{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997127262280954,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.322265625,
      "learning_rate": 2.2988505747126437e-06,
      "loss": 1.1344,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.318359375,
      "learning_rate": 1.1494252873563218e-05,
      "loss": 1.1669,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.255859375,
      "learning_rate": 2.2988505747126437e-05,
      "loss": 1.1315,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.2265625,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.0651,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.2080078125,
      "learning_rate": 4.597701149425287e-05,
      "loss": 1.0782,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.1494140625,
      "learning_rate": 5.747126436781609e-05,
      "loss": 1.0631,
      "step": 25
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.142578125,
      "learning_rate": 6.896551724137931e-05,
      "loss": 1.0328,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.13671875,
      "learning_rate": 8.045977011494253e-05,
      "loss": 0.999,
      "step": 35
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1376953125,
      "learning_rate": 9.195402298850575e-05,
      "loss": 1.0058,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1455078125,
      "learning_rate": 0.00010344827586206898,
      "loss": 1.0379,
      "step": 45
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.1435546875,
      "learning_rate": 0.00011494252873563218,
      "loss": 0.9973,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.14453125,
      "learning_rate": 0.0001264367816091954,
      "loss": 0.9921,
      "step": 55
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1376953125,
      "learning_rate": 0.00013793103448275863,
      "loss": 0.973,
      "step": 60
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1376953125,
      "learning_rate": 0.00014942528735632183,
      "loss": 0.9459,
      "step": 65
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.142578125,
      "learning_rate": 0.00016091954022988506,
      "loss": 0.9482,
      "step": 70
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.00017241379310344826,
      "loss": 1.0018,
      "step": 75
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001839080459770115,
      "loss": 0.9946,
      "step": 80
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.13671875,
      "learning_rate": 0.00019540229885057472,
      "loss": 1.0059,
      "step": 85
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00019999275591576766,
      "loss": 1.0132,
      "step": 90
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.130859375,
      "learning_rate": 0.00019994849031285415,
      "loss": 0.9993,
      "step": 95
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.1171875,
      "learning_rate": 0.00019986400139094236,
      "loss": 0.9768,
      "step": 100
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.12060546875,
      "learning_rate": 0.000199739323151795,
      "loss": 0.9577,
      "step": 105
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.00019957450577098322,
      "loss": 0.9614,
      "step": 110
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.130859375,
      "learning_rate": 0.00019936961557769385,
      "loss": 1.0079,
      "step": 115
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.11328125,
      "learning_rate": 0.00019912473502803582,
      "loss": 0.9538,
      "step": 120
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.115234375,
      "learning_rate": 0.0001988399626718565,
      "loss": 0.9984,
      "step": 125
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.125,
      "learning_rate": 0.00019851541311308123,
      "loss": 0.9909,
      "step": 130
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.00019815121696359212,
      "loss": 1.0142,
      "step": 135
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00019774752079066452,
      "loss": 0.9513,
      "step": 140
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.12060546875,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.9907,
      "step": 145
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.00019682229406025635,
      "loss": 0.9987,
      "step": 150
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00019630113585147063,
      "loss": 0.9661,
      "step": 155
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00019574122216678799,
      "loss": 0.9911,
      "step": 160
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.0001951427783381437,
      "loss": 0.9763,
      "step": 165
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0001945060452035629,
      "loss": 0.9727,
      "step": 170
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.1171875,
      "learning_rate": 0.0001938312790102376,
      "loss": 0.9485,
      "step": 175
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.109375,
      "learning_rate": 0.00019311875131140246,
      "loss": 0.987,
      "step": 180
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00019236874885705075,
      "loss": 0.9369,
      "step": 185
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001915815734785346,
      "loss": 0.962,
      "step": 190
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.11328125,
      "learning_rate": 0.00019075754196709572,
      "loss": 1.0007,
      "step": 195
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1083984375,
      "learning_rate": 0.0001898969859463759,
      "loss": 0.9192,
      "step": 200
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.12890625,
      "learning_rate": 0.00018900025173895822,
      "loss": 0.9357,
      "step": 205
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00018806770022699278,
      "loss": 0.9545,
      "step": 210
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00018709970670696308,
      "loss": 0.9533,
      "step": 215
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00018609666073865158,
      "loss": 1.0024,
      "step": 220
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00018505896598836508,
      "loss": 0.986,
      "step": 225
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.00018398704006648302,
      "loss": 0.9542,
      "step": 230
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.115234375,
      "learning_rate": 0.00018288131435939412,
      "loss": 1.0122,
      "step": 235
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.00018174223385588917,
      "loss": 0.9677,
      "step": 240
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.119140625,
      "learning_rate": 0.0001805702569680794,
      "loss": 0.9935,
      "step": 245
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.00017936585534691291,
      "loss": 0.9992,
      "step": 250
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.00017812951369236316,
      "loss": 0.979,
      "step": 255
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00017686172955836633,
      "loss": 0.9367,
      "step": 260
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.00017556301315258517,
      "loss": 0.9548,
      "step": 265
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.115234375,
      "learning_rate": 0.000174233887131081,
      "loss": 1.0021,
      "step": 270
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00017287488638797563,
      "loss": 0.9767,
      "step": 275
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00017148655784018829,
      "loss": 0.9757,
      "step": 280
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00017006946020733425,
      "loss": 0.9611,
      "step": 285
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.9773,
      "step": 290
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00016715125022459922,
      "loss": 0.9613,
      "step": 295
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.00016565131228056133,
      "loss": 0.9993,
      "step": 300
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0001641249535905147,
      "loss": 1.0112,
      "step": 305
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1103515625,
      "learning_rate": 0.00016257278842299197,
      "loss": 0.969,
      "step": 310
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.0001609954414320973,
      "loss": 0.9559,
      "step": 315
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00015939354740612,
      "loss": 0.9527,
      "step": 320
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.0001577677510120701,
      "loss": 1.0005,
      "step": 325
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.9512,
      "step": 330
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00015444707762088443,
      "loss": 0.9896,
      "step": 335
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.00015275353699716155,
      "loss": 0.9514,
      "step": 340
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1103515625,
      "learning_rate": 0.00015103876621438086,
      "loss": 0.9326,
      "step": 345
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00014930345536572924,
      "loss": 0.9457,
      "step": 350
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.00014754830281054777,
      "loss": 0.9748,
      "step": 355
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00014577401489328335,
      "loss": 0.9776,
      "step": 360
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00014398130565922742,
      "loss": 0.9827,
      "step": 365
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.0001421708965671551,
      "loss": 0.9688,
      "step": 370
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.00014034351619898088,
      "loss": 0.9832,
      "step": 375
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0001384998999665479,
      "loss": 0.9901,
      "step": 380
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00013664078981566843,
      "loss": 0.9898,
      "step": 385
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00013476693392753476,
      "loss": 0.9549,
      "step": 390
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0001328790864176209,
      "loss": 0.9486,
      "step": 395
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.00013097800703219586,
      "loss": 0.9776,
      "step": 400
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.0001290644608425711,
      "loss": 0.9457,
      "step": 405
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.0001271392179372048,
      "loss": 0.9693,
      "step": 410
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.00012520305311178716,
      "loss": 0.9658,
      "step": 415
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1103515625,
      "learning_rate": 0.00012325674555743106,
      "loss": 1.0126,
      "step": 420
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.109375,
      "learning_rate": 0.0001213010785470943,
      "loss": 0.9329,
      "step": 425
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.107421875,
      "learning_rate": 0.00011933683912035856,
      "loss": 0.9311,
      "step": 430
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.115234375,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.9496,
      "step": 435
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.11474609375,
      "learning_rate": 0.00011538580810732938,
      "loss": 0.9682,
      "step": 440
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.00011340060657587623,
      "loss": 0.9753,
      "step": 445
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00011141001209780249,
      "loss": 0.9755,
      "step": 450
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.00010941482576891689,
      "loss": 0.9706,
      "step": 455
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.11328125,
      "learning_rate": 0.00010741585053297494,
      "loss": 0.9557,
      "step": 460
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.9588,
      "step": 465
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00010340975241524132,
      "loss": 0.9213,
      "step": 470
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.00010140424174952232,
      "loss": 0.9914,
      "step": 475
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1201171875,
      "learning_rate": 9.939816596007146e-05,
      "loss": 0.9455,
      "step": 480
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.10986328125,
      "learning_rate": 9.739233237300402e-05,
      "loss": 0.9367,
      "step": 485
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.11083984375,
      "learning_rate": 9.538754821696323e-05,
      "loss": 0.9763,
      "step": 490
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.111328125,
      "learning_rate": 9.338462029825886e-05,
      "loss": 0.9507,
      "step": 495
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.11572265625,
      "learning_rate": 9.138435467617548e-05,
      "loss": 0.992,
      "step": 500
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11181640625,
      "learning_rate": 8.938755633858186e-05,
      "loss": 0.9587,
      "step": 505
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.1123046875,
      "learning_rate": 8.739502887797107e-05,
      "loss": 0.9864,
      "step": 510
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.1123046875,
      "learning_rate": 8.540757416806236e-05,
      "loss": 0.976,
      "step": 515
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.10693359375,
      "learning_rate": 8.342599204109472e-05,
      "loss": 0.948,
      "step": 520
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1123046875,
      "learning_rate": 8.145107996594206e-05,
      "loss": 0.9962,
      "step": 525
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.11279296875,
      "learning_rate": 7.948363272717926e-05,
      "loss": 0.9859,
      "step": 530
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.11669921875,
      "learning_rate": 7.752444210522898e-05,
      "loss": 1.0142,
      "step": 535
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.11328125,
      "learning_rate": 7.55742965577169e-05,
      "loss": 0.954,
      "step": 540
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.111328125,
      "learning_rate": 7.363398090216459e-05,
      "loss": 0.9726,
      "step": 545
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.11474609375,
      "learning_rate": 7.170427600014712e-05,
      "loss": 0.9598,
      "step": 550
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1181640625,
      "learning_rate": 6.978595844304271e-05,
      "loss": 0.9773,
      "step": 555
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.11083984375,
      "learning_rate": 6.787980023950108e-05,
      "loss": 0.964,
      "step": 560
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.12255859375,
      "learning_rate": 6.598656850475562e-05,
      "loss": 0.9626,
      "step": 565
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.11083984375,
      "learning_rate": 6.410702515190543e-05,
      "loss": 0.9722,
      "step": 570
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.10888671875,
      "learning_rate": 6.22419265852906e-05,
      "loss": 0.9332,
      "step": 575
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.1083984375,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.95,
      "step": 580
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.11083984375,
      "learning_rate": 5.8558060060224817e-05,
      "loss": 0.9757,
      "step": 585
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.11279296875,
      "learning_rate": 5.6740774638807935e-05,
      "loss": 0.9489,
      "step": 590
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.11669921875,
      "learning_rate": 5.494089848106156e-05,
      "loss": 0.9606,
      "step": 595
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.111328125,
      "learning_rate": 5.3159155930021e-05,
      "loss": 0.9461,
      "step": 600
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.109375,
      "learning_rate": 5.13962640310241e-05,
      "loss": 0.9324,
      "step": 605
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.109375,
      "learning_rate": 4.9652932243143146e-05,
      "loss": 0.9302,
      "step": 610
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1083984375,
      "learning_rate": 4.792986215366976e-05,
      "loss": 0.9496,
      "step": 615
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1123046875,
      "learning_rate": 4.62277471957679e-05,
      "loss": 0.9185,
      "step": 620
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.1123046875,
      "learning_rate": 4.454727236940814e-05,
      "loss": 0.9632,
      "step": 625
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.11083984375,
      "learning_rate": 4.288911396569599e-05,
      "loss": 0.9515,
      "step": 630
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.10986328125,
      "learning_rate": 4.1253939294705004e-05,
      "loss": 0.9341,
      "step": 635
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1103515625,
      "learning_rate": 3.964240641692416e-05,
      "loss": 0.9914,
      "step": 640
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1123046875,
      "learning_rate": 3.80551638784277e-05,
      "loss": 0.9792,
      "step": 645
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.1220703125,
      "learning_rate": 3.649285044987397e-05,
      "loss": 0.9405,
      "step": 650
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.10986328125,
      "learning_rate": 3.495609486943814e-05,
      "loss": 0.9875,
      "step": 655
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.109375,
      "learning_rate": 3.3445515589782574e-05,
      "loss": 0.933,
      "step": 660
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.111328125,
      "learning_rate": 3.1961720529166436e-05,
      "loss": 0.946,
      "step": 665
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.11376953125,
      "learning_rate": 3.05053068267948e-05,
      "loss": 0.9533,
      "step": 670
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.111328125,
      "learning_rate": 2.9076860602505564e-05,
      "loss": 0.9527,
      "step": 675
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.107421875,
      "learning_rate": 2.7676956720891235e-05,
      "loss": 0.9565,
      "step": 680
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.109375,
      "learning_rate": 2.6306158559950023e-05,
      "loss": 0.9447,
      "step": 685
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.11083984375,
      "learning_rate": 2.496501778435977e-05,
      "loss": 0.9301,
      "step": 690
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.13671875,
      "learning_rate": 2.3654074123465752e-05,
      "loss": 0.9523,
      "step": 695
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1123046875,
      "learning_rate": 2.2373855154071732e-05,
      "loss": 0.9705,
      "step": 700
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.11083984375,
      "learning_rate": 2.1124876088121692e-05,
      "loss": 0.9743,
      "step": 705
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.11083984375,
      "learning_rate": 1.990763956535777e-05,
      "loss": 0.9519,
      "step": 710
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.10986328125,
      "learning_rate": 1.8722635451037497e-05,
      "loss": 0.9858,
      "step": 715
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.10791015625,
      "learning_rate": 1.757034063879235e-05,
      "loss": 0.9419,
      "step": 720
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.115234375,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.9403,
      "step": 725
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.10546875,
      "learning_rate": 1.5365720490692426e-05,
      "loss": 0.9526,
      "step": 730
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.109375,
      "learning_rate": 1.4314282383241096e-05,
      "loss": 0.9508,
      "step": 735
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.10888671875,
      "learning_rate": 1.3297327677615124e-05,
      "loss": 0.979,
      "step": 740
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.11279296875,
      "learning_rate": 1.2315265637560357e-05,
      "loss": 0.9523,
      "step": 745
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.136849148460125e-05,
      "loss": 0.959,
      "step": 750
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.045738623898791e-05,
      "loss": 0.9758,
      "step": 755
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.11328125,
      "learning_rate": 9.582316566357996e-06,
      "loss": 0.9481,
      "step": 760
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.11083984375,
      "learning_rate": 8.74363463017569e-06,
      "loss": 0.9695,
      "step": 765
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.10693359375,
      "learning_rate": 7.94167795000682e-06,
      "loss": 0.964,
      "step": 770
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.11181640625,
      "learning_rate": 7.176769265687389e-06,
      "loss": 0.953,
      "step": 775
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.10791015625,
      "learning_rate": 6.4492164074399065e-06,
      "loss": 0.9455,
      "step": 780
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.1064453125,
      "learning_rate": 5.7593121719900835e-06,
      "loss": 0.966,
      "step": 785
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.11083984375,
      "learning_rate": 5.10733420473366e-06,
      "loss": 0.9649,
      "step": 790
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.1083984375,
      "learning_rate": 4.493544888000467e-06,
      "loss": 0.9341,
      "step": 795
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.11279296875,
      "learning_rate": 3.918191235461333e-06,
      "loss": 0.9724,
      "step": 800
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.1123046875,
      "learning_rate": 3.381504792719714e-06,
      "loss": 0.9757,
      "step": 805
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.1103515625,
      "learning_rate": 2.8837015441283586e-06,
      "loss": 0.9693,
      "step": 810
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.111328125,
      "learning_rate": 2.4249818258684664e-06,
      "loss": 0.9392,
      "step": 815
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.1123046875,
      "learning_rate": 2.0055302453262924e-06,
      "loss": 0.9504,
      "step": 820
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.107421875,
      "learning_rate": 1.6255156067997323e-06,
      "loss": 0.9688,
      "step": 825
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.10791015625,
      "learning_rate": 1.285090843564485e-06,
      "loss": 0.9293,
      "step": 830
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1103515625,
      "learning_rate": 9.843929563276733e-07,
      "loss": 0.9534,
      "step": 835
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.107421875,
      "learning_rate": 7.235429580931152e-07,
      "loss": 0.9132,
      "step": 840
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.111328125,
      "learning_rate": 5.026458254608457e-07,
      "loss": 0.9614,
      "step": 845
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.11865234375,
      "learning_rate": 3.21790456380211e-07,
      "loss": 0.9838,
      "step": 850
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.8104963437381993e-07,
      "loss": 0.9555,
      "step": 855
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.10791015625,
      "learning_rate": 8.047999924645222e-08,
      "loss": 0.9572,
      "step": 860
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.1103515625,
      "learning_rate": 2.012202429091392e-08,
      "loss": 0.9562,
      "step": 865
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.0,
      "loss": 0.98,
      "step": 870
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9584344029426575,
      "eval_runtime": 2489.4137,
      "eval_samples_per_second": 6.199,
      "eval_steps_per_second": 0.775,
      "step": 870
    },
    {
      "epoch": 1.0,
      "step": 870,
      "total_flos": 2.446890748289745e+18,
      "train_loss": 0.9710182381772446,
      "train_runtime": 17696.8906,
      "train_samples_per_second": 1.574,
      "train_steps_per_second": 0.049
    }
  ],
  "logging_steps": 5,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 2.446890748289745e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}