{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 678,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.0978,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.1379,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.9998,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.8656,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.7844,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.352941176470589e-05,
      "loss": 0.7223,
      "step": 25
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.823529411764706e-05,
      "loss": 0.672,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00010294117647058823,
      "loss": 0.6365,
      "step": 35
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00011764705882352942,
      "loss": 0.6207,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001323529411764706,
      "loss": 0.6073,
      "step": 45
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00014705882352941178,
      "loss": 0.6086,
      "step": 50
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00016176470588235295,
      "loss": 0.5898,
      "step": 55
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.5777,
      "step": 60
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001911764705882353,
      "loss": 0.5774,
      "step": 65
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019999469523400122,
      "loss": 0.5809,
      "step": 70
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019993502307985724,
      "loss": 0.5749,
      "step": 75
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019980908751249555,
      "loss": 0.5782,
      "step": 80
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019961697203537952,
      "loss": 0.5809,
      "step": 85
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019935880403355253,
      "loss": 0.5669,
      "step": 90
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001990347546891733,
      "loss": 0.573,
      "step": 95
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019864503886801106,
      "loss": 0.5774,
      "step": 100
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019818991497697565,
      "loss": 0.58,
      "step": 105
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019766968479277683,
      "loss": 0.577,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019708469326182678,
      "loss": 0.5631,
      "step": 115
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001964353282715183,
      "loss": 0.5676,
      "step": 120
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019572202039303,
      "loss": 0.5722,
      "step": 125
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019494524259582992,
      "loss": 0.5665,
      "step": 130
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019410550993406603,
      "loss": 0.5767,
      "step": 135
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019320337920505153,
      "loss": 0.5553,
      "step": 140
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019223944858007253,
      "loss": 0.5646,
      "step": 145
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019121435720776122,
      "loss": 0.5625,
      "step": 150
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019012878479029906,
      "loss": 0.5611,
      "step": 155
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018898345113272998,
      "loss": 0.5602,
      "step": 160
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00018777911566568282,
      "loss": 0.5731,
      "step": 165
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001865165769418196,
      "loss": 0.5587,
      "step": 170
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001851966721063431,
      "loss": 0.5729,
      "step": 175
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018382027634191524,
      "loss": 0.5558,
      "step": 180
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018238830228835417,
      "loss": 0.55,
      "step": 185
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.5561,
      "step": 190
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001793614535036137,
      "loss": 0.552,
      "step": 195
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00017776858576983712,
      "loss": 0.5615,
      "step": 200
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00017612415241096327,
      "loss": 0.5577,
      "step": 205
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001744292437931502,
      "loss": 0.559,
      "step": 210
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00017268498375093202,
      "loss": 0.5467,
      "step": 215
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00017089252884204377,
      "loss": 0.564,
      "step": 220
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001690530675805482,
      "loss": 0.5498,
      "step": 225
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5578014254570007,
      "eval_runtime": 40.6018,
      "eval_samples_per_second": 1.33,
      "eval_steps_per_second": 0.172,
      "step": 226
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001671678196487741,
      "loss": 0.5024,
      "step": 230
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00016523803508858732,
      "loss": 0.4999,
      "step": 235
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00016326499347253207,
      "loss": 0.4973,
      "step": 240
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00016125000305539094,
      "loss": 0.4988,
      "step": 245
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001591943999067273,
      "loss": 0.5004,
      "step": 250
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00015709954702498397,
      "loss": 0.4931,
      "step": 255
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001549668334337271,
      "loss": 0.4909,
      "step": 260
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00015279767326063296,
      "loss": 0.4924,
      "step": 265
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00015059350479982965,
      "loss": 0.4958,
      "step": 270
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00014835578955821457,
      "loss": 0.4941,
      "step": 275
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00014608601128638027,
      "loss": 0.4854,
      "step": 280
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00014378567499479168,
      "loss": 0.4858,
      "step": 285
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00014145630595586607,
      "loss": 0.4914,
      "step": 290
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00013909944869261855,
      "loss": 0.4841,
      "step": 295
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00013671666595454295,
      "loss": 0.4931,
      "step": 300
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00013430953768140723,
      "loss": 0.5001,
      "step": 305
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00013187965995565098,
      "loss": 0.5034,
      "step": 310
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00012942864394407879,
      "loss": 0.4865,
      "step": 315
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00012695811482955227,
      "loss": 0.4919,
      "step": 320
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.000124469710733388,
      "loss": 0.4806,
      "step": 325
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00012196508162917677,
      "loss": 0.4887,
      "step": 330
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00011944588824874388,
      "loss": 0.4826,
      "step": 335
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00011691380098097597,
      "loss": 0.4882,
      "step": 340
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001143704987642448,
      "loss": 0.4881,
      "step": 345
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001118176679731619,
      "loss": 0.4896,
      "step": 350
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00010925700130040266,
      "loss": 0.4799,
      "step": 355
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00010669019663434117,
      "loss": 0.4853,
      "step": 360
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00010411895593323981,
      "loss": 0.4885,
      "step": 365
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00010154498409674051,
      "loss": 0.4864,
      "step": 370
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.896998783540536e-05,
      "loss": 0.4894,
      "step": 375
    },
    {
      "epoch": 1.68,
      "learning_rate": 9.639567453905661e-05,
      "loss": 0.4846,
      "step": 380
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.382375114466644e-05,
      "loss": 0.481,
      "step": 385
    },
    {
      "epoch": 1.73,
      "learning_rate": 9.125592300454676e-05,
      "loss": 0.4834,
      "step": 390
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.869389275558972e-05,
      "loss": 0.4916,
      "step": 395
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.613935919030907e-05,
      "loss": 0.4831,
      "step": 400
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.359401613043012e-05,
      "loss": 0.4769,
      "step": 405
    },
    {
      "epoch": 1.81,
      "learning_rate": 8.1059551303776e-05,
      "loss": 0.4839,
      "step": 410
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.853764522519445e-05,
      "loss": 0.4901,
      "step": 415
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.602997008226726e-05,
      "loss": 0.4893,
      "step": 420
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.353818862654129e-05,
      "loss": 0.4855,
      "step": 425
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.106395307101621e-05,
      "loss": 0.476,
      "step": 430
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.860890399461974e-05,
      "loss": 0.481,
      "step": 435
    },
    {
      "epoch": 1.95,
      "learning_rate": 6.617466925439746e-05,
      "loss": 0.482,
      "step": 440
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.376286290613776e-05,
      "loss": 0.494,
      "step": 445
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.137508413414784e-05,
      "loss": 0.4788,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.557712197303772,
      "eval_runtime": 40.1816,
      "eval_samples_per_second": 1.344,
      "eval_steps_per_second": 0.174,
      "step": 452
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.901291619089081e-05,
      "loss": 0.4471,
      "step": 455
    },
    {
      "epoch": 2.04,
      "learning_rate": 5.667792534718639e-05,
      "loss": 0.4053,
      "step": 460
    },
    {
      "epoch": 2.06,
      "learning_rate": 5.437165985367145e-05,
      "loss": 0.4078,
      "step": 465
    },
    {
      "epoch": 2.08,
      "learning_rate": 5.2095648914209525e-05,
      "loss": 0.4129,
      "step": 470
    },
    {
      "epoch": 2.1,
      "learning_rate": 4.9851401671928934e-05,
      "loss": 0.41,
      "step": 475
    },
    {
      "epoch": 2.12,
      "learning_rate": 4.7640406208563224e-05,
      "loss": 0.3972,
      "step": 480
    },
    {
      "epoch": 2.15,
      "learning_rate": 4.546412855775595e-05,
      "loss": 0.3995,
      "step": 485
    },
    {
      "epoch": 2.17,
      "learning_rate": 4.3324011732985433e-05,
      "loss": 0.3996,
      "step": 490
    },
    {
      "epoch": 2.19,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.4089,
      "step": 495
    },
    {
      "epoch": 2.21,
      "learning_rate": 3.9157911789668525e-05,
      "loss": 0.4055,
      "step": 500
    },
    {
      "epoch": 2.23,
      "learning_rate": 3.7134691066061825e-05,
      "loss": 0.401,
      "step": 505
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.515315412672384e-05,
      "loss": 0.3981,
      "step": 510
    },
    {
      "epoch": 2.28,
      "learning_rate": 3.321461485938847e-05,
      "loss": 0.4027,
      "step": 515
    },
    {
      "epoch": 2.3,
      "learning_rate": 3.132035864153958e-05,
      "loss": 0.3921,
      "step": 520
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.947164148812198e-05,
      "loss": 0.4034,
      "step": 525
    },
    {
      "epoch": 2.35,
      "learning_rate": 2.766968921872213e-05,
      "loss": 0.4035,
      "step": 530
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.5915696644769915e-05,
      "loss": 0.3863,
      "step": 535
    },
    {
      "epoch": 2.39,
      "learning_rate": 2.4210826777301153e-05,
      "loss": 0.3936,
      "step": 540
    },
    {
      "epoch": 2.41,
      "learning_rate": 2.2556210055805793e-05,
      "loss": 0.4058,
      "step": 545
    },
    {
      "epoch": 2.43,
      "learning_rate": 2.0952943598672846e-05,
      "loss": 0.4054,
      "step": 550
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.9402090475729795e-05,
      "loss": 0.3956,
      "step": 555
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.7904679003358283e-05,
      "loss": 0.4115,
      "step": 560
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.6461702062653307e-05,
      "loss": 0.3995,
      "step": 565
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.507411644107879e-05,
      "loss": 0.389,
      "step": 570
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.3742842198055173e-05,
      "loss": 0.394,
      "step": 575
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.2468762054900262e-05,
      "loss": 0.4082,
      "step": 580
    },
    {
      "epoch": 2.59,
      "learning_rate": 1.1252720809527751e-05,
      "loss": 0.4037,
      "step": 585
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.0095524776291165e-05,
      "loss": 0.4072,
      "step": 590
    },
    {
      "epoch": 2.63,
      "learning_rate": 8.997941251345177e-06,
      "loss": 0.4015,
      "step": 595
    },
    {
      "epoch": 2.65,
      "learning_rate": 7.960698003878309e-06,
      "loss": 0.3952,
      "step": 600
    },
    {
      "epoch": 2.68,
      "learning_rate": 6.984482793554781e-06,
      "loss": 0.3996,
      "step": 605
    },
    {
      "epoch": 2.7,
      "learning_rate": 6.06994291448505e-06,
      "loss": 0.3877,
      "step": 610
    },
    {
      "epoch": 2.72,
      "learning_rate": 5.217684766027886e-06,
      "loss": 0.4102,
      "step": 615
    },
    {
      "epoch": 2.74,
      "learning_rate": 4.428273450708065e-06,
      "loss": 0.4056,
      "step": 620
    },
    {
      "epoch": 2.77,
      "learning_rate": 3.702232399516803e-06,
      "loss": 0.4014,
      "step": 625
    },
    {
      "epoch": 2.79,
      "learning_rate": 3.040043024842898e-06,
      "loss": 0.409,
      "step": 630
    },
    {
      "epoch": 2.81,
      "learning_rate": 2.4421444012651564e-06,
      "loss": 0.4061,
      "step": 635
    },
    {
      "epoch": 2.83,
      "learning_rate": 1.908932974417266e-06,
      "loss": 0.4087,
      "step": 640
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.4407622981187253e-06,
      "loss": 0.3909,
      "step": 645
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.0379427999456015e-06,
      "loss": 0.4103,
      "step": 650
    },
    {
      "epoch": 2.9,
      "learning_rate": 7.007415753969348e-07,
      "loss": 0.4012,
      "step": 655
    },
    {
      "epoch": 2.92,
      "learning_rate": 4.2938221079300566e-07,
      "loss": 0.4029,
      "step": 660
    },
    {
      "epoch": 2.94,
      "learning_rate": 2.2404463502315732e-07,
      "loss": 0.4052,
      "step": 665
    },
    {
      "epoch": 2.96,
      "learning_rate": 8.486500024118548e-08,
      "loss": 0.3996,
      "step": 670
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.1935591587641792e-08,
      "loss": 0.3871,
      "step": 675
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5821943879127502,
      "eval_runtime": 40.1449,
      "eval_samples_per_second": 1.345,
      "eval_steps_per_second": 0.174,
      "step": 678
    },
    {
      "epoch": 3.0,
      "step": 678,
      "total_flos": 4.7593079718700646e+17,
      "train_loss": 0.5003105528586733,
      "train_runtime": 13978.5586,
      "train_samples_per_second": 0.387,
      "train_steps_per_second": 0.049
    }
  ],
  "logging_steps": 5,
  "max_steps": 678,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 4.7593079718700646e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}