{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.995245641838352,
  "eval_steps": 500,
  "global_step": 945,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03169572107765452,
      "grad_norm": 5.002077210650163,
      "learning_rate": 5e-06,
      "loss": 0.8641,
      "step": 10
    },
    {
      "epoch": 0.06339144215530904,
      "grad_norm": 1.0041823875277287,
      "learning_rate": 5e-06,
      "loss": 0.7817,
      "step": 20
    },
    {
      "epoch": 0.09508716323296355,
      "grad_norm": 0.7267029948833413,
      "learning_rate": 5e-06,
      "loss": 0.7429,
      "step": 30
    },
    {
      "epoch": 0.12678288431061807,
      "grad_norm": 0.624153716022588,
      "learning_rate": 5e-06,
      "loss": 0.7173,
      "step": 40
    },
    {
      "epoch": 0.15847860538827258,
      "grad_norm": 0.566309592028478,
      "learning_rate": 5e-06,
      "loss": 0.7097,
      "step": 50
    },
    {
      "epoch": 0.1901743264659271,
      "grad_norm": 0.8668636299502676,
      "learning_rate": 5e-06,
      "loss": 0.7121,
      "step": 60
    },
    {
      "epoch": 0.2218700475435816,
      "grad_norm": 0.684958377999424,
      "learning_rate": 5e-06,
      "loss": 0.6997,
      "step": 70
    },
    {
      "epoch": 0.25356576862123614,
      "grad_norm": 0.5215403890931859,
      "learning_rate": 5e-06,
      "loss": 0.6898,
      "step": 80
    },
    {
      "epoch": 0.28526148969889065,
      "grad_norm": 0.4816858922190366,
      "learning_rate": 5e-06,
      "loss": 0.6867,
      "step": 90
    },
    {
      "epoch": 0.31695721077654515,
      "grad_norm": 0.7154671815551356,
      "learning_rate": 5e-06,
      "loss": 0.6748,
      "step": 100
    },
    {
      "epoch": 0.3486529318541997,
      "grad_norm": 0.4058042716028271,
      "learning_rate": 5e-06,
      "loss": 0.6765,
      "step": 110
    },
    {
      "epoch": 0.3803486529318542,
      "grad_norm": 0.39453817862211543,
      "learning_rate": 5e-06,
      "loss": 0.6734,
      "step": 120
    },
    {
      "epoch": 0.4120443740095087,
      "grad_norm": 0.6699185012363967,
      "learning_rate": 5e-06,
      "loss": 0.6736,
      "step": 130
    },
    {
      "epoch": 0.4437400950871632,
      "grad_norm": 0.7047289653585949,
      "learning_rate": 5e-06,
      "loss": 0.6675,
      "step": 140
    },
    {
      "epoch": 0.4754358161648177,
      "grad_norm": 0.5651557636719974,
      "learning_rate": 5e-06,
      "loss": 0.67,
      "step": 150
    },
    {
      "epoch": 0.5071315372424723,
      "grad_norm": 0.7485262569132396,
      "learning_rate": 5e-06,
      "loss": 0.6702,
      "step": 160
    },
    {
      "epoch": 0.5388272583201268,
      "grad_norm": 0.5937798065160911,
      "learning_rate": 5e-06,
      "loss": 0.6684,
      "step": 170
    },
    {
      "epoch": 0.5705229793977813,
      "grad_norm": 0.42087472284785377,
      "learning_rate": 5e-06,
      "loss": 0.6696,
      "step": 180
    },
    {
      "epoch": 0.6022187004754358,
      "grad_norm": 0.6838376914191113,
      "learning_rate": 5e-06,
      "loss": 0.6736,
      "step": 190
    },
    {
      "epoch": 0.6339144215530903,
      "grad_norm": 0.6779376025706788,
      "learning_rate": 5e-06,
      "loss": 0.6568,
      "step": 200
    },
    {
      "epoch": 0.6656101426307448,
      "grad_norm": 0.5461606311887525,
      "learning_rate": 5e-06,
      "loss": 0.6574,
      "step": 210
    },
    {
      "epoch": 0.6973058637083994,
      "grad_norm": 0.4896365938443348,
      "learning_rate": 5e-06,
      "loss": 0.6661,
      "step": 220
    },
    {
      "epoch": 0.7290015847860539,
      "grad_norm": 0.5061952793250585,
      "learning_rate": 5e-06,
      "loss": 0.6568,
      "step": 230
    },
    {
      "epoch": 0.7606973058637084,
      "grad_norm": 0.5463009018381003,
      "learning_rate": 5e-06,
      "loss": 0.6542,
      "step": 240
    },
    {
      "epoch": 0.7923930269413629,
      "grad_norm": 0.4203063093835648,
      "learning_rate": 5e-06,
      "loss": 0.6528,
      "step": 250
    },
    {
      "epoch": 0.8240887480190174,
      "grad_norm": 0.5364831104473663,
      "learning_rate": 5e-06,
      "loss": 0.6596,
      "step": 260
    },
    {
      "epoch": 0.8557844690966719,
      "grad_norm": 0.5836930133680968,
      "learning_rate": 5e-06,
      "loss": 0.6588,
      "step": 270
    },
    {
      "epoch": 0.8874801901743264,
      "grad_norm": 0.4587582257779609,
      "learning_rate": 5e-06,
      "loss": 0.6569,
      "step": 280
    },
    {
      "epoch": 0.919175911251981,
      "grad_norm": 0.5211716841949762,
      "learning_rate": 5e-06,
      "loss": 0.6483,
      "step": 290
    },
    {
      "epoch": 0.9508716323296355,
      "grad_norm": 0.6487858529916467,
      "learning_rate": 5e-06,
      "loss": 0.6492,
      "step": 300
    },
    {
      "epoch": 0.9825673534072901,
      "grad_norm": 0.4204562899057241,
      "learning_rate": 5e-06,
      "loss": 0.6466,
      "step": 310
    },
    {
      "epoch": 0.9984152139461173,
      "eval_loss": 0.6489410996437073,
      "eval_runtime": 170.8766,
      "eval_samples_per_second": 49.72,
      "eval_steps_per_second": 0.392,
      "step": 315
    },
    {
      "epoch": 1.0142630744849446,
      "grad_norm": 0.7909658922802345,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 320
    },
    {
      "epoch": 1.045958795562599,
      "grad_norm": 0.5926743835661953,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 330
    },
    {
      "epoch": 1.0776545166402536,
      "grad_norm": 0.5086080623346543,
      "learning_rate": 5e-06,
      "loss": 0.6184,
      "step": 340
    },
    {
      "epoch": 1.109350237717908,
      "grad_norm": 0.5244697888828465,
      "learning_rate": 5e-06,
      "loss": 0.6175,
      "step": 350
    },
    {
      "epoch": 1.1410459587955626,
      "grad_norm": 0.5658308922949424,
      "learning_rate": 5e-06,
      "loss": 0.6194,
      "step": 360
    },
    {
      "epoch": 1.172741679873217,
      "grad_norm": 0.503634416974372,
      "learning_rate": 5e-06,
      "loss": 0.6139,
      "step": 370
    },
    {
      "epoch": 1.2044374009508716,
      "grad_norm": 0.5134026739487886,
      "learning_rate": 5e-06,
      "loss": 0.6145,
      "step": 380
    },
    {
      "epoch": 1.236133122028526,
      "grad_norm": 0.6504374930809814,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 390
    },
    {
      "epoch": 1.2678288431061806,
      "grad_norm": 0.5488394685032496,
      "learning_rate": 5e-06,
      "loss": 0.6178,
      "step": 400
    },
    {
      "epoch": 1.299524564183835,
      "grad_norm": 0.5637848064827178,
      "learning_rate": 5e-06,
      "loss": 0.6139,
      "step": 410
    },
    {
      "epoch": 1.3312202852614896,
      "grad_norm": 0.4929677114414056,
      "learning_rate": 5e-06,
      "loss": 0.6115,
      "step": 420
    },
    {
      "epoch": 1.3629160063391441,
      "grad_norm": 0.5260476600034447,
      "learning_rate": 5e-06,
      "loss": 0.6097,
      "step": 430
    },
    {
      "epoch": 1.3946117274167986,
      "grad_norm": 0.44727265179318326,
      "learning_rate": 5e-06,
      "loss": 0.6092,
      "step": 440
    },
    {
      "epoch": 1.4263074484944531,
      "grad_norm": 0.601618414738924,
      "learning_rate": 5e-06,
      "loss": 0.6163,
      "step": 450
    },
    {
      "epoch": 1.4580031695721076,
      "grad_norm": 0.49038888044450907,
      "learning_rate": 5e-06,
      "loss": 0.6095,
      "step": 460
    },
    {
      "epoch": 1.4896988906497624,
      "grad_norm": 0.5097913207122167,
      "learning_rate": 5e-06,
      "loss": 0.6136,
      "step": 470
    },
    {
      "epoch": 1.5213946117274166,
      "grad_norm": 0.6535026695551385,
      "learning_rate": 5e-06,
      "loss": 0.6131,
      "step": 480
    },
    {
      "epoch": 1.5530903328050714,
      "grad_norm": 0.5478546695070423,
      "learning_rate": 5e-06,
      "loss": 0.6117,
      "step": 490
    },
    {
      "epoch": 1.5847860538827259,
      "grad_norm": 0.47440853445302006,
      "learning_rate": 5e-06,
      "loss": 0.6275,
      "step": 500
    },
    {
      "epoch": 1.6164817749603804,
      "grad_norm": 0.47242075964062596,
      "learning_rate": 5e-06,
      "loss": 0.6185,
      "step": 510
    },
    {
      "epoch": 1.6481774960380349,
      "grad_norm": 0.4932550522259784,
      "learning_rate": 5e-06,
      "loss": 0.6188,
      "step": 520
    },
    {
      "epoch": 1.6798732171156894,
      "grad_norm": 0.49155732750425185,
      "learning_rate": 5e-06,
      "loss": 0.618,
      "step": 530
    },
    {
      "epoch": 1.7115689381933439,
      "grad_norm": 0.3852759456359732,
      "learning_rate": 5e-06,
      "loss": 0.6108,
      "step": 540
    },
    {
      "epoch": 1.7432646592709984,
      "grad_norm": 0.45204407263371044,
      "learning_rate": 5e-06,
      "loss": 0.6128,
      "step": 550
    },
    {
      "epoch": 1.7749603803486529,
      "grad_norm": 0.45233482856711393,
      "learning_rate": 5e-06,
      "loss": 0.6129,
      "step": 560
    },
    {
      "epoch": 1.8066561014263076,
      "grad_norm": 0.40723601066321924,
      "learning_rate": 5e-06,
      "loss": 0.6141,
      "step": 570
    },
    {
      "epoch": 1.8383518225039621,
      "grad_norm": 0.49021896910219537,
      "learning_rate": 5e-06,
      "loss": 0.6048,
      "step": 580
    },
    {
      "epoch": 1.8700475435816166,
      "grad_norm": 0.4137149099162348,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 590
    },
    {
      "epoch": 1.9017432646592711,
      "grad_norm": 0.43600015726361796,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 600
    },
    {
      "epoch": 1.9334389857369256,
      "grad_norm": 0.5983745339259906,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 610
    },
    {
      "epoch": 1.9651347068145801,
      "grad_norm": 0.44191449750213707,
      "learning_rate": 5e-06,
      "loss": 0.6105,
      "step": 620
    },
    {
      "epoch": 1.9968304278922346,
      "grad_norm": 0.41833944166046033,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 630
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6384235620498657,
      "eval_runtime": 172.0031,
      "eval_samples_per_second": 49.394,
      "eval_steps_per_second": 0.39,
      "step": 631
    },
    {
      "epoch": 2.028526148969889,
      "grad_norm": 0.502856771702954,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 640
    },
    {
      "epoch": 2.0602218700475436,
      "grad_norm": 0.47143025065214356,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 650
    },
    {
      "epoch": 2.091917591125198,
      "grad_norm": 0.4378418090102208,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 660
    },
    {
      "epoch": 2.1236133122028527,
      "grad_norm": 0.6058133875665858,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 670
    },
    {
      "epoch": 2.155309033280507,
      "grad_norm": 0.47371009100624967,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 680
    },
    {
      "epoch": 2.1870047543581617,
      "grad_norm": 0.4991361347258838,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 690
    },
    {
      "epoch": 2.218700475435816,
      "grad_norm": 0.5359340720470293,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 700
    },
    {
      "epoch": 2.2503961965134707,
      "grad_norm": 0.4893107425446941,
      "learning_rate": 5e-06,
      "loss": 0.5751,
      "step": 710
    },
    {
      "epoch": 2.282091917591125,
      "grad_norm": 0.44259860353438574,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 720
    },
    {
      "epoch": 2.3137876386687797,
      "grad_norm": 0.7444991766460172,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 730
    },
    {
      "epoch": 2.345483359746434,
      "grad_norm": 0.39951135529059456,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 740
    },
    {
      "epoch": 2.3771790808240887,
      "grad_norm": 0.4742761127635493,
      "learning_rate": 5e-06,
      "loss": 0.5782,
      "step": 750
    },
    {
      "epoch": 2.408874801901743,
      "grad_norm": 0.585898905502293,
      "learning_rate": 5e-06,
      "loss": 0.5755,
      "step": 760
    },
    {
      "epoch": 2.4405705229793977,
      "grad_norm": 0.6170117233151285,
      "learning_rate": 5e-06,
      "loss": 0.5752,
      "step": 770
    },
    {
      "epoch": 2.472266244057052,
      "grad_norm": 0.45913749051577313,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 780
    },
    {
      "epoch": 2.5039619651347067,
      "grad_norm": 0.4584152935889332,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 790
    },
    {
      "epoch": 2.535657686212361,
      "grad_norm": 0.42856693615532904,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 800
    },
    {
      "epoch": 2.5673534072900157,
      "grad_norm": 0.5273756256360088,
      "learning_rate": 5e-06,
      "loss": 0.5794,
      "step": 810
    },
    {
      "epoch": 2.59904912836767,
      "grad_norm": 0.46899833087451076,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 820
    },
    {
      "epoch": 2.6307448494453247,
      "grad_norm": 0.484076993070708,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 830
    },
    {
      "epoch": 2.662440570522979,
      "grad_norm": 0.4349705497114564,
      "learning_rate": 5e-06,
      "loss": 0.5752,
      "step": 840
    },
    {
      "epoch": 2.6941362916006337,
      "grad_norm": 0.5194459175036173,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 850
    },
    {
      "epoch": 2.7258320126782882,
      "grad_norm": 0.5337441754498483,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 860
    },
    {
      "epoch": 2.7575277337559427,
      "grad_norm": 0.5009650532937617,
      "learning_rate": 5e-06,
      "loss": 0.5772,
      "step": 870
    },
    {
      "epoch": 2.7892234548335972,
      "grad_norm": 0.46031841411878416,
      "learning_rate": 5e-06,
      "loss": 0.5817,
      "step": 880
    },
    {
      "epoch": 2.8209191759112517,
      "grad_norm": 0.5673120105732073,
      "learning_rate": 5e-06,
      "loss": 0.5808,
      "step": 890
    },
    {
      "epoch": 2.8526148969889062,
      "grad_norm": 0.614359093779175,
      "learning_rate": 5e-06,
      "loss": 0.5801,
      "step": 900
    },
    {
      "epoch": 2.8843106180665607,
      "grad_norm": 0.5019306735450663,
      "learning_rate": 5e-06,
      "loss": 0.5813,
      "step": 910
    },
    {
      "epoch": 2.9160063391442153,
      "grad_norm": 0.43396332531042875,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 920
    },
    {
      "epoch": 2.94770206022187,
      "grad_norm": 0.4457359128495874,
      "learning_rate": 5e-06,
      "loss": 0.5798,
      "step": 930
    },
    {
      "epoch": 2.9793977812995247,
      "grad_norm": 0.4575875895533821,
      "learning_rate": 5e-06,
      "loss": 0.5816,
      "step": 940
    },
    {
      "epoch": 2.995245641838352,
      "eval_loss": 0.637653648853302,
      "eval_runtime": 171.7653,
      "eval_samples_per_second": 49.463,
      "eval_steps_per_second": 0.39,
      "step": 945
    },
    {
      "epoch": 2.995245641838352,
      "step": 945,
      "total_flos": 1582491437629440.0,
      "train_loss": 0.6238129633444327,
      "train_runtime": 28593.492,
      "train_samples_per_second": 16.935,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 945,
  "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": 1582491437629440.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}