{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9928514694201747,
  "eval_steps": 500,
  "global_step": 942,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03177124702144559,
      "grad_norm": 3.4397125264946693,
      "learning_rate": 5e-06,
      "loss": 0.8269,
      "step": 10
    },
    {
      "epoch": 0.06354249404289118,
      "grad_norm": 1.3162043926897933,
      "learning_rate": 5e-06,
      "loss": 0.7492,
      "step": 20
    },
    {
      "epoch": 0.09531374106433678,
      "grad_norm": 1.740768639790779,
      "learning_rate": 5e-06,
      "loss": 0.7286,
      "step": 30
    },
    {
      "epoch": 0.12708498808578236,
      "grad_norm": 1.047097510755796,
      "learning_rate": 5e-06,
      "loss": 0.7128,
      "step": 40
    },
    {
      "epoch": 0.15885623510722796,
      "grad_norm": 2.1299057435530897,
      "learning_rate": 5e-06,
      "loss": 0.696,
      "step": 50
    },
    {
      "epoch": 0.19062748212867356,
      "grad_norm": 1.334088036223787,
      "learning_rate": 5e-06,
      "loss": 0.6873,
      "step": 60
    },
    {
      "epoch": 0.22239872915011913,
      "grad_norm": 1.2813478557952303,
      "learning_rate": 5e-06,
      "loss": 0.6917,
      "step": 70
    },
    {
      "epoch": 0.2541699761715647,
      "grad_norm": 1.0941086787458663,
      "learning_rate": 5e-06,
      "loss": 0.6812,
      "step": 80
    },
    {
      "epoch": 0.28594122319301035,
      "grad_norm": 0.7478585687808075,
      "learning_rate": 5e-06,
      "loss": 0.6755,
      "step": 90
    },
    {
      "epoch": 0.3177124702144559,
      "grad_norm": 0.6575538230318294,
      "learning_rate": 5e-06,
      "loss": 0.6712,
      "step": 100
    },
    {
      "epoch": 0.3494837172359015,
      "grad_norm": 0.9175291572423222,
      "learning_rate": 5e-06,
      "loss": 0.6712,
      "step": 110
    },
    {
      "epoch": 0.3812549642573471,
      "grad_norm": 0.9905458946212224,
      "learning_rate": 5e-06,
      "loss": 0.6702,
      "step": 120
    },
    {
      "epoch": 0.4130262112787927,
      "grad_norm": 0.5564766884877899,
      "learning_rate": 5e-06,
      "loss": 0.6639,
      "step": 130
    },
    {
      "epoch": 0.44479745830023826,
      "grad_norm": 0.6577684294501048,
      "learning_rate": 5e-06,
      "loss": 0.6664,
      "step": 140
    },
    {
      "epoch": 0.4765687053216839,
      "grad_norm": 0.6804018194983035,
      "learning_rate": 5e-06,
      "loss": 0.6601,
      "step": 150
    },
    {
      "epoch": 0.5083399523431295,
      "grad_norm": 1.179572621196443,
      "learning_rate": 5e-06,
      "loss": 0.6579,
      "step": 160
    },
    {
      "epoch": 0.5401111993645751,
      "grad_norm": 0.6797391956593329,
      "learning_rate": 5e-06,
      "loss": 0.6574,
      "step": 170
    },
    {
      "epoch": 0.5718824463860207,
      "grad_norm": 0.4921523794931075,
      "learning_rate": 5e-06,
      "loss": 0.6611,
      "step": 180
    },
    {
      "epoch": 0.6036536934074662,
      "grad_norm": 0.43865289260205137,
      "learning_rate": 5e-06,
      "loss": 0.6593,
      "step": 190
    },
    {
      "epoch": 0.6354249404289118,
      "grad_norm": 0.6676069056649501,
      "learning_rate": 5e-06,
      "loss": 0.653,
      "step": 200
    },
    {
      "epoch": 0.6671961874503575,
      "grad_norm": 0.6607839687607865,
      "learning_rate": 5e-06,
      "loss": 0.6465,
      "step": 210
    },
    {
      "epoch": 0.698967434471803,
      "grad_norm": 0.5527119566717958,
      "learning_rate": 5e-06,
      "loss": 0.6513,
      "step": 220
    },
    {
      "epoch": 0.7307386814932486,
      "grad_norm": 1.1754706747514654,
      "learning_rate": 5e-06,
      "loss": 0.6552,
      "step": 230
    },
    {
      "epoch": 0.7625099285146942,
      "grad_norm": 0.5274214651086202,
      "learning_rate": 5e-06,
      "loss": 0.6476,
      "step": 240
    },
    {
      "epoch": 0.7942811755361397,
      "grad_norm": 0.5191905788117661,
      "learning_rate": 5e-06,
      "loss": 0.6515,
      "step": 250
    },
    {
      "epoch": 0.8260524225575854,
      "grad_norm": 0.5021156228769978,
      "learning_rate": 5e-06,
      "loss": 0.6391,
      "step": 260
    },
    {
      "epoch": 0.857823669579031,
      "grad_norm": 0.4860867602338113,
      "learning_rate": 5e-06,
      "loss": 0.6488,
      "step": 270
    },
    {
      "epoch": 0.8895949166004765,
      "grad_norm": 0.5477781086085485,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 280
    },
    {
      "epoch": 0.9213661636219221,
      "grad_norm": 0.4541673708322245,
      "learning_rate": 5e-06,
      "loss": 0.6533,
      "step": 290
    },
    {
      "epoch": 0.9531374106433678,
      "grad_norm": 0.6665636520469818,
      "learning_rate": 5e-06,
      "loss": 0.6458,
      "step": 300
    },
    {
      "epoch": 0.9849086576648134,
      "grad_norm": 1.2466688450308792,
      "learning_rate": 5e-06,
      "loss": 0.6416,
      "step": 310
    },
    {
      "epoch": 0.9976171564733916,
      "eval_loss": 0.6390731930732727,
      "eval_runtime": 169.5155,
      "eval_samples_per_second": 50.025,
      "eval_steps_per_second": 0.395,
      "step": 314
    },
    {
      "epoch": 1.016679904686259,
      "grad_norm": 0.8923786845867862,
      "learning_rate": 5e-06,
      "loss": 0.6169,
      "step": 320
    },
    {
      "epoch": 1.0484511517077044,
      "grad_norm": 0.8258460752195317,
      "learning_rate": 5e-06,
      "loss": 0.5989,
      "step": 330
    },
    {
      "epoch": 1.0802223987291502,
      "grad_norm": 0.8974017625848637,
      "learning_rate": 5e-06,
      "loss": 0.6002,
      "step": 340
    },
    {
      "epoch": 1.1119936457505957,
      "grad_norm": 0.6051249372281612,
      "learning_rate": 5e-06,
      "loss": 0.5969,
      "step": 350
    },
    {
      "epoch": 1.1437648927720412,
      "grad_norm": 0.4964829017815635,
      "learning_rate": 5e-06,
      "loss": 0.5932,
      "step": 360
    },
    {
      "epoch": 1.175536139793487,
      "grad_norm": 0.7022791565648377,
      "learning_rate": 5e-06,
      "loss": 0.5891,
      "step": 370
    },
    {
      "epoch": 1.2073073868149324,
      "grad_norm": 0.48687833937339325,
      "learning_rate": 5e-06,
      "loss": 0.5877,
      "step": 380
    },
    {
      "epoch": 1.2390786338363782,
      "grad_norm": 0.8131676427879705,
      "learning_rate": 5e-06,
      "loss": 0.5934,
      "step": 390
    },
    {
      "epoch": 1.2708498808578237,
      "grad_norm": 0.5514260097560263,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 400
    },
    {
      "epoch": 1.3026211278792692,
      "grad_norm": 0.5691182386121336,
      "learning_rate": 5e-06,
      "loss": 0.5924,
      "step": 410
    },
    {
      "epoch": 1.3343923749007147,
      "grad_norm": 0.5887848699748005,
      "learning_rate": 5e-06,
      "loss": 0.59,
      "step": 420
    },
    {
      "epoch": 1.3661636219221605,
      "grad_norm": 0.6171594708352537,
      "learning_rate": 5e-06,
      "loss": 0.5903,
      "step": 430
    },
    {
      "epoch": 1.397934868943606,
      "grad_norm": 0.5006287746249459,
      "learning_rate": 5e-06,
      "loss": 0.5995,
      "step": 440
    },
    {
      "epoch": 1.4297061159650517,
      "grad_norm": 0.5783363834709443,
      "learning_rate": 5e-06,
      "loss": 0.5987,
      "step": 450
    },
    {
      "epoch": 1.4614773629864972,
      "grad_norm": 0.5607638180460264,
      "learning_rate": 5e-06,
      "loss": 0.5883,
      "step": 460
    },
    {
      "epoch": 1.4932486100079427,
      "grad_norm": 0.5510599347940959,
      "learning_rate": 5e-06,
      "loss": 0.5931,
      "step": 470
    },
    {
      "epoch": 1.5250198570293882,
      "grad_norm": 0.6341820224047038,
      "learning_rate": 5e-06,
      "loss": 0.5871,
      "step": 480
    },
    {
      "epoch": 1.556791104050834,
      "grad_norm": 0.5477960140838268,
      "learning_rate": 5e-06,
      "loss": 0.6005,
      "step": 490
    },
    {
      "epoch": 1.5885623510722797,
      "grad_norm": 0.5564566962985059,
      "learning_rate": 5e-06,
      "loss": 0.585,
      "step": 500
    },
    {
      "epoch": 1.6203335980937252,
      "grad_norm": 0.6479737616056668,
      "learning_rate": 5e-06,
      "loss": 0.5934,
      "step": 510
    },
    {
      "epoch": 1.6521048451151708,
      "grad_norm": 0.5569401541147417,
      "learning_rate": 5e-06,
      "loss": 0.5931,
      "step": 520
    },
    {
      "epoch": 1.6838760921366163,
      "grad_norm": 0.4956422971136313,
      "learning_rate": 5e-06,
      "loss": 0.5847,
      "step": 530
    },
    {
      "epoch": 1.715647339158062,
      "grad_norm": 0.5764728462806425,
      "learning_rate": 5e-06,
      "loss": 0.5918,
      "step": 540
    },
    {
      "epoch": 1.7474185861795075,
      "grad_norm": 0.5683144564118795,
      "learning_rate": 5e-06,
      "loss": 0.5893,
      "step": 550
    },
    {
      "epoch": 1.7791898332009533,
      "grad_norm": 0.45523545149858596,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 560
    },
    {
      "epoch": 1.8109610802223988,
      "grad_norm": 0.5067511090235118,
      "learning_rate": 5e-06,
      "loss": 0.5933,
      "step": 570
    },
    {
      "epoch": 1.8427323272438443,
      "grad_norm": 0.5003192884659386,
      "learning_rate": 5e-06,
      "loss": 0.5915,
      "step": 580
    },
    {
      "epoch": 1.8745035742652898,
      "grad_norm": 0.496854313730653,
      "learning_rate": 5e-06,
      "loss": 0.5871,
      "step": 590
    },
    {
      "epoch": 1.9062748212867355,
      "grad_norm": 0.5480065320983066,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 600
    },
    {
      "epoch": 1.938046068308181,
      "grad_norm": 0.4892198010452981,
      "learning_rate": 5e-06,
      "loss": 0.5925,
      "step": 610
    },
    {
      "epoch": 1.9698173153296268,
      "grad_norm": 0.5258022377268232,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 620
    },
    {
      "epoch": 1.9984114376489277,
      "eval_loss": 0.6303147673606873,
      "eval_runtime": 169.9094,
      "eval_samples_per_second": 49.909,
      "eval_steps_per_second": 0.394,
      "step": 629
    },
    {
      "epoch": 2.0015885623510723,
      "grad_norm": 0.6865592089506408,
      "learning_rate": 5e-06,
      "loss": 0.5833,
      "step": 630
    },
    {
      "epoch": 2.033359809372518,
      "grad_norm": 0.734114065829172,
      "learning_rate": 5e-06,
      "loss": 0.5361,
      "step": 640
    },
    {
      "epoch": 2.0651310563939633,
      "grad_norm": 0.6113057952860269,
      "learning_rate": 5e-06,
      "loss": 0.538,
      "step": 650
    },
    {
      "epoch": 2.096902303415409,
      "grad_norm": 0.7419614574245821,
      "learning_rate": 5e-06,
      "loss": 0.5393,
      "step": 660
    },
    {
      "epoch": 2.128673550436855,
      "grad_norm": 0.5125951202265081,
      "learning_rate": 5e-06,
      "loss": 0.5338,
      "step": 670
    },
    {
      "epoch": 2.1604447974583003,
      "grad_norm": 0.5037660268311202,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 680
    },
    {
      "epoch": 2.192216044479746,
      "grad_norm": 0.5393677046760976,
      "learning_rate": 5e-06,
      "loss": 0.5321,
      "step": 690
    },
    {
      "epoch": 2.2239872915011913,
      "grad_norm": 0.5385301073245446,
      "learning_rate": 5e-06,
      "loss": 0.5403,
      "step": 700
    },
    {
      "epoch": 2.255758538522637,
      "grad_norm": 0.7724939064931073,
      "learning_rate": 5e-06,
      "loss": 0.531,
      "step": 710
    },
    {
      "epoch": 2.2875297855440824,
      "grad_norm": 0.607781764707526,
      "learning_rate": 5e-06,
      "loss": 0.5444,
      "step": 720
    },
    {
      "epoch": 2.3193010325655283,
      "grad_norm": 0.6227051590924966,
      "learning_rate": 5e-06,
      "loss": 0.5363,
      "step": 730
    },
    {
      "epoch": 2.351072279586974,
      "grad_norm": 0.5541522360131526,
      "learning_rate": 5e-06,
      "loss": 0.5377,
      "step": 740
    },
    {
      "epoch": 2.3828435266084194,
      "grad_norm": 0.6694258055269825,
      "learning_rate": 5e-06,
      "loss": 0.55,
      "step": 750
    },
    {
      "epoch": 2.414614773629865,
      "grad_norm": 0.6024726800298386,
      "learning_rate": 5e-06,
      "loss": 0.542,
      "step": 760
    },
    {
      "epoch": 2.4463860206513104,
      "grad_norm": 0.49906984309919067,
      "learning_rate": 5e-06,
      "loss": 0.5415,
      "step": 770
    },
    {
      "epoch": 2.4781572676727563,
      "grad_norm": 0.5863593266075681,
      "learning_rate": 5e-06,
      "loss": 0.5451,
      "step": 780
    },
    {
      "epoch": 2.509928514694202,
      "grad_norm": 0.5802769154479103,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 790
    },
    {
      "epoch": 2.5416997617156474,
      "grad_norm": 0.5886600271892876,
      "learning_rate": 5e-06,
      "loss": 0.5424,
      "step": 800
    },
    {
      "epoch": 2.573471008737093,
      "grad_norm": 0.6006325307836762,
      "learning_rate": 5e-06,
      "loss": 0.5425,
      "step": 810
    },
    {
      "epoch": 2.6052422557585384,
      "grad_norm": 0.6296696985193921,
      "learning_rate": 5e-06,
      "loss": 0.5406,
      "step": 820
    },
    {
      "epoch": 2.6370135027799844,
      "grad_norm": 0.6082995671271276,
      "learning_rate": 5e-06,
      "loss": 0.5371,
      "step": 830
    },
    {
      "epoch": 2.6687847498014294,
      "grad_norm": 0.6361605601027807,
      "learning_rate": 5e-06,
      "loss": 0.5422,
      "step": 840
    },
    {
      "epoch": 2.7005559968228754,
      "grad_norm": 0.5254863126848727,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 850
    },
    {
      "epoch": 2.732327243844321,
      "grad_norm": 0.7335792362538626,
      "learning_rate": 5e-06,
      "loss": 0.5423,
      "step": 860
    },
    {
      "epoch": 2.7640984908657664,
      "grad_norm": 0.6113916939877616,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 870
    },
    {
      "epoch": 2.795869737887212,
      "grad_norm": 0.49594942341373327,
      "learning_rate": 5e-06,
      "loss": 0.542,
      "step": 880
    },
    {
      "epoch": 2.8276409849086575,
      "grad_norm": 0.6503566754620093,
      "learning_rate": 5e-06,
      "loss": 0.5408,
      "step": 890
    },
    {
      "epoch": 2.8594122319301034,
      "grad_norm": 0.6016129927241319,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 900
    },
    {
      "epoch": 2.891183478951549,
      "grad_norm": 0.5016315173194889,
      "learning_rate": 5e-06,
      "loss": 0.5451,
      "step": 910
    },
    {
      "epoch": 2.9229547259729944,
      "grad_norm": 0.585287305851242,
      "learning_rate": 5e-06,
      "loss": 0.5433,
      "step": 920
    },
    {
      "epoch": 2.95472597299444,
      "grad_norm": 0.5879035774581888,
      "learning_rate": 5e-06,
      "loss": 0.5467,
      "step": 930
    },
    {
      "epoch": 2.9864972200158855,
      "grad_norm": 0.4888796678433693,
      "learning_rate": 5e-06,
      "loss": 0.5442,
      "step": 940
    },
    {
      "epoch": 2.9928514694201747,
      "eval_loss": 0.6355611085891724,
      "eval_runtime": 170.8785,
      "eval_samples_per_second": 49.626,
      "eval_steps_per_second": 0.392,
      "step": 942
    },
    {
      "epoch": 2.9928514694201747,
      "step": 942,
      "total_flos": 1577466325893120.0,
      "train_loss": 0.6022182443592452,
      "train_runtime": 28264.0109,
      "train_samples_per_second": 17.101,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 942,
  "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": 1577466325893120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}