{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16842105263157894,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016842105263157896,
      "grad_norm": 0.7416742444038391,
      "learning_rate": 2.525252525252526e-07,
      "loss": 1.6163,
      "step": 10
    },
    {
      "epoch": 0.003368421052631579,
      "grad_norm": 0.8192729353904724,
      "learning_rate": 5.331088664421998e-07,
      "loss": 1.5854,
      "step": 20
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": 0.7132650017738342,
      "learning_rate": 8.13692480359147e-07,
      "loss": 1.5937,
      "step": 30
    },
    {
      "epoch": 0.006736842105263158,
      "grad_norm": 0.6016515493392944,
      "learning_rate": 1.0942760942760944e-06,
      "loss": 1.5379,
      "step": 40
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 0.8635797500610352,
      "learning_rate": 1.3748597081930417e-06,
      "loss": 1.6066,
      "step": 50
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": 0.7259553670883179,
      "learning_rate": 1.655443322109989e-06,
      "loss": 1.5905,
      "step": 60
    },
    {
      "epoch": 0.011789473684210527,
      "grad_norm": 0.630763828754425,
      "learning_rate": 1.936026936026936e-06,
      "loss": 1.4836,
      "step": 70
    },
    {
      "epoch": 0.013473684210526317,
      "grad_norm": 0.8008495569229126,
      "learning_rate": 2.2166105499438833e-06,
      "loss": 1.5698,
      "step": 80
    },
    {
      "epoch": 0.015157894736842105,
      "grad_norm": 0.719158947467804,
      "learning_rate": 2.497194163860831e-06,
      "loss": 1.4721,
      "step": 90
    },
    {
      "epoch": 0.016842105263157894,
      "grad_norm": 0.7813356518745422,
      "learning_rate": 2.777777777777778e-06,
      "loss": 1.5929,
      "step": 100
    },
    {
      "epoch": 0.018526315789473686,
      "grad_norm": 0.7189694046974182,
      "learning_rate": 3.058361391694725e-06,
      "loss": 1.6497,
      "step": 110
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 0.673009991645813,
      "learning_rate": 3.3389450056116726e-06,
      "loss": 1.4904,
      "step": 120
    },
    {
      "epoch": 0.021894736842105262,
      "grad_norm": 0.6332181096076965,
      "learning_rate": 3.6195286195286197e-06,
      "loss": 1.5269,
      "step": 130
    },
    {
      "epoch": 0.023578947368421053,
      "grad_norm": 0.6532586812973022,
      "learning_rate": 3.900112233445567e-06,
      "loss": 1.4615,
      "step": 140
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 0.5978661179542542,
      "learning_rate": 4.180695847362514e-06,
      "loss": 1.5024,
      "step": 150
    },
    {
      "epoch": 0.026947368421052633,
      "grad_norm": 0.5529018044471741,
      "learning_rate": 4.4612794612794615e-06,
      "loss": 1.4819,
      "step": 160
    },
    {
      "epoch": 0.02863157894736842,
      "grad_norm": 0.5229254961013794,
      "learning_rate": 4.741863075196409e-06,
      "loss": 1.5354,
      "step": 170
    },
    {
      "epoch": 0.03031578947368421,
      "grad_norm": 0.4654325246810913,
      "learning_rate": 5.022446689113356e-06,
      "loss": 1.472,
      "step": 180
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.44726964831352234,
      "learning_rate": 5.303030303030304e-06,
      "loss": 1.4595,
      "step": 190
    },
    {
      "epoch": 0.03368421052631579,
      "grad_norm": 0.4176335334777832,
      "learning_rate": 5.583613916947251e-06,
      "loss": 1.5168,
      "step": 200
    },
    {
      "epoch": 0.03536842105263158,
      "grad_norm": 0.3661172688007355,
      "learning_rate": 5.864197530864198e-06,
      "loss": 1.452,
      "step": 210
    },
    {
      "epoch": 0.03705263157894737,
      "grad_norm": 0.38835084438323975,
      "learning_rate": 6.144781144781145e-06,
      "loss": 1.4537,
      "step": 220
    },
    {
      "epoch": 0.03873684210526316,
      "grad_norm": 0.3330041468143463,
      "learning_rate": 6.425364758698092e-06,
      "loss": 1.4693,
      "step": 230
    },
    {
      "epoch": 0.04042105263157895,
      "grad_norm": 0.33307236433029175,
      "learning_rate": 6.705948372615039e-06,
      "loss": 1.4899,
      "step": 240
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.30282339453697205,
      "learning_rate": 6.986531986531987e-06,
      "loss": 1.5017,
      "step": 250
    },
    {
      "epoch": 0.043789473684210524,
      "grad_norm": 0.302558034658432,
      "learning_rate": 7.267115600448934e-06,
      "loss": 1.4894,
      "step": 260
    },
    {
      "epoch": 0.04547368421052632,
      "grad_norm": 0.32156404852867126,
      "learning_rate": 7.5476992143658815e-06,
      "loss": 1.5006,
      "step": 270
    },
    {
      "epoch": 0.04715789473684211,
      "grad_norm": 0.28996139764785767,
      "learning_rate": 7.82828282828283e-06,
      "loss": 1.447,
      "step": 280
    },
    {
      "epoch": 0.048842105263157895,
      "grad_norm": 0.31116044521331787,
      "learning_rate": 8.108866442199776e-06,
      "loss": 1.5103,
      "step": 290
    },
    {
      "epoch": 0.05052631578947368,
      "grad_norm": 0.3400988280773163,
      "learning_rate": 8.389450056116724e-06,
      "loss": 1.517,
      "step": 300
    },
    {
      "epoch": 0.05221052631578947,
      "grad_norm": 0.3122132420539856,
      "learning_rate": 8.67003367003367e-06,
      "loss": 1.4381,
      "step": 310
    },
    {
      "epoch": 0.053894736842105266,
      "grad_norm": 0.31050199270248413,
      "learning_rate": 8.950617283950618e-06,
      "loss": 1.4649,
      "step": 320
    },
    {
      "epoch": 0.055578947368421054,
      "grad_norm": 0.29493045806884766,
      "learning_rate": 9.231200897867564e-06,
      "loss": 1.4224,
      "step": 330
    },
    {
      "epoch": 0.05726315789473684,
      "grad_norm": 0.3371477425098419,
      "learning_rate": 9.511784511784512e-06,
      "loss": 1.4904,
      "step": 340
    },
    {
      "epoch": 0.05894736842105263,
      "grad_norm": 0.3025756776332855,
      "learning_rate": 9.79236812570146e-06,
      "loss": 1.4743,
      "step": 350
    },
    {
      "epoch": 0.06063157894736842,
      "grad_norm": 0.3008587658405304,
      "learning_rate": 1.0072951739618406e-05,
      "loss": 1.5047,
      "step": 360
    },
    {
      "epoch": 0.06231578947368421,
      "grad_norm": 0.2756430506706238,
      "learning_rate": 1.0353535353535354e-05,
      "loss": 1.4286,
      "step": 370
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.3119344413280487,
      "learning_rate": 1.0634118967452302e-05,
      "loss": 1.4723,
      "step": 380
    },
    {
      "epoch": 0.06568421052631579,
      "grad_norm": 0.3306136131286621,
      "learning_rate": 1.0914702581369249e-05,
      "loss": 1.4769,
      "step": 390
    },
    {
      "epoch": 0.06736842105263158,
      "grad_norm": 0.28518420457839966,
      "learning_rate": 1.1195286195286197e-05,
      "loss": 1.4551,
      "step": 400
    },
    {
      "epoch": 0.06905263157894737,
      "grad_norm": 0.28847867250442505,
      "learning_rate": 1.1475869809203143e-05,
      "loss": 1.4071,
      "step": 410
    },
    {
      "epoch": 0.07073684210526315,
      "grad_norm": 0.2927733361721039,
      "learning_rate": 1.175645342312009e-05,
      "loss": 1.4057,
      "step": 420
    },
    {
      "epoch": 0.07242105263157894,
      "grad_norm": 0.3126303553581238,
      "learning_rate": 1.2037037037037037e-05,
      "loss": 1.4561,
      "step": 430
    },
    {
      "epoch": 0.07410526315789474,
      "grad_norm": 0.3449290990829468,
      "learning_rate": 1.2317620650953985e-05,
      "loss": 1.4998,
      "step": 440
    },
    {
      "epoch": 0.07578947368421053,
      "grad_norm": 0.2801138758659363,
      "learning_rate": 1.2598204264870933e-05,
      "loss": 1.4468,
      "step": 450
    },
    {
      "epoch": 0.07747368421052632,
      "grad_norm": 0.29857516288757324,
      "learning_rate": 1.287878787878788e-05,
      "loss": 1.5324,
      "step": 460
    },
    {
      "epoch": 0.07915789473684211,
      "grad_norm": 0.30076226592063904,
      "learning_rate": 1.3159371492704827e-05,
      "loss": 1.4199,
      "step": 470
    },
    {
      "epoch": 0.0808421052631579,
      "grad_norm": 0.3206464946269989,
      "learning_rate": 1.3439955106621773e-05,
      "loss": 1.4405,
      "step": 480
    },
    {
      "epoch": 0.08252631578947368,
      "grad_norm": 0.3138670027256012,
      "learning_rate": 1.3720538720538723e-05,
      "loss": 1.4967,
      "step": 490
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.3104718327522278,
      "learning_rate": 1.4001122334455668e-05,
      "loss": 1.5703,
      "step": 500
    },
    {
      "epoch": 0.08421052631578947,
      "eval_loss": 1.4425467252731323,
      "eval_runtime": 627.4744,
      "eval_samples_per_second": 7.968,
      "eval_steps_per_second": 3.984,
      "step": 500
    },
    {
      "epoch": 0.08589473684210526,
      "grad_norm": 0.3332298994064331,
      "learning_rate": 1.4281705948372614e-05,
      "loss": 1.4636,
      "step": 510
    },
    {
      "epoch": 0.08757894736842105,
      "grad_norm": 0.29114049673080444,
      "learning_rate": 1.4562289562289564e-05,
      "loss": 1.3763,
      "step": 520
    },
    {
      "epoch": 0.08926315789473684,
      "grad_norm": 0.2750283479690552,
      "learning_rate": 1.484287317620651e-05,
      "loss": 1.4726,
      "step": 530
    },
    {
      "epoch": 0.09094736842105264,
      "grad_norm": 0.29571524262428284,
      "learning_rate": 1.5123456790123458e-05,
      "loss": 1.4944,
      "step": 540
    },
    {
      "epoch": 0.09263157894736843,
      "grad_norm": 0.30884265899658203,
      "learning_rate": 1.5404040404040404e-05,
      "loss": 1.4321,
      "step": 550
    },
    {
      "epoch": 0.09431578947368421,
      "grad_norm": 0.2976180911064148,
      "learning_rate": 1.5684624017957354e-05,
      "loss": 1.4563,
      "step": 560
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.3064989745616913,
      "learning_rate": 1.59652076318743e-05,
      "loss": 1.4104,
      "step": 570
    },
    {
      "epoch": 0.09768421052631579,
      "grad_norm": 0.3264683187007904,
      "learning_rate": 1.6245791245791246e-05,
      "loss": 1.4738,
      "step": 580
    },
    {
      "epoch": 0.09936842105263158,
      "grad_norm": 0.2948909103870392,
      "learning_rate": 1.6526374859708193e-05,
      "loss": 1.4363,
      "step": 590
    },
    {
      "epoch": 0.10105263157894737,
      "grad_norm": 0.32367390394210815,
      "learning_rate": 1.6806958473625142e-05,
      "loss": 1.4438,
      "step": 600
    },
    {
      "epoch": 0.10273684210526315,
      "grad_norm": 0.29063737392425537,
      "learning_rate": 1.708754208754209e-05,
      "loss": 1.4437,
      "step": 610
    },
    {
      "epoch": 0.10442105263157894,
      "grad_norm": 0.3163065016269684,
      "learning_rate": 1.7368125701459035e-05,
      "loss": 1.4542,
      "step": 620
    },
    {
      "epoch": 0.10610526315789473,
      "grad_norm": 0.29881158471107483,
      "learning_rate": 1.7648709315375984e-05,
      "loss": 1.4029,
      "step": 630
    },
    {
      "epoch": 0.10778947368421053,
      "grad_norm": 0.3249943256378174,
      "learning_rate": 1.7929292929292927e-05,
      "loss": 1.4454,
      "step": 640
    },
    {
      "epoch": 0.10947368421052632,
      "grad_norm": 0.31320974230766296,
      "learning_rate": 1.8209876543209877e-05,
      "loss": 1.5437,
      "step": 650
    },
    {
      "epoch": 0.11115789473684211,
      "grad_norm": 0.30014970898628235,
      "learning_rate": 1.8490460157126823e-05,
      "loss": 1.3781,
      "step": 660
    },
    {
      "epoch": 0.1128421052631579,
      "grad_norm": 0.3208349943161011,
      "learning_rate": 1.8771043771043773e-05,
      "loss": 1.4615,
      "step": 670
    },
    {
      "epoch": 0.11452631578947368,
      "grad_norm": 0.33636245131492615,
      "learning_rate": 1.905162738496072e-05,
      "loss": 1.3844,
      "step": 680
    },
    {
      "epoch": 0.11621052631578947,
      "grad_norm": 0.2895752489566803,
      "learning_rate": 1.933221099887767e-05,
      "loss": 1.5021,
      "step": 690
    },
    {
      "epoch": 0.11789473684210526,
      "grad_norm": 0.33455783128738403,
      "learning_rate": 1.9612794612794612e-05,
      "loss": 1.3939,
      "step": 700
    },
    {
      "epoch": 0.11957894736842105,
      "grad_norm": 0.36592987179756165,
      "learning_rate": 1.989337822671156e-05,
      "loss": 1.4311,
      "step": 710
    },
    {
      "epoch": 0.12126315789473684,
      "grad_norm": 0.317028671503067,
      "learning_rate": 2.0173961840628508e-05,
      "loss": 1.4778,
      "step": 720
    },
    {
      "epoch": 0.12294736842105262,
      "grad_norm": 0.3277951180934906,
      "learning_rate": 2.0454545454545457e-05,
      "loss": 1.3975,
      "step": 730
    },
    {
      "epoch": 0.12463157894736843,
      "grad_norm": 0.33263206481933594,
      "learning_rate": 2.0735129068462404e-05,
      "loss": 1.4842,
      "step": 740
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.34084832668304443,
      "learning_rate": 2.101571268237935e-05,
      "loss": 1.4702,
      "step": 750
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.3358267843723297,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 1.4088,
      "step": 760
    },
    {
      "epoch": 0.1296842105263158,
      "grad_norm": 0.3366195559501648,
      "learning_rate": 2.1576879910213242e-05,
      "loss": 1.4043,
      "step": 770
    },
    {
      "epoch": 0.13136842105263158,
      "grad_norm": 0.3151577115058899,
      "learning_rate": 2.1857463524130192e-05,
      "loss": 1.4305,
      "step": 780
    },
    {
      "epoch": 0.13305263157894737,
      "grad_norm": 0.3637940287590027,
      "learning_rate": 2.213804713804714e-05,
      "loss": 1.4381,
      "step": 790
    },
    {
      "epoch": 0.13473684210526315,
      "grad_norm": 0.30998823046684265,
      "learning_rate": 2.2418630751964088e-05,
      "loss": 1.4181,
      "step": 800
    },
    {
      "epoch": 0.13642105263157894,
      "grad_norm": 0.29245883226394653,
      "learning_rate": 2.2699214365881034e-05,
      "loss": 1.4515,
      "step": 810
    },
    {
      "epoch": 0.13810526315789473,
      "grad_norm": 0.32378411293029785,
      "learning_rate": 2.297979797979798e-05,
      "loss": 1.4873,
      "step": 820
    },
    {
      "epoch": 0.13978947368421052,
      "grad_norm": 0.32840538024902344,
      "learning_rate": 2.3260381593714927e-05,
      "loss": 1.4798,
      "step": 830
    },
    {
      "epoch": 0.1414736842105263,
      "grad_norm": 0.32433003187179565,
      "learning_rate": 2.3540965207631877e-05,
      "loss": 1.4148,
      "step": 840
    },
    {
      "epoch": 0.1431578947368421,
      "grad_norm": 0.3382358253002167,
      "learning_rate": 2.3821548821548823e-05,
      "loss": 1.4499,
      "step": 850
    },
    {
      "epoch": 0.14484210526315788,
      "grad_norm": 0.30143994092941284,
      "learning_rate": 2.4102132435465772e-05,
      "loss": 1.3917,
      "step": 860
    },
    {
      "epoch": 0.14652631578947367,
      "grad_norm": 0.3304138481616974,
      "learning_rate": 2.438271604938272e-05,
      "loss": 1.3791,
      "step": 870
    },
    {
      "epoch": 0.1482105263157895,
      "grad_norm": 0.353997141122818,
      "learning_rate": 2.466329966329966e-05,
      "loss": 1.4707,
      "step": 880
    },
    {
      "epoch": 0.14989473684210528,
      "grad_norm": 0.3323941230773926,
      "learning_rate": 2.494388327721661e-05,
      "loss": 1.4232,
      "step": 890
    },
    {
      "epoch": 0.15157894736842106,
      "grad_norm": 0.3112866282463074,
      "learning_rate": 2.5224466891133558e-05,
      "loss": 1.4291,
      "step": 900
    },
    {
      "epoch": 0.15326315789473685,
      "grad_norm": 0.3290766477584839,
      "learning_rate": 2.5505050505050504e-05,
      "loss": 1.4411,
      "step": 910
    },
    {
      "epoch": 0.15494736842105264,
      "grad_norm": 0.3461703360080719,
      "learning_rate": 2.5785634118967457e-05,
      "loss": 1.4012,
      "step": 920
    },
    {
      "epoch": 0.15663157894736843,
      "grad_norm": 0.359667032957077,
      "learning_rate": 2.6066217732884403e-05,
      "loss": 1.4327,
      "step": 930
    },
    {
      "epoch": 0.15831578947368422,
      "grad_norm": 0.3078553378582001,
      "learning_rate": 2.6346801346801346e-05,
      "loss": 1.445,
      "step": 940
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.31644898653030396,
      "learning_rate": 2.6627384960718292e-05,
      "loss": 1.4784,
      "step": 950
    },
    {
      "epoch": 0.1616842105263158,
      "grad_norm": 0.3724164366722107,
      "learning_rate": 2.6907968574635245e-05,
      "loss": 1.4873,
      "step": 960
    },
    {
      "epoch": 0.16336842105263158,
      "grad_norm": 0.32616913318634033,
      "learning_rate": 2.718855218855219e-05,
      "loss": 1.4213,
      "step": 970
    },
    {
      "epoch": 0.16505263157894737,
      "grad_norm": 0.3016490936279297,
      "learning_rate": 2.7469135802469138e-05,
      "loss": 1.4085,
      "step": 980
    },
    {
      "epoch": 0.16673684210526316,
      "grad_norm": 0.33823099732398987,
      "learning_rate": 2.7749719416386084e-05,
      "loss": 1.4121,
      "step": 990
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.40880540013313293,
      "learning_rate": 2.803030303030303e-05,
      "loss": 1.4945,
      "step": 1000
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 1.4282265901565552,
      "eval_runtime": 627.3446,
      "eval_samples_per_second": 7.97,
      "eval_steps_per_second": 3.985,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 17814,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.625805619481805e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}