{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009615384615384616,
      "grad_norm": 4.21875,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 3.0033,
      "step": 1
    },
    {
      "epoch": 0.04807692307692308,
      "grad_norm": 4.0,
      "learning_rate": 9.615384615384616e-06,
      "loss": 3.0098,
      "step": 5
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 3.15625,
      "learning_rate": 1.923076923076923e-05,
      "loss": 2.9448,
      "step": 10
    },
    {
      "epoch": 0.14423076923076922,
      "grad_norm": 4.15625,
      "learning_rate": 2.8846153846153845e-05,
      "loss": 2.7074,
      "step": 15
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 1.8984375,
      "learning_rate": 3.846153846153846e-05,
      "loss": 2.4264,
      "step": 20
    },
    {
      "epoch": 0.2403846153846154,
      "grad_norm": 3.75,
      "learning_rate": 4.8076923076923084e-05,
      "loss": 2.1972,
      "step": 25
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 1.3671875,
      "learning_rate": 5.769230769230769e-05,
      "loss": 1.9962,
      "step": 30
    },
    {
      "epoch": 0.33653846153846156,
      "grad_norm": 5.53125,
      "learning_rate": 6.730769230769232e-05,
      "loss": 1.8086,
      "step": 35
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.65625,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.6425,
      "step": 40
    },
    {
      "epoch": 0.4326923076923077,
      "grad_norm": 0.60546875,
      "learning_rate": 8.653846153846155e-05,
      "loss": 1.5058,
      "step": 45
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 0.5625,
      "learning_rate": 9.615384615384617e-05,
      "loss": 1.401,
      "step": 50
    },
    {
      "epoch": 0.5288461538461539,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00010576923076923077,
      "loss": 1.3223,
      "step": 55
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00011538461538461538,
      "loss": 1.2631,
      "step": 60
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.7578125,
      "learning_rate": 0.000125,
      "loss": 1.2263,
      "step": 65
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 0.66796875,
      "learning_rate": 0.00013461538461538464,
      "loss": 1.1954,
      "step": 70
    },
    {
      "epoch": 0.7211538461538461,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00014423076923076924,
      "loss": 1.1671,
      "step": 75
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.00015384615384615385,
      "loss": 1.1505,
      "step": 80
    },
    {
      "epoch": 0.8173076923076923,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00016346153846153846,
      "loss": 1.1211,
      "step": 85
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001730769230769231,
      "loss": 1.1226,
      "step": 90
    },
    {
      "epoch": 0.9134615384615384,
      "grad_norm": 0.330078125,
      "learning_rate": 0.0001826923076923077,
      "loss": 1.114,
      "step": 95
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00019230769230769233,
      "loss": 1.0978,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.483147621154785,
      "eval_runtime": 0.4801,
      "eval_samples_per_second": 20.827,
      "eval_steps_per_second": 2.083,
      "step": 104
    },
    {
      "epoch": 1.0096153846153846,
      "grad_norm": 0.640625,
      "learning_rate": 0.0001999994367286727,
      "loss": 1.0851,
      "step": 105
    },
    {
      "epoch": 1.0576923076923077,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00019997972289848503,
      "loss": 1.0778,
      "step": 110
    },
    {
      "epoch": 1.1057692307692308,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019993185184710165,
      "loss": 1.0708,
      "step": 115
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 1.484375,
      "learning_rate": 0.00019985583705641418,
      "loss": 1.0615,
      "step": 120
    },
    {
      "epoch": 1.2019230769230769,
      "grad_norm": 0.625,
      "learning_rate": 0.00019975169993441627,
      "loss": 1.0549,
      "step": 125
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.416015625,
      "learning_rate": 0.00019961946980917456,
      "loss": 1.039,
      "step": 130
    },
    {
      "epoch": 1.2980769230769231,
      "grad_norm": 0.3359375,
      "learning_rate": 0.0001994591839205691,
      "loss": 1.0429,
      "step": 135
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.478515625,
      "learning_rate": 0.0001992708874098054,
      "loss": 1.0433,
      "step": 140
    },
    {
      "epoch": 1.3942307692307692,
      "grad_norm": 0.40234375,
      "learning_rate": 0.00019905463330670143,
      "loss": 1.0285,
      "step": 145
    },
    {
      "epoch": 1.4423076923076923,
      "grad_norm": 0.37109375,
      "learning_rate": 0.0001988104825147528,
      "loss": 1.0263,
      "step": 150
    },
    {
      "epoch": 1.4903846153846154,
      "grad_norm": 0.3671875,
      "learning_rate": 0.0001985385037939806,
      "loss": 1.0219,
      "step": 155
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.3125,
      "learning_rate": 0.00019823877374156647,
      "loss": 1.0197,
      "step": 160
    },
    {
      "epoch": 1.5865384615384617,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00019791137677028082,
      "loss": 1.0135,
      "step": 165
    },
    {
      "epoch": 1.6346153846153846,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00019755640508470942,
      "loss": 1.0121,
      "step": 170
    },
    {
      "epoch": 1.6826923076923077,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00019717395865528602,
      "loss": 1.0105,
      "step": 175
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00019676414519013781,
      "loss": 1.0087,
      "step": 180
    },
    {
      "epoch": 1.7788461538461537,
      "grad_norm": 0.79296875,
      "learning_rate": 0.00019632708010475165,
      "loss": 1.0026,
      "step": 185
    },
    {
      "epoch": 1.8269230769230769,
      "grad_norm": 0.7265625,
      "learning_rate": 0.00019586288648946947,
      "loss": 1.0078,
      "step": 190
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.21484375,
      "learning_rate": 0.0001953716950748227,
      "loss": 1.0,
      "step": 195
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00019485364419471454,
      "loss": 0.9957,
      "step": 200
    },
    {
      "epoch": 1.9711538461538463,
      "grad_norm": 0.59375,
      "learning_rate": 0.0001943088797474612,
      "loss": 0.9985,
      "step": 205
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.4666388034820557,
      "eval_runtime": 0.4867,
      "eval_samples_per_second": 20.548,
      "eval_steps_per_second": 2.055,
      "step": 208
    },
    {
      "epoch": 2.019230769230769,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00019373755515470254,
      "loss": 0.9897,
      "step": 210
    },
    {
      "epoch": 2.0673076923076925,
      "grad_norm": 0.453125,
      "learning_rate": 0.00019313983131819407,
      "loss": 0.9717,
      "step": 215
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00019251587657449236,
      "loss": 0.9697,
      "step": 220
    },
    {
      "epoch": 2.1634615384615383,
      "grad_norm": 0.33984375,
      "learning_rate": 0.0001918658666475465,
      "loss": 0.9697,
      "step": 225
    },
    {
      "epoch": 2.2115384615384617,
      "grad_norm": 0.5625,
      "learning_rate": 0.00019118998459920902,
      "loss": 0.9735,
      "step": 230
    },
    {
      "epoch": 2.2596153846153846,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001904884207776804,
      "loss": 0.9675,
      "step": 235
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.41015625,
      "learning_rate": 0.0001897613727639014,
      "loss": 0.9654,
      "step": 240
    },
    {
      "epoch": 2.355769230769231,
      "grad_norm": 0.25,
      "learning_rate": 0.00018900904531590846,
      "loss": 0.9655,
      "step": 245
    },
    {
      "epoch": 2.4038461538461537,
      "grad_norm": 0.341796875,
      "learning_rate": 0.0001882316503111678,
      "loss": 0.9653,
      "step": 250
    },
    {
      "epoch": 2.451923076923077,
      "grad_norm": 0.81640625,
      "learning_rate": 0.00018742940668690464,
      "loss": 0.9729,
      "step": 255
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.33203125,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.9619,
      "step": 260
    },
    {
      "epoch": 2.5480769230769234,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00018575128425558023,
      "loss": 0.9702,
      "step": 265
    },
    {
      "epoch": 2.5961538461538463,
      "grad_norm": 0.48828125,
      "learning_rate": 0.00018487587805699526,
      "loss": 0.964,
      "step": 270
    },
    {
      "epoch": 2.644230769230769,
      "grad_norm": 0.546875,
      "learning_rate": 0.0001839765683227398,
      "loss": 0.9603,
      "step": 275
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.455078125,
      "learning_rate": 0.00018305360832480117,
      "loss": 0.9593,
      "step": 280
    },
    {
      "epoch": 2.7403846153846154,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00018210725799577439,
      "loss": 0.963,
      "step": 285
    },
    {
      "epoch": 2.7884615384615383,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00018113778385565733,
      "loss": 0.9626,
      "step": 290
    },
    {
      "epoch": 2.8365384615384617,
      "grad_norm": 1.515625,
      "learning_rate": 0.00018014545893679115,
      "loss": 0.9655,
      "step": 295
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 0.44921875,
      "learning_rate": 0.0001791305627069662,
      "loss": 0.9599,
      "step": 300
    },
    {
      "epoch": 2.9326923076923075,
      "grad_norm": 0.310546875,
      "learning_rate": 0.00017809338099071577,
      "loss": 0.9557,
      "step": 305
    },
    {
      "epoch": 2.980769230769231,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00017703420588881946,
      "loss": 0.9543,
      "step": 310
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.4561338424682617,
      "eval_runtime": 0.4747,
      "eval_samples_per_second": 21.065,
      "eval_steps_per_second": 2.107,
      "step": 312
    },
    {
      "epoch": 3.0288461538461537,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.0001759533356960391,
      "loss": 0.946,
      "step": 315
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.9384,
      "step": 320
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.0001737277336810124,
      "loss": 0.9299,
      "step": 325
    },
    {
      "epoch": 3.173076923076923,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00017258362865354426,
      "loss": 0.9322,
      "step": 330
    },
    {
      "epoch": 3.2211538461538463,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00017141908194822446,
      "loss": 0.9328,
      "step": 335
    },
    {
      "epoch": 3.269230769230769,
      "grad_norm": 0.28125,
      "learning_rate": 0.00017023442153554777,
      "loss": 0.9307,
      "step": 340
    },
    {
      "epoch": 3.3173076923076925,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.00016902998105061844,
      "loss": 0.9273,
      "step": 345
    },
    {
      "epoch": 3.3653846153846154,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001678060996991891,
      "loss": 0.9324,
      "step": 350
    },
    {
      "epoch": 3.4134615384615383,
      "grad_norm": 0.234375,
      "learning_rate": 0.00016656312216213034,
      "loss": 0.9233,
      "step": 355
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0001653013984983585,
      "loss": 0.925,
      "step": 360
    },
    {
      "epoch": 3.5096153846153846,
      "grad_norm": 0.34765625,
      "learning_rate": 0.00016402128404624882,
      "loss": 0.9351,
      "step": 365
    },
    {
      "epoch": 3.5576923076923075,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00016272313932356162,
      "loss": 0.9266,
      "step": 370
    },
    {
      "epoch": 3.605769230769231,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001614073299259101,
      "loss": 0.9259,
      "step": 375
    },
    {
      "epoch": 3.6538461538461537,
      "grad_norm": 0.2109375,
      "learning_rate": 0.0001600742264237979,
      "loss": 0.9322,
      "step": 380
    },
    {
      "epoch": 3.7019230769230766,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001587242042582554,
      "loss": 0.9327,
      "step": 385
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001573576436351046,
      "loss": 0.9308,
      "step": 390
    },
    {
      "epoch": 3.7980769230769234,
      "grad_norm": 0.3984375,
      "learning_rate": 0.00015597492941788222,
      "loss": 0.9265,
      "step": 395
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.41015625,
      "learning_rate": 0.00015457645101945046,
      "loss": 0.9273,
      "step": 400
    },
    {
      "epoch": 3.894230769230769,
      "grad_norm": 0.25,
      "learning_rate": 0.00015316260229232727,
      "loss": 0.9285,
      "step": 405
    },
    {
      "epoch": 3.9423076923076925,
      "grad_norm": 0.2138671875,
      "learning_rate": 0.00015173378141776568,
      "loss": 0.9243,
      "step": 410
    },
    {
      "epoch": 3.9903846153846154,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.00015029039079361448,
      "loss": 0.92,
      "step": 415
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.4799063205718994,
      "eval_runtime": 0.4817,
      "eval_samples_per_second": 20.76,
      "eval_steps_per_second": 2.076,
      "step": 416
    },
    {
      "epoch": 4.038461538461538,
      "grad_norm": 0.310546875,
      "learning_rate": 0.00014883283692099112,
      "loss": 0.9122,
      "step": 420
    },
    {
      "epoch": 4.086538461538462,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00014736153028979893,
      "loss": 0.9007,
      "step": 425
    },
    {
      "epoch": 4.134615384615385,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00014587688526312143,
      "loss": 0.9098,
      "step": 430
    },
    {
      "epoch": 4.1826923076923075,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00014437931996052518,
      "loss": 0.8987,
      "step": 435
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00014286925614030542,
      "loss": 0.9044,
      "step": 440
    },
    {
      "epoch": 4.278846153846154,
      "grad_norm": 0.27734375,
      "learning_rate": 0.00014134711908070631,
      "loss": 0.8988,
      "step": 445
    },
    {
      "epoch": 4.326923076923077,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0001398133374601501,
      "loss": 0.9037,
      "step": 450
    },
    {
      "epoch": 4.375,
      "grad_norm": 0.248046875,
      "learning_rate": 0.000138268343236509,
      "loss": 0.9034,
      "step": 455
    },
    {
      "epoch": 4.423076923076923,
      "grad_norm": 0.25,
      "learning_rate": 0.00013671257152545277,
      "loss": 0.8994,
      "step": 460
    },
    {
      "epoch": 4.471153846153846,
      "grad_norm": 0.265625,
      "learning_rate": 0.00013514646047790775,
      "loss": 0.9013,
      "step": 465
    },
    {
      "epoch": 4.519230769230769,
      "grad_norm": 0.23828125,
      "learning_rate": 0.0001335704511566605,
      "loss": 0.9069,
      "step": 470
    },
    {
      "epoch": 4.5673076923076925,
      "grad_norm": 0.28125,
      "learning_rate": 0.00013198498741214166,
      "loss": 0.9028,
      "step": 475
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 0.271484375,
      "learning_rate": 0.0001303905157574247,
      "loss": 0.9059,
      "step": 480
    },
    {
      "epoch": 4.663461538461538,
      "grad_norm": 0.265625,
      "learning_rate": 0.00012878748524247462,
      "loss": 0.9004,
      "step": 485
    },
    {
      "epoch": 4.711538461538462,
      "grad_norm": 0.333984375,
      "learning_rate": 0.00012717634732768243,
      "loss": 0.905,
      "step": 490
    },
    {
      "epoch": 4.759615384615385,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0001255575557567207,
      "loss": 0.9035,
      "step": 495
    },
    {
      "epoch": 4.8076923076923075,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001239315664287558,
      "loss": 0.8974,
      "step": 500
    },
    {
      "epoch": 4.855769230769231,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00012229883727005365,
      "loss": 0.9034,
      "step": 505
    },
    {
      "epoch": 4.903846153846154,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00012065982810501404,
      "loss": 0.9056,
      "step": 510
    },
    {
      "epoch": 4.951923076923077,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00011901500052667068,
      "loss": 0.902,
      "step": 515
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.9016,
      "step": 520
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.4989540576934814,
      "eval_runtime": 0.4791,
      "eval_samples_per_second": 20.875,
      "eval_steps_per_second": 2.087,
      "step": 520
    },
    {
      "epoch": 5.048076923076923,
      "grad_norm": 0.25,
      "learning_rate": 0.00011570974456492678,
      "loss": 0.8816,
      "step": 525
    },
    {
      "epoch": 5.096153846153846,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00011405024703850929,
      "loss": 0.8777,
      "step": 530
    },
    {
      "epoch": 5.144230769230769,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00011238679255059752,
      "loss": 0.8809,
      "step": 535
    },
    {
      "epoch": 5.1923076923076925,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00011071984957874479,
      "loss": 0.882,
      "step": 540
    },
    {
      "epoch": 5.240384615384615,
      "grad_norm": 0.236328125,
      "learning_rate": 0.0001090498875829638,
      "loss": 0.8787,
      "step": 545
    },
    {
      "epoch": 5.288461538461538,
      "grad_norm": 0.2333984375,
      "learning_rate": 0.00010737737687351284,
      "loss": 0.8806,
      "step": 550
    },
    {
      "epoch": 5.336538461538462,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.00010570278847844275,
      "loss": 0.8859,
      "step": 555
    },
    {
      "epoch": 5.384615384615385,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.8832,
      "step": 560
    },
    {
      "epoch": 5.4326923076923075,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00010234926553651422,
      "loss": 0.8803,
      "step": 565
    },
    {
      "epoch": 5.480769230769231,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00010067127544003563,
      "loss": 0.882,
      "step": 570
    },
    {
      "epoch": 5.528846153846154,
      "grad_norm": 0.2275390625,
      "learning_rate": 9.899309629271246e-05,
      "loss": 0.8797,
      "step": 575
    },
    {
      "epoch": 5.576923076923077,
      "grad_norm": 0.2734375,
      "learning_rate": 9.73152007189939e-05,
      "loss": 0.8818,
      "step": 580
    },
    {
      "epoch": 5.625,
      "grad_norm": 0.3828125,
      "learning_rate": 9.563806126346642e-05,
      "loss": 0.8864,
      "step": 585
    },
    {
      "epoch": 5.673076923076923,
      "grad_norm": 0.2451171875,
      "learning_rate": 9.396215025777139e-05,
      "loss": 0.8876,
      "step": 590
    },
    {
      "epoch": 5.721153846153846,
      "grad_norm": 0.279296875,
      "learning_rate": 9.22879396875828e-05,
      "loss": 0.8843,
      "step": 595
    },
    {
      "epoch": 5.769230769230769,
      "grad_norm": 0.294921875,
      "learning_rate": 9.061590105968208e-05,
      "loss": 0.8832,
      "step": 600
    },
    {
      "epoch": 5.8173076923076925,
      "grad_norm": 0.359375,
      "learning_rate": 8.894650526916803e-05,
      "loss": 0.884,
      "step": 605
    },
    {
      "epoch": 5.865384615384615,
      "grad_norm": 0.388671875,
      "learning_rate": 8.728022246683894e-05,
      "loss": 0.8814,
      "step": 610
    },
    {
      "epoch": 5.913461538461538,
      "grad_norm": 0.33203125,
      "learning_rate": 8.561752192678443e-05,
      "loss": 0.8826,
      "step": 615
    },
    {
      "epoch": 5.961538461538462,
      "grad_norm": 0.328125,
      "learning_rate": 8.395887191422397e-05,
      "loss": 0.8871,
      "step": 620
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.5249791145324707,
      "eval_runtime": 0.4816,
      "eval_samples_per_second": 20.766,
      "eval_steps_per_second": 2.077,
      "step": 624
    },
    {
      "epoch": 6.009615384615385,
      "grad_norm": 0.234375,
      "learning_rate": 8.23047395536298e-05,
      "loss": 0.8778,
      "step": 625
    },
    {
      "epoch": 6.0576923076923075,
      "grad_norm": 0.2373046875,
      "learning_rate": 8.065559069717088e-05,
      "loss": 0.8638,
      "step": 630
    },
    {
      "epoch": 6.105769230769231,
      "grad_norm": 0.248046875,
      "learning_rate": 7.901188979351526e-05,
      "loss": 0.8612,
      "step": 635
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.2431640625,
      "learning_rate": 7.73740997570278e-05,
      "loss": 0.8638,
      "step": 640
    },
    {
      "epoch": 6.201923076923077,
      "grad_norm": 0.224609375,
      "learning_rate": 7.574268183739989e-05,
      "loss": 0.866,
      "step": 645
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.236328125,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.8673,
      "step": 650
    },
    {
      "epoch": 6.298076923076923,
      "grad_norm": 0.263671875,
      "learning_rate": 7.250079824521743e-05,
      "loss": 0.87,
      "step": 655
    },
    {
      "epoch": 6.346153846153846,
      "grad_norm": 0.30859375,
      "learning_rate": 7.089124558212871e-05,
      "loss": 0.8634,
      "step": 660
    },
    {
      "epoch": 6.394230769230769,
      "grad_norm": 0.23828125,
      "learning_rate": 6.928989079770094e-05,
      "loss": 0.8688,
      "step": 665
    },
    {
      "epoch": 6.4423076923076925,
      "grad_norm": 0.234375,
      "learning_rate": 6.769718488039023e-05,
      "loss": 0.864,
      "step": 670
    },
    {
      "epoch": 6.490384615384615,
      "grad_norm": 0.236328125,
      "learning_rate": 6.611357638287823e-05,
      "loss": 0.8698,
      "step": 675
    },
    {
      "epoch": 6.538461538461538,
      "grad_norm": 0.2431640625,
      "learning_rate": 6.453951129574644e-05,
      "loss": 0.865,
      "step": 680
    },
    {
      "epoch": 6.586538461538462,
      "grad_norm": 0.23046875,
      "learning_rate": 6.297543292187215e-05,
      "loss": 0.874,
      "step": 685
    },
    {
      "epoch": 6.634615384615385,
      "grad_norm": 0.2294921875,
      "learning_rate": 6.142178175158149e-05,
      "loss": 0.8694,
      "step": 690
    },
    {
      "epoch": 6.6826923076923075,
      "grad_norm": 0.2421875,
      "learning_rate": 5.9878995338594224e-05,
      "loss": 0.8688,
      "step": 695
    },
    {
      "epoch": 6.730769230769231,
      "grad_norm": 0.23046875,
      "learning_rate": 5.834750817679606e-05,
      "loss": 0.8671,
      "step": 700
    },
    {
      "epoch": 6.778846153846154,
      "grad_norm": 0.240234375,
      "learning_rate": 5.682775157787213e-05,
      "loss": 0.8666,
      "step": 705
    },
    {
      "epoch": 6.826923076923077,
      "grad_norm": 0.2158203125,
      "learning_rate": 5.5320153549837415e-05,
      "loss": 0.8623,
      "step": 710
    },
    {
      "epoch": 6.875,
      "grad_norm": 0.21484375,
      "learning_rate": 5.382513867649663e-05,
      "loss": 0.8677,
      "step": 715
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 0.2138671875,
      "learning_rate": 5.234312799786921e-05,
      "loss": 0.8654,
      "step": 720
    },
    {
      "epoch": 6.971153846153846,
      "grad_norm": 0.208984375,
      "learning_rate": 5.087453889161229e-05,
      "loss": 0.8635,
      "step": 725
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.5363287925720215,
      "eval_runtime": 0.4813,
      "eval_samples_per_second": 20.776,
      "eval_steps_per_second": 2.078,
      "step": 728
    },
    {
      "epoch": 7.019230769230769,
      "grad_norm": 0.2373046875,
      "learning_rate": 4.9419784955474524e-05,
      "loss": 0.8611,
      "step": 730
    },
    {
      "epoch": 7.0673076923076925,
      "grad_norm": 0.2333984375,
      "learning_rate": 4.797927589081509e-05,
      "loss": 0.8528,
      "step": 735
    },
    {
      "epoch": 7.115384615384615,
      "grad_norm": 0.24609375,
      "learning_rate": 4.6553417387219886e-05,
      "loss": 0.858,
      "step": 740
    },
    {
      "epoch": 7.163461538461538,
      "grad_norm": 0.240234375,
      "learning_rate": 4.514261100824709e-05,
      "loss": 0.8525,
      "step": 745
    },
    {
      "epoch": 7.211538461538462,
      "grad_norm": 0.2373046875,
      "learning_rate": 4.374725407833532e-05,
      "loss": 0.8593,
      "step": 750
    },
    {
      "epoch": 7.259615384615385,
      "grad_norm": 0.244140625,
      "learning_rate": 4.236773957090548e-05,
      "loss": 0.8563,
      "step": 755
    },
    {
      "epoch": 7.3076923076923075,
      "grad_norm": 0.259765625,
      "learning_rate": 4.100445599768774e-05,
      "loss": 0.8562,
      "step": 760
    },
    {
      "epoch": 7.355769230769231,
      "grad_norm": 0.2177734375,
      "learning_rate": 3.96577872993053e-05,
      "loss": 0.8574,
      "step": 765
    },
    {
      "epoch": 7.403846153846154,
      "grad_norm": 0.224609375,
      "learning_rate": 3.832811273714569e-05,
      "loss": 0.85,
      "step": 770
    },
    {
      "epoch": 7.451923076923077,
      "grad_norm": 0.2158203125,
      "learning_rate": 3.701580678654925e-05,
      "loss": 0.8537,
      "step": 775
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.25390625,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.8579,
      "step": 780
    },
    {
      "epoch": 7.548076923076923,
      "grad_norm": 0.2099609375,
      "learning_rate": 3.4444774059770536e-05,
      "loss": 0.8567,
      "step": 785
    },
    {
      "epoch": 7.596153846153846,
      "grad_norm": 0.2177734375,
      "learning_rate": 3.318677136178228e-05,
      "loss": 0.8515,
      "step": 790
    },
    {
      "epoch": 7.644230769230769,
      "grad_norm": 0.224609375,
      "learning_rate": 3.1947585227823394e-05,
      "loss": 0.8519,
      "step": 795
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 0.2216796875,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.8611,
      "step": 800
    },
    {
      "epoch": 7.740384615384615,
      "grad_norm": 0.21484375,
      "learning_rate": 2.9527053218996037e-05,
      "loss": 0.855,
      "step": 805
    },
    {
      "epoch": 7.788461538461538,
      "grad_norm": 0.220703125,
      "learning_rate": 2.8346389036906828e-05,
      "loss": 0.8529,
      "step": 810
    },
    {
      "epoch": 7.836538461538462,
      "grad_norm": 0.21484375,
      "learning_rate": 2.7185904612421176e-05,
      "loss": 0.8506,
      "step": 815
    },
    {
      "epoch": 7.884615384615385,
      "grad_norm": 0.2236328125,
      "learning_rate": 2.6045926771976303e-05,
      "loss": 0.8563,
      "step": 820
    },
    {
      "epoch": 7.9326923076923075,
      "grad_norm": 0.2109375,
      "learning_rate": 2.492677656675414e-05,
      "loss": 0.861,
      "step": 825
    },
    {
      "epoch": 7.980769230769231,
      "grad_norm": 0.2177734375,
      "learning_rate": 2.382876918226409e-05,
      "loss": 0.8535,
      "step": 830
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.5545527935028076,
      "eval_runtime": 0.4771,
      "eval_samples_per_second": 20.959,
      "eval_steps_per_second": 2.096,
      "step": 832
    },
    {
      "epoch": 8.028846153846153,
      "grad_norm": 0.2158203125,
      "learning_rate": 2.2752213849577188e-05,
      "loss": 0.8505,
      "step": 835
    },
    {
      "epoch": 8.076923076923077,
      "grad_norm": 0.2177734375,
      "learning_rate": 2.1697413758237784e-05,
      "loss": 0.8473,
      "step": 840
    },
    {
      "epoch": 8.125,
      "grad_norm": 0.220703125,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.8438,
      "step": 845
    },
    {
      "epoch": 8.173076923076923,
      "grad_norm": 0.212890625,
      "learning_rate": 1.965426133954854e-05,
      "loss": 0.8551,
      "step": 850
    },
    {
      "epoch": 8.221153846153847,
      "grad_norm": 0.2119140625,
      "learning_rate": 1.8666484423821373e-05,
      "loss": 0.8528,
      "step": 855
    },
    {
      "epoch": 8.26923076923077,
      "grad_norm": 0.2236328125,
      "learning_rate": 1.7701613410634365e-05,
      "loss": 0.848,
      "step": 860
    },
    {
      "epoch": 8.317307692307692,
      "grad_norm": 0.216796875,
      "learning_rate": 1.6759920035953093e-05,
      "loss": 0.8475,
      "step": 865
    },
    {
      "epoch": 8.365384615384615,
      "grad_norm": 0.208984375,
      "learning_rate": 1.584166950824061e-05,
      "loss": 0.8535,
      "step": 870
    },
    {
      "epoch": 8.413461538461538,
      "grad_norm": 0.2119140625,
      "learning_rate": 1.4947120433767047e-05,
      "loss": 0.8508,
      "step": 875
    },
    {
      "epoch": 8.461538461538462,
      "grad_norm": 0.212890625,
      "learning_rate": 1.4076524743778319e-05,
      "loss": 0.8459,
      "step": 880
    },
    {
      "epoch": 8.509615384615385,
      "grad_norm": 0.21484375,
      "learning_rate": 1.3230127623545064e-05,
      "loss": 0.8481,
      "step": 885
    },
    {
      "epoch": 8.557692307692308,
      "grad_norm": 0.2109375,
      "learning_rate": 1.2408167443311214e-05,
      "loss": 0.8508,
      "step": 890
    },
    {
      "epoch": 8.60576923076923,
      "grad_norm": 0.212890625,
      "learning_rate": 1.1610875691161915e-05,
      "loss": 0.8489,
      "step": 895
    },
    {
      "epoch": 8.653846153846153,
      "grad_norm": 0.2060546875,
      "learning_rate": 1.083847690782972e-05,
      "loss": 0.8423,
      "step": 900
    },
    {
      "epoch": 8.701923076923077,
      "grad_norm": 0.22265625,
      "learning_rate": 1.0091188623457415e-05,
      "loss": 0.8562,
      "step": 905
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.2138671875,
      "learning_rate": 9.369221296335006e-06,
      "loss": 0.8515,
      "step": 910
    },
    {
      "epoch": 8.798076923076923,
      "grad_norm": 0.2138671875,
      "learning_rate": 8.672778253628621e-06,
      "loss": 0.8497,
      "step": 915
    },
    {
      "epoch": 8.846153846153847,
      "grad_norm": 0.208984375,
      "learning_rate": 8.002055634117578e-06,
      "loss": 0.8469,
      "step": 920
    },
    {
      "epoch": 8.89423076923077,
      "grad_norm": 0.208984375,
      "learning_rate": 7.357242332955916e-06,
      "loss": 0.8509,
      "step": 925
    },
    {
      "epoch": 8.942307692307692,
      "grad_norm": 0.208984375,
      "learning_rate": 6.738519948473976e-06,
      "loss": 0.8545,
      "step": 930
    },
    {
      "epoch": 8.990384615384615,
      "grad_norm": 0.205078125,
      "learning_rate": 6.146062731035129e-06,
      "loss": 0.845,
      "step": 935
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.5566022396087646,
      "eval_runtime": 0.4819,
      "eval_samples_per_second": 20.752,
      "eval_steps_per_second": 2.075,
      "step": 936
    },
    {
      "epoch": 9.038461538461538,
      "grad_norm": 0.2138671875,
      "learning_rate": 5.580037533961546e-06,
      "loss": 0.8439,
      "step": 940
    },
    {
      "epoch": 9.086538461538462,
      "grad_norm": 0.2060546875,
      "learning_rate": 5.040603766543594e-06,
      "loss": 0.8496,
      "step": 945
    },
    {
      "epoch": 9.134615384615385,
      "grad_norm": 0.208984375,
      "learning_rate": 4.527913349145441e-06,
      "loss": 0.8483,
      "step": 950
    },
    {
      "epoch": 9.182692307692308,
      "grad_norm": 0.2060546875,
      "learning_rate": 4.042110670419763e-06,
      "loss": 0.8508,
      "step": 955
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 0.205078125,
      "learning_rate": 3.5833325466437694e-06,
      "loss": 0.8508,
      "step": 960
    },
    {
      "epoch": 9.278846153846153,
      "grad_norm": 0.2021484375,
      "learning_rate": 3.1517081831876737e-06,
      "loss": 0.8437,
      "step": 965
    },
    {
      "epoch": 9.326923076923077,
      "grad_norm": 0.212890625,
      "learning_rate": 2.7473591381266708e-06,
      "loss": 0.845,
      "step": 970
    },
    {
      "epoch": 9.375,
      "grad_norm": 0.2060546875,
      "learning_rate": 2.3703992880066638e-06,
      "loss": 0.8428,
      "step": 975
    },
    {
      "epoch": 9.423076923076923,
      "grad_norm": 0.20703125,
      "learning_rate": 2.0209347957732328e-06,
      "loss": 0.8495,
      "step": 980
    },
    {
      "epoch": 9.471153846153847,
      "grad_norm": 0.2138671875,
      "learning_rate": 1.6990640808730696e-06,
      "loss": 0.846,
      "step": 985
    },
    {
      "epoch": 9.51923076923077,
      "grad_norm": 0.2109375,
      "learning_rate": 1.404877791536141e-06,
      "loss": 0.8475,
      "step": 990
    },
    {
      "epoch": 9.567307692307692,
      "grad_norm": 0.203125,
      "learning_rate": 1.1384587792465872e-06,
      "loss": 0.8478,
      "step": 995
    },
    {
      "epoch": 9.615384615384615,
      "grad_norm": 0.21875,
      "learning_rate": 8.998820754091531e-07,
      "loss": 0.844,
      "step": 1000
    },
    {
      "epoch": 9.663461538461538,
      "grad_norm": 0.2060546875,
      "learning_rate": 6.892148702183133e-07,
      "loss": 0.8478,
      "step": 1005
    },
    {
      "epoch": 9.711538461538462,
      "grad_norm": 0.2060546875,
      "learning_rate": 5.065164937354428e-07,
      "loss": 0.8459,
      "step": 1010
    },
    {
      "epoch": 9.759615384615385,
      "grad_norm": 0.2041015625,
      "learning_rate": 3.5183839917972697e-07,
      "loss": 0.8475,
      "step": 1015
    },
    {
      "epoch": 9.807692307692308,
      "grad_norm": 0.2216796875,
      "learning_rate": 2.2522414843748618e-07,
      "loss": 0.8533,
      "step": 1020
    },
    {
      "epoch": 9.85576923076923,
      "grad_norm": 0.205078125,
      "learning_rate": 1.2670939979384512e-07,
      "loss": 0.8547,
      "step": 1025
    },
    {
      "epoch": 9.903846153846153,
      "grad_norm": 0.2080078125,
      "learning_rate": 5.632189789027687e-08,
      "loss": 0.8463,
      "step": 1030
    },
    {
      "epoch": 9.951923076923077,
      "grad_norm": 0.2060546875,
      "learning_rate": 1.4081465910975588e-08,
      "loss": 0.8418,
      "step": 1035
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.2080078125,
      "learning_rate": 0.0,
      "loss": 0.853,
      "step": 1040
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.5572547912597656,
      "eval_runtime": 0.4824,
      "eval_samples_per_second": 20.728,
      "eval_steps_per_second": 2.073,
      "step": 1040
    },
    {
      "epoch": 10.0,
      "step": 1040,
      "total_flos": 1.6530423313701274e+18,
      "train_loss": 0.977329820394516,
      "train_runtime": 7126.3412,
      "train_samples_per_second": 18.665,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 5,
  "max_steps": 1040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6530423313701274e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}