{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 548.0,
      "learning_rate": 1.818181818181818e-06,
      "loss": 53.7965,
      "step": 1
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 668.0,
      "learning_rate": 9.090909090909091e-06,
      "loss": 55.3182,
      "step": 5
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 486.0,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 51.173,
      "step": 10
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 159.0,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 33.7467,
      "step": 15
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 37.5,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 24.0423,
      "step": 20
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 32.25,
      "learning_rate": 4.545454545454546e-05,
      "loss": 22.1424,
      "step": 25
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 21.25,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 20.3818,
      "step": 30
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 7.90625,
      "learning_rate": 6.363636363636364e-05,
      "loss": 18.8064,
      "step": 35
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 11.625,
      "learning_rate": 7.272727272727273e-05,
      "loss": 17.8515,
      "step": 40
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 27.125,
      "learning_rate": 8.181818181818183e-05,
      "loss": 16.8604,
      "step": 45
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 56.25,
      "learning_rate": 9.090909090909092e-05,
      "loss": 12.4796,
      "step": 50
    },
    {
      "epoch": 0.5,
      "grad_norm": 11.4375,
      "learning_rate": 0.0001,
      "loss": 4.4979,
      "step": 55
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 3.25,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.9919,
      "step": 60
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 25.375,
      "learning_rate": 0.0001181818181818182,
      "loss": 1.6619,
      "step": 65
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 3.125,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.527,
      "step": 70
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 9.6875,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.3688,
      "step": 75
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 8.0625,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.2618,
      "step": 80
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 6.9375,
      "learning_rate": 0.00015454545454545454,
      "loss": 1.238,
      "step": 85
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 3.15625,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1871,
      "step": 90
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 4.34375,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.154,
      "step": 95
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.65625,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1375,
      "step": 100
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 3.296875,
      "learning_rate": 0.00019090909090909092,
      "loss": 1.0352,
      "step": 105
    },
    {
      "epoch": 1.0,
      "grad_norm": 9.25,
      "learning_rate": 0.0002,
      "loss": 1.0256,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.388709783554077,
      "eval_runtime": 1.0069,
      "eval_samples_per_second": 4.966,
      "eval_steps_per_second": 1.986,
      "step": 110
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 1.53125,
      "learning_rate": 0.00019998741276738754,
      "loss": 1.0186,
      "step": 115
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 2.5625,
      "learning_rate": 0.00019994965423831854,
      "loss": 0.9466,
      "step": 120
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 7.21875,
      "learning_rate": 0.0001998867339183008,
      "loss": 0.9645,
      "step": 125
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 86.5,
      "learning_rate": 0.00019979866764718843,
      "loss": 0.9547,
      "step": 130
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019968547759519425,
      "loss": 0.9527,
      "step": 135
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019954719225730847,
      "loss": 0.9091,
      "step": 140
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 1.703125,
      "learning_rate": 0.00019938384644612543,
      "loss": 0.8789,
      "step": 145
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 2.40625,
      "learning_rate": 0.00019919548128307954,
      "loss": 0.9036,
      "step": 150
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 5.09375,
      "learning_rate": 0.0001989821441880933,
      "loss": 0.8787,
      "step": 155
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00019874388886763944,
      "loss": 0.8671,
      "step": 160
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.046875,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.8872,
      "step": 165
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 4.0625,
      "learning_rate": 0.00019819286972627066,
      "loss": 0.9179,
      "step": 170
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 3.25,
      "learning_rate": 0.00019788024462147788,
      "loss": 0.8857,
      "step": 175
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00019754297868854073,
      "loss": 0.8474,
      "step": 180
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 3.03125,
      "learning_rate": 0.00019718115683235417,
      "loss": 0.861,
      "step": 185
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 3.515625,
      "learning_rate": 0.00019679487013963564,
      "loss": 0.8266,
      "step": 190
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00019638421585599423,
      "loss": 0.8515,
      "step": 195
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 2.015625,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.8328,
      "step": 200
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 1.7578125,
      "learning_rate": 0.0001954902241444074,
      "loss": 0.8601,
      "step": 205
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 1.65625,
      "learning_rate": 0.00019500711177409454,
      "loss": 0.8435,
      "step": 210
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 2.421875,
      "learning_rate": 0.00019450008187146684,
      "loss": 0.8082,
      "step": 215
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.75390625,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.8325,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.227036952972412,
      "eval_runtime": 1.0053,
      "eval_samples_per_second": 4.974,
      "eval_steps_per_second": 1.989,
      "step": 220
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.70703125,
      "learning_rate": 0.00019341478602651069,
      "loss": 0.7413,
      "step": 225
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 3.796875,
      "learning_rate": 0.00019283679330160726,
      "loss": 0.7526,
      "step": 230
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00019223542941045817,
      "loss": 0.739,
      "step": 235
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.09375,
      "learning_rate": 0.00019161084574320696,
      "loss": 0.7665,
      "step": 240
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.859375,
      "learning_rate": 0.00019096319953545185,
      "loss": 0.7655,
      "step": 245
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 2.53125,
      "learning_rate": 0.00019029265382866214,
      "loss": 0.753,
      "step": 250
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018959937742913359,
      "loss": 0.7557,
      "step": 255
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00018888354486549237,
      "loss": 0.7805,
      "step": 260
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 4.75,
      "learning_rate": 0.00018814533634475822,
      "loss": 0.7451,
      "step": 265
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 1.109375,
      "learning_rate": 0.00018738493770697852,
      "loss": 0.7308,
      "step": 270
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8117,
      "step": 275
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.515625,
      "learning_rate": 0.00018579834132349772,
      "loss": 0.7756,
      "step": 280
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00018497254299495146,
      "loss": 0.7503,
      "step": 285
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 1.25,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.7886,
      "step": 290
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00018325698546347715,
      "loss": 0.7452,
      "step": 295
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 4.0,
      "learning_rate": 0.0001823676581429833,
      "loss": 0.7579,
      "step": 300
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 1.59375,
      "learning_rate": 0.00018145759520503358,
      "loss": 0.7494,
      "step": 305
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 1.6953125,
      "learning_rate": 0.00018052702575310588,
      "loss": 0.7343,
      "step": 310
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 3.28125,
      "learning_rate": 0.00017957618405308324,
      "loss": 0.7402,
      "step": 315
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00017860530947427875,
      "loss": 0.7428,
      "step": 320
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.828125,
      "learning_rate": 0.0001776146464291757,
      "loss": 0.7699,
      "step": 325
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.21875,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.749,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.2333221435546875,
      "eval_runtime": 1.0046,
      "eval_samples_per_second": 4.977,
      "eval_steps_per_second": 1.991,
      "step": 330
    },
    {
      "epoch": 3.0454545454545454,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00017557495743542585,
      "loss": 0.6475,
      "step": 335
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.63671875,
      "learning_rate": 0.0001745264449675755,
      "loss": 0.6833,
      "step": 340
    },
    {
      "epoch": 3.1363636363636362,
      "grad_norm": 0.671875,
      "learning_rate": 0.00017345917086575332,
      "loss": 0.6776,
      "step": 345
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.921875,
      "learning_rate": 0.00017237340381050703,
      "loss": 0.6798,
      "step": 350
    },
    {
      "epoch": 3.227272727272727,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00017126941713788632,
      "loss": 0.6606,
      "step": 355
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 1.203125,
      "learning_rate": 0.00017014748877063214,
      "loss": 0.6629,
      "step": 360
    },
    {
      "epoch": 3.3181818181818183,
      "grad_norm": 0.9375,
      "learning_rate": 0.00016900790114821122,
      "loss": 0.6871,
      "step": 365
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 0.578125,
      "learning_rate": 0.00016785094115571322,
      "loss": 0.6575,
      "step": 370
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00016667690005162916,
      "loss": 0.6674,
      "step": 375
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.7054,
      "step": 380
    },
    {
      "epoch": 3.5,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.6646,
      "step": 385
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 1.453125,
      "learning_rate": 0.00016305526670845226,
      "loss": 0.6766,
      "step": 390
    },
    {
      "epoch": 3.590909090909091,
      "grad_norm": 1.5703125,
      "learning_rate": 0.00016181589862206052,
      "loss": 0.6716,
      "step": 395
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00016056096871376667,
      "loss": 0.6976,
      "step": 400
    },
    {
      "epoch": 3.6818181818181817,
      "grad_norm": 1.734375,
      "learning_rate": 0.00015929079290546408,
      "loss": 0.6624,
      "step": 405
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.83984375,
      "learning_rate": 0.00015800569095711982,
      "loss": 0.6907,
      "step": 410
    },
    {
      "epoch": 3.7727272727272725,
      "grad_norm": 1.078125,
      "learning_rate": 0.00015670598638627706,
      "loss": 0.6664,
      "step": 415
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00015539200638661104,
      "loss": 0.6642,
      "step": 420
    },
    {
      "epoch": 3.8636363636363638,
      "grad_norm": 3.203125,
      "learning_rate": 0.00015406408174555976,
      "loss": 0.7091,
      "step": 425
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00015272254676105025,
      "loss": 0.7034,
      "step": 430
    },
    {
      "epoch": 3.9545454545454546,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00015136773915734066,
      "loss": 0.6679,
      "step": 435
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.140625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6755,
      "step": 440
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.29927659034729,
      "eval_runtime": 1.0067,
      "eval_samples_per_second": 4.967,
      "eval_steps_per_second": 1.987,
      "step": 440
    },
    {
      "epoch": 4.045454545454546,
      "grad_norm": 2.75,
      "learning_rate": 0.00014861967361004687,
      "loss": 0.6121,
      "step": 445
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.625,
      "learning_rate": 0.0001472271074772683,
      "loss": 0.598,
      "step": 450
    },
    {
      "epoch": 4.136363636363637,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00014582265217274104,
      "loss": 0.5832,
      "step": 455
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00014440666126057744,
      "loss": 0.591,
      "step": 460
    },
    {
      "epoch": 4.2272727272727275,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00014297949120891718,
      "loss": 0.5767,
      "step": 465
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 0.69140625,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.5742,
      "step": 470
    },
    {
      "epoch": 4.318181818181818,
      "grad_norm": 0.6328125,
      "learning_rate": 0.00014009305354066137,
      "loss": 0.5806,
      "step": 475
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.7109375,
      "learning_rate": 0.00013863451256931287,
      "loss": 0.605,
      "step": 480
    },
    {
      "epoch": 4.409090909090909,
      "grad_norm": 0.6796875,
      "learning_rate": 0.00013716624556603274,
      "loss": 0.6142,
      "step": 485
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00013568862215918717,
      "loss": 0.586,
      "step": 490
    },
    {
      "epoch": 4.5,
      "grad_norm": 1.34375,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.6088,
      "step": 495
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00013270679633174218,
      "loss": 0.5974,
      "step": 500
    },
    {
      "epoch": 4.590909090909091,
      "grad_norm": 1.171875,
      "learning_rate": 0.0001312033445698487,
      "loss": 0.5808,
      "step": 505
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 1.515625,
      "learning_rate": 0.0001296920375328275,
      "loss": 0.6008,
      "step": 510
    },
    {
      "epoch": 4.681818181818182,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00012817325568414297,
      "loss": 0.6069,
      "step": 515
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.6484375,
      "learning_rate": 0.00012664738136900348,
      "loss": 0.6111,
      "step": 520
    },
    {
      "epoch": 4.7727272727272725,
      "grad_norm": 0.640625,
      "learning_rate": 0.0001251147987181079,
      "loss": 0.6114,
      "step": 525
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 0.6015625,
      "learning_rate": 0.00012357589355094275,
      "loss": 0.5905,
      "step": 530
    },
    {
      "epoch": 4.863636363636363,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00012203105327865407,
      "loss": 0.6153,
      "step": 535
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.73828125,
      "learning_rate": 0.00012048066680651908,
      "loss": 0.6179,
      "step": 540
    },
    {
      "epoch": 4.954545454545455,
      "grad_norm": 0.62890625,
      "learning_rate": 0.00011892512443604102,
      "loss": 0.5833,
      "step": 545
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.6197,
      "step": 550
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.3820290565490723,
      "eval_runtime": 1.0056,
      "eval_samples_per_second": 4.972,
      "eval_steps_per_second": 1.989,
      "step": 550
    },
    {
      "epoch": 5.045454545454546,
      "grad_norm": 0.71484375,
      "learning_rate": 0.000115800139597335,
      "loss": 0.5034,
      "step": 555
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.66796875,
      "learning_rate": 0.00011423148382732853,
      "loss": 0.5171,
      "step": 560
    },
    {
      "epoch": 5.136363636363637,
      "grad_norm": 0.6875,
      "learning_rate": 0.00011265924535737493,
      "loss": 0.5233,
      "step": 565
    },
    {
      "epoch": 5.181818181818182,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00011108381999010111,
      "loss": 0.5103,
      "step": 570
    },
    {
      "epoch": 5.2272727272727275,
      "grad_norm": 0.63671875,
      "learning_rate": 0.00010950560433041826,
      "loss": 0.5371,
      "step": 575
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00010792499568567884,
      "loss": 0.5228,
      "step": 580
    },
    {
      "epoch": 5.318181818181818,
      "grad_norm": 0.7734375,
      "learning_rate": 0.00010634239196565646,
      "loss": 0.5308,
      "step": 585
    },
    {
      "epoch": 5.363636363636363,
      "grad_norm": 0.6015625,
      "learning_rate": 0.00010475819158237425,
      "loss": 0.5349,
      "step": 590
    },
    {
      "epoch": 5.409090909090909,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00010317279334980678,
      "loss": 0.5204,
      "step": 595
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.70703125,
      "learning_rate": 0.00010158659638348081,
      "loss": 0.5182,
      "step": 600
    },
    {
      "epoch": 5.5,
      "grad_norm": 0.58984375,
      "learning_rate": 0.0001,
      "loss": 0.5215,
      "step": 605
    },
    {
      "epoch": 5.545454545454545,
      "grad_norm": 0.6484375,
      "learning_rate": 9.84134036165192e-05,
      "loss": 0.5282,
      "step": 610
    },
    {
      "epoch": 5.590909090909091,
      "grad_norm": 0.6015625,
      "learning_rate": 9.682720665019325e-05,
      "loss": 0.5103,
      "step": 615
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.63671875,
      "learning_rate": 9.524180841762577e-05,
      "loss": 0.5257,
      "step": 620
    },
    {
      "epoch": 5.681818181818182,
      "grad_norm": 0.6640625,
      "learning_rate": 9.365760803434355e-05,
      "loss": 0.5228,
      "step": 625
    },
    {
      "epoch": 5.7272727272727275,
      "grad_norm": 0.60546875,
      "learning_rate": 9.207500431432115e-05,
      "loss": 0.5487,
      "step": 630
    },
    {
      "epoch": 5.7727272727272725,
      "grad_norm": 0.7734375,
      "learning_rate": 9.049439566958175e-05,
      "loss": 0.528,
      "step": 635
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.79296875,
      "learning_rate": 8.891618000989891e-05,
      "loss": 0.5213,
      "step": 640
    },
    {
      "epoch": 5.863636363636363,
      "grad_norm": 0.640625,
      "learning_rate": 8.734075464262507e-05,
      "loss": 0.5312,
      "step": 645
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.62890625,
      "learning_rate": 8.57685161726715e-05,
      "loss": 0.5208,
      "step": 650
    },
    {
      "epoch": 5.954545454545455,
      "grad_norm": 0.6953125,
      "learning_rate": 8.4199860402665e-05,
      "loss": 0.5372,
      "step": 655
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.640625,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.5208,
      "step": 660
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.586942672729492,
      "eval_runtime": 1.0065,
      "eval_samples_per_second": 4.968,
      "eval_steps_per_second": 1.987,
      "step": 660
    },
    {
      "epoch": 6.045454545454546,
      "grad_norm": 0.7734375,
      "learning_rate": 8.107487556395901e-05,
      "loss": 0.46,
      "step": 665
    },
    {
      "epoch": 6.090909090909091,
      "grad_norm": 0.703125,
      "learning_rate": 7.951933319348095e-05,
      "loss": 0.4614,
      "step": 670
    },
    {
      "epoch": 6.136363636363637,
      "grad_norm": 0.6640625,
      "learning_rate": 7.796894672134594e-05,
      "loss": 0.4648,
      "step": 675
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.76171875,
      "learning_rate": 7.642410644905726e-05,
      "loss": 0.4445,
      "step": 680
    },
    {
      "epoch": 6.2272727272727275,
      "grad_norm": 0.67578125,
      "learning_rate": 7.488520128189209e-05,
      "loss": 0.4483,
      "step": 685
    },
    {
      "epoch": 6.2727272727272725,
      "grad_norm": 0.6875,
      "learning_rate": 7.335261863099651e-05,
      "loss": 0.4484,
      "step": 690
    },
    {
      "epoch": 6.318181818181818,
      "grad_norm": 0.65234375,
      "learning_rate": 7.182674431585704e-05,
      "loss": 0.4452,
      "step": 695
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.69140625,
      "learning_rate": 7.030796246717255e-05,
      "loss": 0.4615,
      "step": 700
    },
    {
      "epoch": 6.409090909090909,
      "grad_norm": 0.66796875,
      "learning_rate": 6.87966554301513e-05,
      "loss": 0.4443,
      "step": 705
    },
    {
      "epoch": 6.454545454545454,
      "grad_norm": 0.65625,
      "learning_rate": 6.729320366825784e-05,
      "loss": 0.4509,
      "step": 710
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.734375,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.461,
      "step": 715
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.66015625,
      "learning_rate": 6.431137784081282e-05,
      "loss": 0.4571,
      "step": 720
    },
    {
      "epoch": 6.590909090909091,
      "grad_norm": 0.63671875,
      "learning_rate": 6.283375443396726e-05,
      "loss": 0.4698,
      "step": 725
    },
    {
      "epoch": 6.636363636363637,
      "grad_norm": 0.62890625,
      "learning_rate": 6.136548743068713e-05,
      "loss": 0.441,
      "step": 730
    },
    {
      "epoch": 6.681818181818182,
      "grad_norm": 0.65625,
      "learning_rate": 5.9906946459338656e-05,
      "loss": 0.4464,
      "step": 735
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.71875,
      "learning_rate": 5.845849869981137e-05,
      "loss": 0.4455,
      "step": 740
    },
    {
      "epoch": 6.7727272727272725,
      "grad_norm": 0.8359375,
      "learning_rate": 5.702050879108284e-05,
      "loss": 0.4541,
      "step": 745
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.69921875,
      "learning_rate": 5.559333873942259e-05,
      "loss": 0.4546,
      "step": 750
    },
    {
      "epoch": 6.863636363636363,
      "grad_norm": 0.66015625,
      "learning_rate": 5.417734782725896e-05,
      "loss": 0.4427,
      "step": 755
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.703125,
      "learning_rate": 5.277289252273174e-05,
      "loss": 0.4497,
      "step": 760
    },
    {
      "epoch": 6.954545454545455,
      "grad_norm": 0.66796875,
      "learning_rate": 5.138032638995315e-05,
      "loss": 0.4519,
      "step": 765
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.6953125,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4474,
      "step": 770
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.838920831680298,
      "eval_runtime": 1.0059,
      "eval_samples_per_second": 4.971,
      "eval_steps_per_second": 1.988,
      "step": 770
    },
    {
      "epoch": 7.045454545454546,
      "grad_norm": 0.66015625,
      "learning_rate": 4.8632260842659393e-05,
      "loss": 0.3915,
      "step": 775
    },
    {
      "epoch": 7.090909090909091,
      "grad_norm": 0.69140625,
      "learning_rate": 4.727745323894976e-05,
      "loss": 0.3938,
      "step": 780
    },
    {
      "epoch": 7.136363636363637,
      "grad_norm": 0.81640625,
      "learning_rate": 4.593591825444028e-05,
      "loss": 0.3943,
      "step": 785
    },
    {
      "epoch": 7.181818181818182,
      "grad_norm": 0.8515625,
      "learning_rate": 4.4607993613388976e-05,
      "loss": 0.3993,
      "step": 790
    },
    {
      "epoch": 7.2272727272727275,
      "grad_norm": 0.7109375,
      "learning_rate": 4.329401361372294e-05,
      "loss": 0.397,
      "step": 795
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.609375,
      "learning_rate": 4.19943090428802e-05,
      "loss": 0.3952,
      "step": 800
    },
    {
      "epoch": 7.318181818181818,
      "grad_norm": 0.703125,
      "learning_rate": 4.070920709453597e-05,
      "loss": 0.3992,
      "step": 805
    },
    {
      "epoch": 7.363636363636363,
      "grad_norm": 0.6953125,
      "learning_rate": 3.943903128623335e-05,
      "loss": 0.3869,
      "step": 810
    },
    {
      "epoch": 7.409090909090909,
      "grad_norm": 0.65234375,
      "learning_rate": 3.8184101377939476e-05,
      "loss": 0.3931,
      "step": 815
    },
    {
      "epoch": 7.454545454545454,
      "grad_norm": 0.65625,
      "learning_rate": 3.694473329154778e-05,
      "loss": 0.398,
      "step": 820
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.66015625,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.4006,
      "step": 825
    },
    {
      "epoch": 7.545454545454545,
      "grad_norm": 0.6640625,
      "learning_rate": 3.45139266054715e-05,
      "loss": 0.3935,
      "step": 830
    },
    {
      "epoch": 7.590909090909091,
      "grad_norm": 0.74609375,
      "learning_rate": 3.332309994837085e-05,
      "loss": 0.3984,
      "step": 835
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.6953125,
      "learning_rate": 3.21490588442868e-05,
      "loss": 0.3981,
      "step": 840
    },
    {
      "epoch": 7.681818181818182,
      "grad_norm": 0.640625,
      "learning_rate": 3.099209885178882e-05,
      "loss": 0.3981,
      "step": 845
    },
    {
      "epoch": 7.7272727272727275,
      "grad_norm": 0.65234375,
      "learning_rate": 2.9852511229367865e-05,
      "loss": 0.3978,
      "step": 850
    },
    {
      "epoch": 7.7727272727272725,
      "grad_norm": 0.6796875,
      "learning_rate": 2.8730582862113742e-05,
      "loss": 0.3943,
      "step": 855
    },
    {
      "epoch": 7.818181818181818,
      "grad_norm": 0.6484375,
      "learning_rate": 2.7626596189492983e-05,
      "loss": 0.3913,
      "step": 860
    },
    {
      "epoch": 7.863636363636363,
      "grad_norm": 0.73046875,
      "learning_rate": 2.654082913424668e-05,
      "loss": 0.4045,
      "step": 865
    },
    {
      "epoch": 7.909090909090909,
      "grad_norm": 0.6796875,
      "learning_rate": 2.5473555032424533e-05,
      "loss": 0.3828,
      "step": 870
    },
    {
      "epoch": 7.954545454545455,
      "grad_norm": 0.6953125,
      "learning_rate": 2.4425042564574184e-05,
      "loss": 0.388,
      "step": 875
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7734375,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.4044,
      "step": 880
    },
    {
      "epoch": 8.0,
      "eval_loss": 3.102931499481201,
      "eval_runtime": 1.0057,
      "eval_samples_per_second": 4.972,
      "eval_steps_per_second": 1.989,
      "step": 880
    },
    {
      "epoch": 8.045454545454545,
      "grad_norm": 0.59375,
      "learning_rate": 2.2385353570824308e-05,
      "loss": 0.3693,
      "step": 885
    },
    {
      "epoch": 8.090909090909092,
      "grad_norm": 0.65625,
      "learning_rate": 2.139469052572127e-05,
      "loss": 0.3641,
      "step": 890
    },
    {
      "epoch": 8.136363636363637,
      "grad_norm": 0.65234375,
      "learning_rate": 2.042381594691678e-05,
      "loss": 0.3647,
      "step": 895
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.671875,
      "learning_rate": 1.947297424689414e-05,
      "loss": 0.3619,
      "step": 900
    },
    {
      "epoch": 8.227272727272727,
      "grad_norm": 0.64453125,
      "learning_rate": 1.854240479496643e-05,
      "loss": 0.3566,
      "step": 905
    },
    {
      "epoch": 8.272727272727273,
      "grad_norm": 0.6640625,
      "learning_rate": 1.763234185701673e-05,
      "loss": 0.354,
      "step": 910
    },
    {
      "epoch": 8.318181818181818,
      "grad_norm": 0.6953125,
      "learning_rate": 1.6743014536522873e-05,
      "loss": 0.3703,
      "step": 915
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.75,
      "learning_rate": 1.587464671688187e-05,
      "loss": 0.3597,
      "step": 920
    },
    {
      "epoch": 8.409090909090908,
      "grad_norm": 0.6875,
      "learning_rate": 1.5027457005048573e-05,
      "loss": 0.3705,
      "step": 925
    },
    {
      "epoch": 8.454545454545455,
      "grad_norm": 0.70703125,
      "learning_rate": 1.4201658676502294e-05,
      "loss": 0.367,
      "step": 930
    },
    {
      "epoch": 8.5,
      "grad_norm": 0.640625,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.3607,
      "step": 935
    },
    {
      "epoch": 8.545454545454545,
      "grad_norm": 0.6484375,
      "learning_rate": 1.2615062293021507e-05,
      "loss": 0.3633,
      "step": 940
    },
    {
      "epoch": 8.590909090909092,
      "grad_norm": 0.66015625,
      "learning_rate": 1.1854663655241805e-05,
      "loss": 0.3622,
      "step": 945
    },
    {
      "epoch": 8.636363636363637,
      "grad_norm": 0.65625,
      "learning_rate": 1.1116455134507664e-05,
      "loss": 0.3734,
      "step": 950
    },
    {
      "epoch": 8.681818181818182,
      "grad_norm": 0.66015625,
      "learning_rate": 1.0400622570866425e-05,
      "loss": 0.367,
      "step": 955
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.63671875,
      "learning_rate": 9.707346171337894e-06,
      "loss": 0.3578,
      "step": 960
    },
    {
      "epoch": 8.772727272727273,
      "grad_norm": 0.6640625,
      "learning_rate": 9.036800464548157e-06,
      "loss": 0.364,
      "step": 965
    },
    {
      "epoch": 8.818181818181818,
      "grad_norm": 0.61328125,
      "learning_rate": 8.38915425679304e-06,
      "loss": 0.3558,
      "step": 970
    },
    {
      "epoch": 8.863636363636363,
      "grad_norm": 0.65625,
      "learning_rate": 7.764570589541875e-06,
      "loss": 0.3664,
      "step": 975
    },
    {
      "epoch": 8.909090909090908,
      "grad_norm": 0.61328125,
      "learning_rate": 7.163206698392744e-06,
      "loss": 0.3573,
      "step": 980
    },
    {
      "epoch": 8.954545454545455,
      "grad_norm": 0.6484375,
      "learning_rate": 6.585213973489335e-06,
      "loss": 0.3717,
      "step": 985
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.640625,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.3573,
      "step": 990
    },
    {
      "epoch": 9.0,
      "eval_loss": 3.357294797897339,
      "eval_runtime": 1.005,
      "eval_samples_per_second": 4.975,
      "eval_steps_per_second": 1.99,
      "step": 990
    },
    {
      "epoch": 9.045454545454545,
      "grad_norm": 0.58984375,
      "learning_rate": 5.499918128533155e-06,
      "loss": 0.3595,
      "step": 995
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.5859375,
      "learning_rate": 4.992888225905468e-06,
      "loss": 0.359,
      "step": 1000
    },
    {
      "epoch": 9.136363636363637,
      "grad_norm": 0.6328125,
      "learning_rate": 4.509775855592613e-06,
      "loss": 0.3584,
      "step": 1005
    },
    {
      "epoch": 9.181818181818182,
      "grad_norm": 0.6328125,
      "learning_rate": 4.050702638550275e-06,
      "loss": 0.3575,
      "step": 1010
    },
    {
      "epoch": 9.227272727272727,
      "grad_norm": 0.640625,
      "learning_rate": 3.615784144005796e-06,
      "loss": 0.3449,
      "step": 1015
    },
    {
      "epoch": 9.272727272727273,
      "grad_norm": 0.61328125,
      "learning_rate": 3.2051298603643753e-06,
      "loss": 0.354,
      "step": 1020
    },
    {
      "epoch": 9.318181818181818,
      "grad_norm": 0.64453125,
      "learning_rate": 2.818843167645835e-06,
      "loss": 0.3463,
      "step": 1025
    },
    {
      "epoch": 9.363636363636363,
      "grad_norm": 0.65625,
      "learning_rate": 2.4570213114592954e-06,
      "loss": 0.351,
      "step": 1030
    },
    {
      "epoch": 9.409090909090908,
      "grad_norm": 0.6640625,
      "learning_rate": 2.119755378522137e-06,
      "loss": 0.3594,
      "step": 1035
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.60546875,
      "learning_rate": 1.8071302737293295e-06,
      "loss": 0.3541,
      "step": 1040
    },
    {
      "epoch": 9.5,
      "grad_norm": 0.66796875,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.36,
      "step": 1045
    },
    {
      "epoch": 9.545454545454545,
      "grad_norm": 0.609375,
      "learning_rate": 1.2561111323605712e-06,
      "loss": 0.3573,
      "step": 1050
    },
    {
      "epoch": 9.590909090909092,
      "grad_norm": 0.62109375,
      "learning_rate": 1.0178558119067315e-06,
      "loss": 0.3601,
      "step": 1055
    },
    {
      "epoch": 9.636363636363637,
      "grad_norm": 0.6171875,
      "learning_rate": 8.04518716920466e-07,
      "loss": 0.3574,
      "step": 1060
    },
    {
      "epoch": 9.681818181818182,
      "grad_norm": 0.64453125,
      "learning_rate": 6.161535538745878e-07,
      "loss": 0.3664,
      "step": 1065
    },
    {
      "epoch": 9.727272727272727,
      "grad_norm": 0.578125,
      "learning_rate": 4.5280774269154115e-07,
      "loss": 0.3542,
      "step": 1070
    },
    {
      "epoch": 9.772727272727273,
      "grad_norm": 0.62109375,
      "learning_rate": 3.145224048057727e-07,
      "loss": 0.36,
      "step": 1075
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 0.63671875,
      "learning_rate": 2.0133235281156736e-07,
      "loss": 0.3565,
      "step": 1080
    },
    {
      "epoch": 9.863636363636363,
      "grad_norm": 0.62109375,
      "learning_rate": 1.1326608169920372e-07,
      "loss": 0.3694,
      "step": 1085
    },
    {
      "epoch": 9.909090909090908,
      "grad_norm": 0.62109375,
      "learning_rate": 5.0345761681491746e-08,
      "loss": 0.354,
      "step": 1090
    },
    {
      "epoch": 9.954545454545455,
      "grad_norm": 0.59765625,
      "learning_rate": 1.2587232612493172e-08,
      "loss": 0.3516,
      "step": 1095
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.5859375,
      "learning_rate": 0.0,
      "loss": 0.354,
      "step": 1100
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.380370616912842,
      "eval_runtime": 1.0228,
      "eval_samples_per_second": 4.888,
      "eval_steps_per_second": 1.955,
      "step": 1100
    },
    {
      "epoch": 10.0,
      "step": 1100,
      "total_flos": 1.6817604900715233e+18,
      "train_loss": 1.8264882094209844,
      "train_runtime": 8654.8771,
      "train_samples_per_second": 2.032,
      "train_steps_per_second": 0.127
    }
  ],
  "logging_steps": 5,
  "max_steps": 1100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6817604900715233e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}