{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3816793893129771,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003816793893129771,
      "grad_norm": 2.560382604598999,
      "learning_rate": 1.3740458015267178e-06,
      "loss": 0.1604,
      "step": 10
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": 3.7791059017181396,
      "learning_rate": 2.900763358778626e-06,
      "loss": 0.2,
      "step": 20
    },
    {
      "epoch": 0.011450381679389313,
      "grad_norm": 3.4597890377044678,
      "learning_rate": 4.427480916030535e-06,
      "loss": 0.1753,
      "step": 30
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 2.7554614543914795,
      "learning_rate": 5.9541984732824435e-06,
      "loss": 0.1171,
      "step": 40
    },
    {
      "epoch": 0.019083969465648856,
      "grad_norm": 2.082803726196289,
      "learning_rate": 7.480916030534352e-06,
      "loss": 0.0549,
      "step": 50
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": 2.8653404712677,
      "learning_rate": 9.007633587786259e-06,
      "loss": 0.0671,
      "step": 60
    },
    {
      "epoch": 0.026717557251908396,
      "grad_norm": 1.3137264251708984,
      "learning_rate": 1.0534351145038168e-05,
      "loss": 0.0492,
      "step": 70
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 1.7409602403640747,
      "learning_rate": 1.2061068702290078e-05,
      "loss": 0.0343,
      "step": 80
    },
    {
      "epoch": 0.03435114503816794,
      "grad_norm": 0.6623567342758179,
      "learning_rate": 1.3587786259541987e-05,
      "loss": 0.0439,
      "step": 90
    },
    {
      "epoch": 0.03816793893129771,
      "grad_norm": 1.5286792516708374,
      "learning_rate": 1.5114503816793895e-05,
      "loss": 0.0377,
      "step": 100
    },
    {
      "epoch": 0.04198473282442748,
      "grad_norm": 0.9364567399024963,
      "learning_rate": 1.6641221374045802e-05,
      "loss": 0.019,
      "step": 110
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": 0.9754840135574341,
      "learning_rate": 1.816793893129771e-05,
      "loss": 0.0245,
      "step": 120
    },
    {
      "epoch": 0.04961832061068702,
      "grad_norm": 0.17266954481601715,
      "learning_rate": 1.969465648854962e-05,
      "loss": 0.0259,
      "step": 130
    },
    {
      "epoch": 0.05343511450381679,
      "grad_norm": 1.5330302715301514,
      "learning_rate": 2.122137404580153e-05,
      "loss": 0.0268,
      "step": 140
    },
    {
      "epoch": 0.05725190839694656,
      "grad_norm": 1.4104247093200684,
      "learning_rate": 2.2748091603053437e-05,
      "loss": 0.0211,
      "step": 150
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": 0.004101096652448177,
      "learning_rate": 2.4274809160305344e-05,
      "loss": 0.0263,
      "step": 160
    },
    {
      "epoch": 0.0648854961832061,
      "grad_norm": 0.6165310144424438,
      "learning_rate": 2.5801526717557254e-05,
      "loss": 0.0138,
      "step": 170
    },
    {
      "epoch": 0.06870229007633588,
      "grad_norm": 0.37463024258613586,
      "learning_rate": 2.732824427480916e-05,
      "loss": 0.0322,
      "step": 180
    },
    {
      "epoch": 0.07251908396946564,
      "grad_norm": 0.620210587978363,
      "learning_rate": 2.885496183206107e-05,
      "loss": 0.0188,
      "step": 190
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": 0.758702278137207,
      "learning_rate": 3.038167938931298e-05,
      "loss": 0.0139,
      "step": 200
    },
    {
      "epoch": 0.08015267175572519,
      "grad_norm": 1.3074781894683838,
      "learning_rate": 3.190839694656489e-05,
      "loss": 0.0306,
      "step": 210
    },
    {
      "epoch": 0.08396946564885496,
      "grad_norm": 0.6031699776649475,
      "learning_rate": 3.3435114503816796e-05,
      "loss": 0.0175,
      "step": 220
    },
    {
      "epoch": 0.08778625954198473,
      "grad_norm": 1.136716365814209,
      "learning_rate": 3.4961832061068706e-05,
      "loss": 0.0242,
      "step": 230
    },
    {
      "epoch": 0.0916030534351145,
      "grad_norm": 0.5463850498199463,
      "learning_rate": 3.6488549618320616e-05,
      "loss": 0.0218,
      "step": 240
    },
    {
      "epoch": 0.09541984732824428,
      "grad_norm": 0.1893869787454605,
      "learning_rate": 3.801526717557252e-05,
      "loss": 0.0171,
      "step": 250
    },
    {
      "epoch": 0.09923664122137404,
      "grad_norm": 0.05841643363237381,
      "learning_rate": 3.954198473282443e-05,
      "loss": 0.0183,
      "step": 260
    },
    {
      "epoch": 0.10305343511450382,
      "grad_norm": 0.5519092082977295,
      "learning_rate": 3.999913022869401e-05,
      "loss": 0.0171,
      "step": 270
    },
    {
      "epoch": 0.10687022900763359,
      "grad_norm": 0.75583815574646,
      "learning_rate": 3.999487030645216e-05,
      "loss": 0.0269,
      "step": 280
    },
    {
      "epoch": 0.11068702290076336,
      "grad_norm": 0.34393128752708435,
      "learning_rate": 3.998706123456487e-05,
      "loss": 0.021,
      "step": 290
    },
    {
      "epoch": 0.11450381679389313,
      "grad_norm": 0.741912841796875,
      "learning_rate": 3.997570439916593e-05,
      "loss": 0.0139,
      "step": 300
    },
    {
      "epoch": 0.1183206106870229,
      "grad_norm": 0.42950552701950073,
      "learning_rate": 3.996080181612776e-05,
      "loss": 0.01,
      "step": 310
    },
    {
      "epoch": 0.12213740458015267,
      "grad_norm": 0.8363562822341919,
      "learning_rate": 3.9942356130703715e-05,
      "loss": 0.0119,
      "step": 320
    },
    {
      "epoch": 0.12595419847328243,
      "grad_norm": 0.2727142572402954,
      "learning_rate": 3.992037061705845e-05,
      "loss": 0.0127,
      "step": 330
    },
    {
      "epoch": 0.1297709923664122,
      "grad_norm": 1.3103034496307373,
      "learning_rate": 3.98948491776868e-05,
      "loss": 0.0167,
      "step": 340
    },
    {
      "epoch": 0.13358778625954199,
      "grad_norm": 0.1281624436378479,
      "learning_rate": 3.986579634272105e-05,
      "loss": 0.0178,
      "step": 350
    },
    {
      "epoch": 0.13740458015267176,
      "grad_norm": 0.22181691229343414,
      "learning_rate": 3.9833217269126826e-05,
      "loss": 0.0213,
      "step": 360
    },
    {
      "epoch": 0.14122137404580154,
      "grad_norm": 0.3226180970668793,
      "learning_rate": 3.979711773978772e-05,
      "loss": 0.0177,
      "step": 370
    },
    {
      "epoch": 0.1450381679389313,
      "grad_norm": 0.15748214721679688,
      "learning_rate": 3.9757504162478827e-05,
      "loss": 0.0161,
      "step": 380
    },
    {
      "epoch": 0.14885496183206107,
      "grad_norm": 0.7109506726264954,
      "learning_rate": 3.971438356872931e-05,
      "loss": 0.0186,
      "step": 390
    },
    {
      "epoch": 0.15267175572519084,
      "grad_norm": 0.1298808604478836,
      "learning_rate": 3.966776361257431e-05,
      "loss": 0.0068,
      "step": 400
    },
    {
      "epoch": 0.15648854961832062,
      "grad_norm": 0.5112190842628479,
      "learning_rate": 3.961765256919633e-05,
      "loss": 0.0175,
      "step": 410
    },
    {
      "epoch": 0.16030534351145037,
      "grad_norm": 0.12070173770189285,
      "learning_rate": 3.956405933345637e-05,
      "loss": 0.0138,
      "step": 420
    },
    {
      "epoch": 0.16412213740458015,
      "grad_norm": 0.009782848879694939,
      "learning_rate": 3.950699341831502e-05,
      "loss": 0.0087,
      "step": 430
    },
    {
      "epoch": 0.16793893129770993,
      "grad_norm": 0.49791470170021057,
      "learning_rate": 3.944646495314395e-05,
      "loss": 0.0153,
      "step": 440
    },
    {
      "epoch": 0.1717557251908397,
      "grad_norm": 0.5504122376441956,
      "learning_rate": 3.938248468192785e-05,
      "loss": 0.0202,
      "step": 450
    },
    {
      "epoch": 0.17557251908396945,
      "grad_norm": 1.6467090845108032,
      "learning_rate": 3.931506396135738e-05,
      "loss": 0.0206,
      "step": 460
    },
    {
      "epoch": 0.17938931297709923,
      "grad_norm": 0.4959694445133209,
      "learning_rate": 3.924421475881333e-05,
      "loss": 0.0146,
      "step": 470
    },
    {
      "epoch": 0.183206106870229,
      "grad_norm": 0.6547468304634094,
      "learning_rate": 3.916994965024234e-05,
      "loss": 0.014,
      "step": 480
    },
    {
      "epoch": 0.18702290076335878,
      "grad_norm": 0.37912440299987793,
      "learning_rate": 3.909228181792464e-05,
      "loss": 0.0149,
      "step": 490
    },
    {
      "epoch": 0.19083969465648856,
      "grad_norm": 0.17722374200820923,
      "learning_rate": 3.901122504813418e-05,
      "loss": 0.0142,
      "step": 500
    },
    {
      "epoch": 0.19083969465648856,
      "eval_loss": 0.03738304600119591,
      "eval_runtime": 140.2925,
      "eval_samples_per_second": 56.895,
      "eval_steps_per_second": 0.299,
      "step": 500
    },
    {
      "epoch": 0.1946564885496183,
      "grad_norm": 0.012979953549802303,
      "learning_rate": 3.89267937286915e-05,
      "loss": 0.0095,
      "step": 510
    },
    {
      "epoch": 0.1984732824427481,
      "grad_norm": 0.30195748805999756,
      "learning_rate": 3.883900284640987e-05,
      "loss": 0.0075,
      "step": 520
    },
    {
      "epoch": 0.20229007633587787,
      "grad_norm": 0.7806116938591003,
      "learning_rate": 3.874786798443505e-05,
      "loss": 0.0169,
      "step": 530
    },
    {
      "epoch": 0.20610687022900764,
      "grad_norm": 0.17662391066551208,
      "learning_rate": 3.8653405319479285e-05,
      "loss": 0.0135,
      "step": 540
    },
    {
      "epoch": 0.2099236641221374,
      "grad_norm": 0.12067825347185135,
      "learning_rate": 3.855563161894985e-05,
      "loss": 0.0104,
      "step": 550
    },
    {
      "epoch": 0.21374045801526717,
      "grad_norm": 0.5847358107566833,
      "learning_rate": 3.8454564237972786e-05,
      "loss": 0.0175,
      "step": 560
    },
    {
      "epoch": 0.21755725190839695,
      "grad_norm": 0.2978436350822449,
      "learning_rate": 3.835022111631235e-05,
      "loss": 0.0093,
      "step": 570
    },
    {
      "epoch": 0.22137404580152673,
      "grad_norm": 0.07228351384401321,
      "learning_rate": 3.8242620775186596e-05,
      "loss": 0.0111,
      "step": 580
    },
    {
      "epoch": 0.22519083969465647,
      "grad_norm": 0.33176591992378235,
      "learning_rate": 3.8131782313979864e-05,
      "loss": 0.0087,
      "step": 590
    },
    {
      "epoch": 0.22900763358778625,
      "grad_norm": 0.08005018532276154,
      "learning_rate": 3.801772540685253e-05,
      "loss": 0.011,
      "step": 600
    },
    {
      "epoch": 0.23282442748091603,
      "grad_norm": 0.09141408652067184,
      "learning_rate": 3.7900470299248824e-05,
      "loss": 0.0111,
      "step": 610
    },
    {
      "epoch": 0.2366412213740458,
      "grad_norm": 0.21106335520744324,
      "learning_rate": 3.778003780430317e-05,
      "loss": 0.0091,
      "step": 620
    },
    {
      "epoch": 0.24045801526717558,
      "grad_norm": 0.8840196132659912,
      "learning_rate": 3.7656449299145814e-05,
      "loss": 0.0096,
      "step": 630
    },
    {
      "epoch": 0.24427480916030533,
      "grad_norm": 0.09080683439970016,
      "learning_rate": 3.7529726721108305e-05,
      "loss": 0.0113,
      "step": 640
    },
    {
      "epoch": 0.2480916030534351,
      "grad_norm": 0.026247017085552216,
      "learning_rate": 3.739989256382957e-05,
      "loss": 0.0117,
      "step": 650
    },
    {
      "epoch": 0.25190839694656486,
      "grad_norm": 0.116756871342659,
      "learning_rate": 3.726696987326319e-05,
      "loss": 0.0097,
      "step": 660
    },
    {
      "epoch": 0.25572519083969464,
      "grad_norm": 0.23034921288490295,
      "learning_rate": 3.713098224358673e-05,
      "loss": 0.0072,
      "step": 670
    },
    {
      "epoch": 0.2595419847328244,
      "grad_norm": 0.03517864644527435,
      "learning_rate": 3.699195381301364e-05,
      "loss": 0.0048,
      "step": 680
    },
    {
      "epoch": 0.2633587786259542,
      "grad_norm": 0.23623879253864288,
      "learning_rate": 3.684990925950871e-05,
      "loss": 0.0103,
      "step": 690
    },
    {
      "epoch": 0.26717557251908397,
      "grad_norm": 0.043465759605169296,
      "learning_rate": 3.6704873796407605e-05,
      "loss": 0.0118,
      "step": 700
    },
    {
      "epoch": 0.27099236641221375,
      "grad_norm": 0.2958603799343109,
      "learning_rate": 3.655687316794144e-05,
      "loss": 0.0092,
      "step": 710
    },
    {
      "epoch": 0.2748091603053435,
      "grad_norm": 0.20194493234157562,
      "learning_rate": 3.640593364466712e-05,
      "loss": 0.0097,
      "step": 720
    },
    {
      "epoch": 0.2786259541984733,
      "grad_norm": 1.3390525579452515,
      "learning_rate": 3.625208201880421e-05,
      "loss": 0.0155,
      "step": 730
    },
    {
      "epoch": 0.2824427480916031,
      "grad_norm": 0.41017207503318787,
      "learning_rate": 3.609534559947926e-05,
      "loss": 0.0122,
      "step": 740
    },
    {
      "epoch": 0.2862595419847328,
      "grad_norm": 0.30380892753601074,
      "learning_rate": 3.5935752207878315e-05,
      "loss": 0.0112,
      "step": 750
    },
    {
      "epoch": 0.2900763358778626,
      "grad_norm": 0.3873494863510132,
      "learning_rate": 3.5773330172308627e-05,
      "loss": 0.0067,
      "step": 760
    },
    {
      "epoch": 0.29389312977099236,
      "grad_norm": 0.4039303958415985,
      "learning_rate": 3.5608108323170246e-05,
      "loss": 0.0109,
      "step": 770
    },
    {
      "epoch": 0.29770992366412213,
      "grad_norm": 0.5778370499610901,
      "learning_rate": 3.544011598783855e-05,
      "loss": 0.0177,
      "step": 780
    },
    {
      "epoch": 0.3015267175572519,
      "grad_norm": 0.032092221081256866,
      "learning_rate": 3.526938298545858e-05,
      "loss": 0.0144,
      "step": 790
    },
    {
      "epoch": 0.3053435114503817,
      "grad_norm": 0.06190834194421768,
      "learning_rate": 3.509593962165199e-05,
      "loss": 0.0117,
      "step": 800
    },
    {
      "epoch": 0.30916030534351147,
      "grad_norm": 0.609595000743866,
      "learning_rate": 3.491981668313776e-05,
      "loss": 0.0141,
      "step": 810
    },
    {
      "epoch": 0.31297709923664124,
      "grad_norm": 0.14446590840816498,
      "learning_rate": 3.474104543226746e-05,
      "loss": 0.0125,
      "step": 820
    },
    {
      "epoch": 0.31679389312977096,
      "grad_norm": 0.23196451365947723,
      "learning_rate": 3.455965760147604e-05,
      "loss": 0.0068,
      "step": 830
    },
    {
      "epoch": 0.32061068702290074,
      "grad_norm": 0.4062262177467346,
      "learning_rate": 3.4375685387649266e-05,
      "loss": 0.0157,
      "step": 840
    },
    {
      "epoch": 0.3244274809160305,
      "grad_norm": 0.16551926732063293,
      "learning_rate": 3.4189161446408706e-05,
      "loss": 0.0048,
      "step": 850
    },
    {
      "epoch": 0.3282442748091603,
      "grad_norm": 0.1871049553155899,
      "learning_rate": 3.4000118886315173e-05,
      "loss": 0.0082,
      "step": 860
    },
    {
      "epoch": 0.3320610687022901,
      "grad_norm": 0.437691330909729,
      "learning_rate": 3.3808591262991935e-05,
      "loss": 0.0133,
      "step": 870
    },
    {
      "epoch": 0.33587786259541985,
      "grad_norm": 0.24410566687583923,
      "learning_rate": 3.361461257316845e-05,
      "loss": 0.007,
      "step": 880
    },
    {
      "epoch": 0.33969465648854963,
      "grad_norm": 0.532948911190033,
      "learning_rate": 3.341821724864585e-05,
      "loss": 0.0097,
      "step": 890
    },
    {
      "epoch": 0.3435114503816794,
      "grad_norm": 0.1803872287273407,
      "learning_rate": 3.321944015018522e-05,
      "loss": 0.0074,
      "step": 900
    },
    {
      "epoch": 0.3473282442748092,
      "grad_norm": 0.019201336428523064,
      "learning_rate": 3.3018316561319667e-05,
      "loss": 0.0195,
      "step": 910
    },
    {
      "epoch": 0.3511450381679389,
      "grad_norm": 0.38370391726493835,
      "learning_rate": 3.281488218209141e-05,
      "loss": 0.0081,
      "step": 920
    },
    {
      "epoch": 0.3549618320610687,
      "grad_norm": 1.1995326280593872,
      "learning_rate": 3.260917312271491e-05,
      "loss": 0.0181,
      "step": 930
    },
    {
      "epoch": 0.35877862595419846,
      "grad_norm": 0.1598449945449829,
      "learning_rate": 3.2401225897167193e-05,
      "loss": 0.0127,
      "step": 940
    },
    {
      "epoch": 0.36259541984732824,
      "grad_norm": 0.15862394869327545,
      "learning_rate": 3.219107741670653e-05,
      "loss": 0.0096,
      "step": 950
    },
    {
      "epoch": 0.366412213740458,
      "grad_norm": 0.02166523039340973,
      "learning_rate": 3.1978764983320556e-05,
      "loss": 0.0135,
      "step": 960
    },
    {
      "epoch": 0.3702290076335878,
      "grad_norm": 0.05919814854860306,
      "learning_rate": 3.176432628310506e-05,
      "loss": 0.0087,
      "step": 970
    },
    {
      "epoch": 0.37404580152671757,
      "grad_norm": 0.11933150142431259,
      "learning_rate": 3.1547799379574593e-05,
      "loss": 0.0048,
      "step": 980
    },
    {
      "epoch": 0.37786259541984735,
      "grad_norm": 0.044685620814561844,
      "learning_rate": 3.132922270690607e-05,
      "loss": 0.0121,
      "step": 990
    },
    {
      "epoch": 0.3816793893129771,
      "grad_norm": 0.5684109330177307,
      "learning_rate": 3.1108635063116604e-05,
      "loss": 0.0107,
      "step": 1000
    },
    {
      "epoch": 0.3816793893129771,
      "eval_loss": 0.03127766400575638,
      "eval_runtime": 140.1532,
      "eval_samples_per_second": 56.952,
      "eval_steps_per_second": 0.3,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2620,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.056287130325811e+17,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}