "epoch": 0.5499541704857929,
      "grad_norm": 0.6643060954517749,
      "learning_rate": 5e-06,
      "loss": 0.7601,
      "step": 150
    },
    {
      "epoch": 0.5866177818515124,
      "grad_norm": 0.654862572470797,
      "learning_rate": 5e-06,
      "loss": 0.7561,
      "step": 160
    },
    {
      "epoch": 0.6232813932172319,
      "grad_norm": 0.7126834121476828,
      "learning_rate": 5e-06,
      "loss": 0.7549,
      "step": 170
    },
    {
      "epoch": 0.6599450045829515,
      "grad_norm": 0.5845932549413623,
      "learning_rate": 5e-06,
      "loss": 0.7525,
      "step": 180
    },
    {
      "epoch": 0.696608615948671,
      "grad_norm": 0.583642927450063,
      "learning_rate": 5e-06,
      "loss": 0.7507,
      "step": 190
    },
    {
      "epoch": 0.7332722273143905,
      "grad_norm": 0.5759630428428489,
      "learning_rate": 5e-06,
      "loss": 0.7492,
      "step": 200
    },
    {
      "epoch": 0.76993583868011,
      "grad_norm": 0.597809207757354,
      "learning_rate": 5e-06,
      "loss": 0.7446,
      "step": 210
    },
    {
      "epoch": 0.8065994500458296,
      "grad_norm": 0.6520665055230834,
      "learning_rate": 5e-06,
      "loss": 0.7512,
      "step": 220
    },
    {
      "epoch": 0.843263061411549,
      "grad_norm": 0.6521761800994458,
      "learning_rate": 5e-06,
      "loss": 0.744,
      "step": 230
    },
    {
      "epoch": 0.8799266727772685,
      "grad_norm": 0.6083361886529014,
      "learning_rate": 5e-06,
      "loss": 0.7431,
      "step": 240
    },
    {
      "epoch": 0.916590284142988,
      "grad_norm": 0.8966782629847545,
      "learning_rate": 5e-06,
      "loss": 0.7399,
      "step": 250
    },
    {
      "epoch": 0.9532538955087076,
      "grad_norm": 0.6584181334872885,
      "learning_rate": 5e-06,
      "loss": 0.7457,
      "step": 260
    },
    {
      "epoch": 0.9899175068744271,
      "grad_norm": 0.5614900416740534,
      "learning_rate": 5e-06,
      "loss": 0.7434,
      "step": 270
    },
    {
      "epoch": 0.997250229147571,
      "eval_loss": 0.743977963924408,
      "eval_runtime": 96.6447,
      "eval_samples_per_second": 76.052,
      "eval_steps_per_second": 0.6,
      "step": 272
    },
    {
      "epoch": 1.0284142988084326,
      "grad_norm": 0.6377526876986616,
      "learning_rate": 5e-06,
      "loss": 0.7593,
      "step": 280
    },
    {
      "epoch": 1.065077910174152,
      "grad_norm": 0.8312923337011684,
      "learning_rate": 5e-06,
      "loss": 0.6885,
      "step": 290
    },
    {
      "epoch": 1.1017415215398716,
      "grad_norm": 0.6499984381614756,
      "learning_rate": 5e-06,
      "loss": 0.6893,
      "step": 300
    },
    {
      "epoch": 1.138405132905591,
      "grad_norm": 0.658519279927457,
      "learning_rate": 5e-06,
      "loss": 0.6868,
      "step": 310
    },
    {
      "epoch": 1.1750687442713108,
      "grad_norm": 0.6307182099292118,
      "learning_rate": 5e-06,
      "loss": 0.6885,
      "step": 320
    },
    {
      "epoch": 1.2117323556370303,
      "grad_norm": 0.6191143311988347,
      "learning_rate": 5e-06,
      "loss": 0.6871,
      "step": 330
    },
    {
      "epoch": 1.2483959670027498,
      "grad_norm": 0.6735946598593434,
      "learning_rate": 5e-06,
      "loss": 0.6935,
      "step": 340
    },
    {
      "epoch": 1.2850595783684693,
      "grad_norm": 0.7213451984916242,
      "learning_rate": 5e-06,
      "loss": 0.6943,
      "step": 350
    },
    {
      "epoch": 1.3217231897341888,
      "grad_norm": 0.5841901070016948,
      "learning_rate": 5e-06,
      "loss": 0.6938,
      "step": 360
    },
    {
      "epoch": 1.3583868010999083,
      "grad_norm": 0.6609752377099979,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 370
    },
    {
      "epoch": 1.3950504124656278,
      "grad_norm": 0.6004672142282963,
      "learning_rate": 5e-06,
      "loss": 0.69,
      "step": 380
    },
    {
      "epoch": 1.4317140238313475,
      "grad_norm": 0.7494020947088555,
      "learning_rate": 5e-06,
      "loss": 0.682,
      "step": 390
    },
    {
      "epoch": 1.468377635197067,
      "grad_norm": 0.6711006066177567,
      "learning_rate": 5e-06,
      "loss": 0.6917,
      "step": 400
    },
    {
      "epoch": 1.5050412465627865,
      "grad_norm": 0.6517430215570676,
      "learning_rate": 5e-06,
      "loss": 0.6871,
      "step": 410
    },
    {
      "epoch": 1.541704857928506,
      "grad_norm": 0.6180564693914907,
      "learning_rate": 5e-06,
      "loss": 0.6829,
      "step": 420
    },
    {
      "epoch": 1.5783684692942255,
      "grad_norm": 0.5764324092377354,
      "learning_rate": 5e-06,
      "loss": 0.6824,
      "step": 430
    },
    {
      "epoch": 1.615032080659945,
      "grad_norm": 0.7134204082562298,
      "learning_rate": 5e-06,
      "loss": 0.6822,
      "step": 440
    },
    {
      "epoch": 1.6516956920256645,
      "grad_norm": 0.7630512170385407,
      "learning_rate": 5e-06,
      "loss": 0.6879,
      "step": 450
    },
    {
      "epoch": 1.6883593033913842,
      "grad_norm": 0.6285437172539765,
      "learning_rate": 5e-06,
      "loss": 0.6804,
      "step": 460
    },
    {
      "epoch": 1.7250229147571035,
      "grad_norm": 0.5968789313484854,
      "learning_rate": 5e-06,
      "loss": 0.686,
      "step": 470
    },
    {
      "epoch": 1.7616865261228232,
      "grad_norm": 0.6425175740435289,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 480
    },
    {
      "epoch": 1.7983501374885427,
      "grad_norm": 0.7614365266625939,
      "learning_rate": 5e-06,
      "loss": 0.6814,
      "step": 490
    },
    {
      "epoch": 1.8350137488542622,
      "grad_norm": 0.5496379357416068,
      "learning_rate": 5e-06,
      "loss": 0.6855,
      "step": 500
    },
    {
      "epoch": 1.8716773602199817,
      "grad_norm": 0.8494093367270151,
      "learning_rate": 5e-06,
      "loss": 0.6875,
      "step": 510
    },
    {
      "epoch": 1.9083409715857012,
      "grad_norm": 0.6756166103000668,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 520
    },
    {
      "epoch": 1.9450045829514209,
      "grad_norm": 0.7228484772895967,
      "learning_rate": 5e-06,
      "loss": 0.6841,
      "step": 530
    },
    {
      "epoch": 1.9816681943171401,
      "grad_norm": 0.7786774729146112,
      "learning_rate": 5e-06,
      "loss": 0.6845,
      "step": 540
    },
    {
      "epoch": 1.996333638863428,
      "eval_loss": 0.7305116057395935,
      "eval_runtime": 96.1532,
      "eval_samples_per_second": 76.441,
      "eval_steps_per_second": 0.603,
      "step": 544
    },
    {
      "epoch": 2.020164986251146,
      "grad_norm": 1.0425759476709966,
      "learning_rate": 5e-06,
      "loss": 0.707,
      "step": 550
    },
    {
      "epoch": 2.056828597616865,
      "grad_norm": 0.8473344095764829,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 560
    },
    {
      "epoch": 2.093492208982585,
      "grad_norm": 0.7205628261028438,
      "learning_rate": 5e-06,
      "loss": 0.6281,
      "step": 570
    },
    {
      "epoch": 2.130155820348304,
      "grad_norm": 0.6604987014823058,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 580
    },
    {
      "epoch": 2.166819431714024,
      "grad_norm": 0.6774961015973217,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 590
    },
    {
      "epoch": 2.203483043079743,
      "grad_norm": 0.8519809292040578,
      "learning_rate": 5e-06,
      "loss": 0.634,
      "step": 600
    },
    {
      "epoch": 2.240146654445463,
      "grad_norm": 0.693823740633704,
      "learning_rate": 5e-06,
      "loss": 0.6327,
      "step": 610
    },
    {
      "epoch": 2.276810265811182,
      "grad_norm": 0.6448705487045298,
      "learning_rate": 5e-06,
      "loss": 0.6339,
      "step": 620
    },
    {
      "epoch": 2.313473877176902,
      "grad_norm": 0.5865817788059118,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 630
    },
    {
      "epoch": 2.3501374885426216,
      "grad_norm": 0.8116556137845999,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 640
    },
    {
      "epoch": 2.386801099908341,
      "grad_norm": 0.6231657257473445,
      "learning_rate": 5e-06,
      "loss": 0.637,
      "step": 650
    },
    {
      "epoch": 2.4234647112740606,
      "grad_norm": 0.6250913266909794,
      "learning_rate": 5e-06,
      "loss": 0.63,
      "step": 660
    },
    {
      "epoch": 2.46012832263978,
      "grad_norm": 0.582068921531117,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 670
    },
    {
      "epoch": 2.4967919340054996,
      "grad_norm": 0.6912367969819871,
      "learning_rate": 5e-06,
      "loss": 0.6381,
      "step": 680
    },
    {
      "epoch": 2.5334555453712193,
      "grad_norm": 0.7147652107920064,
      "learning_rate": 5e-06,
      "loss": 0.6332,
      "step": 690
    },
    {
      "epoch": 2.5701191567369386,
      "grad_norm": 0.5792260811836798,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 700
    },
    {
      "epoch": 2.606782768102658,
      "grad_norm": 0.7963438662743851,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 710
    },
    {
      "epoch": 2.6434463794683776,
      "grad_norm": 0.9276380358330181,
      "learning_rate": 5e-06,
      "loss": 0.6355,
      "step": 720
    },
    {
      "epoch": 2.6801099908340973,
      "grad_norm": 0.9313823270809661,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 730
    },
    {
      "epoch": 2.7167736021998166,
      "grad_norm": 0.7304200587600748,
      "learning_rate": 5e-06,
      "loss": 0.638,
      "step": 740
    },
    {
      "epoch": 2.7534372135655363,
      "grad_norm": 0.6212966397528322,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 750
    },
    {
      "epoch": 2.7901008249312556,
      "grad_norm": 0.6720686482466423,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 760
    },
    {
      "epoch": 2.8267644362969753,
      "grad_norm": 0.6438467896193539,
      "learning_rate": 5e-06,
      "loss": 0.6421,
      "step": 770
    },
    {
      "epoch": 2.863428047662695,
      "grad_norm": 0.6043416931907646,
      "learning_rate": 5e-06,
      "loss": 0.6379,
      "step": 780
    },
    {
      "epoch": 2.9000916590284143,
      "grad_norm": 0.6496494693588303,
      "learning_rate": 5e-06,
      "loss": 0.6414,
      "step": 790
    },
    {
      "epoch": 2.936755270394134,
      "grad_norm": 0.8144443719589332,
      "learning_rate": 5e-06,
      "loss": 0.6361,
      "step": 800
    },
    {
      "epoch": 2.9734188817598532,
      "grad_norm": 0.7037764123768507,
      "learning_rate": 5e-06,
      "loss": 0.6373,
      "step": 810
    },
    {
      "epoch": 2.9954170485792853,
      "eval_loss": 0.7332214117050171,
      "eval_runtime": 94.4197,
      "eval_samples_per_second": 77.844,
      "eval_steps_per_second": 0.614,
      "step": 816
    },
    {
      "epoch": 2.9954170485792853,
      "step": 816,
      "total_flos": 1366411632967680.0,
      "train_loss": 0.7035682309491962,
      "train_runtime": 14220.3782,
      "train_samples_per_second": 29.46,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 10,
  "max_steps": 816,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1366411632967680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}