{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5074024226110363,
  "eval_steps": 500,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007178106774338268,
      "grad_norm": 0.65234375,
      "learning_rate": 0.0001,
      "loss": 6.8185,
      "step": 5
    },
    {
      "epoch": 0.014356213548676536,
      "grad_norm": 0.69921875,
      "learning_rate": 0.0001,
      "loss": 5.3587,
      "step": 10
    },
    {
      "epoch": 0.021534320323014805,
      "grad_norm": 0.984375,
      "learning_rate": 0.0001,
      "loss": 3.9044,
      "step": 15
    },
    {
      "epoch": 0.028712427097353072,
      "grad_norm": 0.84765625,
      "learning_rate": 0.0001,
      "loss": 2.4036,
      "step": 20
    },
    {
      "epoch": 0.03589053387169134,
      "grad_norm": 0.63671875,
      "learning_rate": 0.0001,
      "loss": 1.5506,
      "step": 25
    },
    {
      "epoch": 0.04306864064602961,
      "grad_norm": 0.44921875,
      "learning_rate": 0.0001,
      "loss": 0.8859,
      "step": 30
    },
    {
      "epoch": 0.05024674742036788,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001,
      "loss": 0.3927,
      "step": 35
    },
    {
      "epoch": 0.057424854194706144,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.0001,
      "loss": 0.1452,
      "step": 40
    },
    {
      "epoch": 0.06460296096904442,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.0001,
      "loss": 0.0693,
      "step": 45
    },
    {
      "epoch": 0.07178106774338268,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.0001,
      "loss": 0.0279,
      "step": 50
    },
    {
      "epoch": 0.07895917451772096,
      "grad_norm": 0.46484375,
      "learning_rate": 0.0001,
      "loss": 1.6299,
      "step": 55
    },
    {
      "epoch": 0.08613728129205922,
      "grad_norm": 0.201171875,
      "learning_rate": 0.0001,
      "loss": 0.9721,
      "step": 60
    },
    {
      "epoch": 0.09331538806639748,
      "grad_norm": 0.1953125,
      "learning_rate": 0.0001,
      "loss": 0.8273,
      "step": 65
    },
    {
      "epoch": 0.10049349484073576,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.0001,
      "loss": 0.6694,
      "step": 70
    },
    {
      "epoch": 0.10767160161507403,
      "grad_norm": 0.1171875,
      "learning_rate": 0.0001,
      "loss": 0.5689,
      "step": 75
    },
    {
      "epoch": 0.11484970838941229,
      "grad_norm": 0.1357421875,
      "learning_rate": 0.0001,
      "loss": 0.35,
      "step": 80
    },
    {
      "epoch": 0.12202781516375057,
      "grad_norm": 0.06640625,
      "learning_rate": 0.0001,
      "loss": 0.1548,
      "step": 85
    },
    {
      "epoch": 0.12920592193808883,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.0001,
      "loss": 0.0625,
      "step": 90
    },
    {
      "epoch": 0.1363840287124271,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.0001,
      "loss": 0.0345,
      "step": 95
    },
    {
      "epoch": 0.14356213548676536,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.0001,
      "loss": 0.0194,
      "step": 100
    },
    {
      "epoch": 0.15074024226110364,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001,
      "loss": 1.1732,
      "step": 105
    },
    {
      "epoch": 0.1579183490354419,
      "grad_norm": 0.2099609375,
      "learning_rate": 0.0001,
      "loss": 0.87,
      "step": 110
    },
    {
      "epoch": 0.16509645580978016,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.0001,
      "loss": 0.7213,
      "step": 115
    },
    {
      "epoch": 0.17227456258411844,
      "grad_norm": 0.158203125,
      "learning_rate": 0.0001,
      "loss": 0.5522,
      "step": 120
    },
    {
      "epoch": 0.17945266935845672,
      "grad_norm": 0.1015625,
      "learning_rate": 0.0001,
      "loss": 0.4513,
      "step": 125
    },
    {
      "epoch": 0.18663077613279497,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.0001,
      "loss": 0.2306,
      "step": 130
    },
    {
      "epoch": 0.19380888290713325,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.0001,
      "loss": 0.0997,
      "step": 135
    },
    {
      "epoch": 0.20098698968147152,
      "grad_norm": 0.060546875,
      "learning_rate": 0.0001,
      "loss": 0.0362,
      "step": 140
    },
    {
      "epoch": 0.20816509645580977,
      "grad_norm": 0.037109375,
      "learning_rate": 0.0001,
      "loss": 0.0274,
      "step": 145
    },
    {
      "epoch": 0.21534320323014805,
      "grad_norm": 0.0234375,
      "learning_rate": 0.0001,
      "loss": 0.0054,
      "step": 150
    },
    {
      "epoch": 0.22252131000448633,
      "grad_norm": 0.337890625,
      "learning_rate": 0.0001,
      "loss": 1.0624,
      "step": 155
    },
    {
      "epoch": 0.22969941677882458,
      "grad_norm": 0.1787109375,
      "learning_rate": 0.0001,
      "loss": 0.829,
      "step": 160
    },
    {
      "epoch": 0.23687752355316286,
      "grad_norm": 0.15234375,
      "learning_rate": 0.0001,
      "loss": 0.6497,
      "step": 165
    },
    {
      "epoch": 0.24405563032750113,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.0001,
      "loss": 0.5721,
      "step": 170
    },
    {
      "epoch": 0.2512337371018394,
      "grad_norm": 0.1533203125,
      "learning_rate": 0.0001,
      "loss": 0.4299,
      "step": 175
    },
    {
      "epoch": 0.25841184387617766,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001,
      "loss": 0.2842,
      "step": 180
    },
    {
      "epoch": 0.26558995065051594,
      "grad_norm": 0.049560546875,
      "learning_rate": 0.0001,
      "loss": 0.1096,
      "step": 185
    },
    {
      "epoch": 0.2727680574248542,
      "grad_norm": 0.072265625,
      "learning_rate": 0.0001,
      "loss": 0.0362,
      "step": 190
    },
    {
      "epoch": 0.27994616419919244,
      "grad_norm": 0.0634765625,
      "learning_rate": 0.0001,
      "loss": 0.0188,
      "step": 195
    },
    {
      "epoch": 0.2871242709735307,
      "grad_norm": 0.0167236328125,
      "learning_rate": 0.0001,
      "loss": 0.0077,
      "step": 200
    },
    {
      "epoch": 0.294302377747869,
      "grad_norm": 0.2109375,
      "learning_rate": 0.0001,
      "loss": 1.0719,
      "step": 205
    },
    {
      "epoch": 0.30148048452220727,
      "grad_norm": 0.1669921875,
      "learning_rate": 0.0001,
      "loss": 0.79,
      "step": 210
    },
    {
      "epoch": 0.30865859129654555,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001,
      "loss": 0.6307,
      "step": 215
    },
    {
      "epoch": 0.3158366980708838,
      "grad_norm": 0.126953125,
      "learning_rate": 0.0001,
      "loss": 0.5041,
      "step": 220
    },
    {
      "epoch": 0.32301480484522205,
      "grad_norm": 0.1748046875,
      "learning_rate": 0.0001,
      "loss": 0.4389,
      "step": 225
    },
    {
      "epoch": 0.3301929116195603,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001,
      "loss": 0.2337,
      "step": 230
    },
    {
      "epoch": 0.3373710183938986,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.0001,
      "loss": 0.1152,
      "step": 235
    },
    {
      "epoch": 0.3445491251682369,
      "grad_norm": 0.038818359375,
      "learning_rate": 0.0001,
      "loss": 0.0224,
      "step": 240
    },
    {
      "epoch": 0.35172723194257516,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0001,
      "loss": 0.0363,
      "step": 245
    },
    {
      "epoch": 0.35890533871691344,
      "grad_norm": 0.0400390625,
      "learning_rate": 0.0001,
      "loss": 0.0073,
      "step": 250
    },
    {
      "epoch": 0.36608344549125166,
      "grad_norm": 0.1650390625,
      "learning_rate": 0.0001,
      "loss": 1.0824,
      "step": 255
    },
    {
      "epoch": 0.37326155226558994,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0001,
      "loss": 0.8525,
      "step": 260
    },
    {
      "epoch": 0.3804396590399282,
      "grad_norm": 0.1484375,
      "learning_rate": 0.0001,
      "loss": 0.6736,
      "step": 265
    },
    {
      "epoch": 0.3876177658142665,
      "grad_norm": 0.16015625,
      "learning_rate": 0.0001,
      "loss": 0.5694,
      "step": 270
    },
    {
      "epoch": 0.39479587258860477,
      "grad_norm": 0.146484375,
      "learning_rate": 0.0001,
      "loss": 0.4329,
      "step": 275
    },
    {
      "epoch": 0.40197397936294305,
      "grad_norm": 0.095703125,
      "learning_rate": 0.0001,
      "loss": 0.2051,
      "step": 280
    },
    {
      "epoch": 0.40915208613728127,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001,
      "loss": 0.1067,
      "step": 285
    },
    {
      "epoch": 0.41633019291161955,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.0001,
      "loss": 0.0365,
      "step": 290
    },
    {
      "epoch": 0.4235082996859578,
      "grad_norm": 0.05126953125,
      "learning_rate": 0.0001,
      "loss": 0.0252,
      "step": 295
    },
    {
      "epoch": 0.4306864064602961,
      "grad_norm": 0.0029449462890625,
      "learning_rate": 0.0001,
      "loss": 0.0046,
      "step": 300
    },
    {
      "epoch": 0.4378645132346344,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.0461,
      "step": 305
    },
    {
      "epoch": 0.44504262000897266,
      "grad_norm": 0.1474609375,
      "learning_rate": 0.0001,
      "loss": 0.7834,
      "step": 310
    },
    {
      "epoch": 0.4522207267833109,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.0001,
      "loss": 0.6162,
      "step": 315
    },
    {
      "epoch": 0.45939883355764916,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.0001,
      "loss": 0.4886,
      "step": 320
    },
    {
      "epoch": 0.46657694033198743,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001,
      "loss": 0.3858,
      "step": 325
    },
    {
      "epoch": 0.4737550471063257,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001,
      "loss": 0.2249,
      "step": 330
    },
    {
      "epoch": 0.480933153880664,
      "grad_norm": 0.061279296875,
      "learning_rate": 0.0001,
      "loss": 0.0778,
      "step": 335
    },
    {
      "epoch": 0.48811126065500227,
      "grad_norm": 0.04931640625,
      "learning_rate": 0.0001,
      "loss": 0.0258,
      "step": 340
    },
    {
      "epoch": 0.4952893674293405,
      "grad_norm": 0.0283203125,
      "learning_rate": 0.0001,
      "loss": 0.0245,
      "step": 345
    },
    {
      "epoch": 0.5024674742036788,
      "grad_norm": 0.0218505859375,
      "learning_rate": 0.0001,
      "loss": 0.0108,
      "step": 350
    },
    {
      "epoch": 0.509645580978017,
      "grad_norm": 0.2060546875,
      "learning_rate": 0.0001,
      "loss": 1.1229,
      "step": 355
    },
    {
      "epoch": 0.5168236877523553,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001,
      "loss": 0.7767,
      "step": 360
    },
    {
      "epoch": 0.5240017945266936,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0001,
      "loss": 0.6151,
      "step": 365
    },
    {
      "epoch": 0.5311799013010319,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.0001,
      "loss": 0.4997,
      "step": 370
    },
    {
      "epoch": 0.5383580080753702,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001,
      "loss": 0.3645,
      "step": 375
    },
    {
      "epoch": 0.5455361148497084,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.0001,
      "loss": 0.2487,
      "step": 380
    },
    {
      "epoch": 0.5527142216240467,
      "grad_norm": 0.043212890625,
      "learning_rate": 0.0001,
      "loss": 0.1116,
      "step": 385
    },
    {
      "epoch": 0.5598923283983849,
      "grad_norm": 0.0262451171875,
      "learning_rate": 0.0001,
      "loss": 0.0278,
      "step": 390
    },
    {
      "epoch": 0.5670704351727232,
      "grad_norm": 0.048583984375,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 395
    },
    {
      "epoch": 0.5742485419470614,
      "grad_norm": 0.0458984375,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 400
    },
    {
      "epoch": 0.5814266487213997,
      "grad_norm": 0.1953125,
      "learning_rate": 0.0001,
      "loss": 0.9303,
      "step": 405
    },
    {
      "epoch": 0.588604755495738,
      "grad_norm": 0.1513671875,
      "learning_rate": 0.0001,
      "loss": 0.766,
      "step": 410
    },
    {
      "epoch": 0.5957828622700763,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001,
      "loss": 0.5917,
      "step": 415
    },
    {
      "epoch": 0.6029609690444145,
      "grad_norm": 0.10595703125,
      "learning_rate": 0.0001,
      "loss": 0.5611,
      "step": 420
    },
    {
      "epoch": 0.6101390758187528,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.0001,
      "loss": 0.3833,
      "step": 425
    },
    {
      "epoch": 0.6173171825930911,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.0001,
      "loss": 0.2563,
      "step": 430
    },
    {
      "epoch": 0.6244952893674294,
      "grad_norm": 0.07568359375,
      "learning_rate": 0.0001,
      "loss": 0.1056,
      "step": 435
    },
    {
      "epoch": 0.6316733961417677,
      "grad_norm": 0.087890625,
      "learning_rate": 0.0001,
      "loss": 0.0343,
      "step": 440
    },
    {
      "epoch": 0.6388515029161059,
      "grad_norm": 0.038818359375,
      "learning_rate": 0.0001,
      "loss": 0.0113,
      "step": 445
    },
    {
      "epoch": 0.6460296096904441,
      "grad_norm": 0.0194091796875,
      "learning_rate": 0.0001,
      "loss": 0.0062,
      "step": 450
    },
    {
      "epoch": 0.6532077164647824,
      "grad_norm": 0.18359375,
      "learning_rate": 0.0001,
      "loss": 0.894,
      "step": 455
    },
    {
      "epoch": 0.6603858232391207,
      "grad_norm": 0.158203125,
      "learning_rate": 0.0001,
      "loss": 0.7454,
      "step": 460
    },
    {
      "epoch": 0.6675639300134589,
      "grad_norm": 0.123046875,
      "learning_rate": 0.0001,
      "loss": 0.5539,
      "step": 465
    },
    {
      "epoch": 0.6747420367877972,
      "grad_norm": 0.1357421875,
      "learning_rate": 0.0001,
      "loss": 0.5263,
      "step": 470
    },
    {
      "epoch": 0.6819201435621355,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001,
      "loss": 0.3882,
      "step": 475
    },
    {
      "epoch": 0.6890982503364738,
      "grad_norm": 0.07958984375,
      "learning_rate": 0.0001,
      "loss": 0.2243,
      "step": 480
    },
    {
      "epoch": 0.696276357110812,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.0001,
      "loss": 0.0728,
      "step": 485
    },
    {
      "epoch": 0.7034544638851503,
      "grad_norm": 0.048583984375,
      "learning_rate": 0.0001,
      "loss": 0.0205,
      "step": 490
    },
    {
      "epoch": 0.7106325706594886,
      "grad_norm": 0.06103515625,
      "learning_rate": 0.0001,
      "loss": 0.0179,
      "step": 495
    },
    {
      "epoch": 0.7178106774338269,
      "grad_norm": 0.031494140625,
      "learning_rate": 0.0001,
      "loss": 0.0072,
      "step": 500
    },
    {
      "epoch": 0.7249887842081651,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.0001,
      "loss": 0.9516,
      "step": 505
    },
    {
      "epoch": 0.7321668909825033,
      "grad_norm": 0.1240234375,
      "learning_rate": 0.0001,
      "loss": 0.6854,
      "step": 510
    },
    {
      "epoch": 0.7393449977568416,
      "grad_norm": 0.1552734375,
      "learning_rate": 0.0001,
      "loss": 0.5769,
      "step": 515
    },
    {
      "epoch": 0.7465231045311799,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001,
      "loss": 0.4634,
      "step": 520
    },
    {
      "epoch": 0.7537012113055181,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001,
      "loss": 0.3856,
      "step": 525
    },
    {
      "epoch": 0.7608793180798564,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.0001,
      "loss": 0.2155,
      "step": 530
    },
    {
      "epoch": 0.7680574248541947,
      "grad_norm": 0.0634765625,
      "learning_rate": 0.0001,
      "loss": 0.0857,
      "step": 535
    },
    {
      "epoch": 0.775235531628533,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001,
      "loss": 0.0233,
      "step": 540
    },
    {
      "epoch": 0.7824136384028713,
      "grad_norm": 0.0281982421875,
      "learning_rate": 0.0001,
      "loss": 0.013,
      "step": 545
    },
    {
      "epoch": 0.7895917451772095,
      "grad_norm": 0.016845703125,
      "learning_rate": 0.0001,
      "loss": 0.0061,
      "step": 550
    },
    {
      "epoch": 0.7967698519515478,
      "grad_norm": 0.1796875,
      "learning_rate": 0.0001,
      "loss": 0.8853,
      "step": 555
    },
    {
      "epoch": 0.8039479587258861,
      "grad_norm": 0.154296875,
      "learning_rate": 0.0001,
      "loss": 0.726,
      "step": 560
    },
    {
      "epoch": 0.8111260655002244,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001,
      "loss": 0.62,
      "step": 565
    },
    {
      "epoch": 0.8183041722745625,
      "grad_norm": 0.126953125,
      "learning_rate": 0.0001,
      "loss": 0.5036,
      "step": 570
    },
    {
      "epoch": 0.8254822790489008,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0001,
      "loss": 0.4053,
      "step": 575
    },
    {
      "epoch": 0.8326603858232391,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.0001,
      "loss": 0.2355,
      "step": 580
    },
    {
      "epoch": 0.8398384925975774,
      "grad_norm": 0.045654296875,
      "learning_rate": 0.0001,
      "loss": 0.0751,
      "step": 585
    },
    {
      "epoch": 0.8470165993719156,
      "grad_norm": 0.109375,
      "learning_rate": 0.0001,
      "loss": 0.0226,
      "step": 590
    },
    {
      "epoch": 0.8541947061462539,
      "grad_norm": 0.027587890625,
      "learning_rate": 0.0001,
      "loss": 0.0055,
      "step": 595
    },
    {
      "epoch": 0.8613728129205922,
      "grad_norm": 0.05712890625,
      "learning_rate": 0.0001,
      "loss": 0.0052,
      "step": 600
    },
    {
      "epoch": 0.8685509196949305,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 0.9366,
      "step": 605
    },
    {
      "epoch": 0.8757290264692688,
      "grad_norm": 0.1484375,
      "learning_rate": 0.0001,
      "loss": 0.7429,
      "step": 610
    },
    {
      "epoch": 0.882907133243607,
      "grad_norm": 0.14453125,
      "learning_rate": 0.0001,
      "loss": 0.564,
      "step": 615
    },
    {
      "epoch": 0.8900852400179453,
      "grad_norm": 0.140625,
      "learning_rate": 0.0001,
      "loss": 0.5045,
      "step": 620
    },
    {
      "epoch": 0.8972633467922836,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.0001,
      "loss": 0.3997,
      "step": 625
    },
    {
      "epoch": 0.9044414535666218,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.0001,
      "loss": 0.1856,
      "step": 630
    },
    {
      "epoch": 0.91161956034096,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.0001,
      "loss": 0.0583,
      "step": 635
    },
    {
      "epoch": 0.9187976671152983,
      "grad_norm": 0.033935546875,
      "learning_rate": 0.0001,
      "loss": 0.0274,
      "step": 640
    },
    {
      "epoch": 0.9259757738896366,
      "grad_norm": 0.03271484375,
      "learning_rate": 0.0001,
      "loss": 0.0078,
      "step": 645
    },
    {
      "epoch": 0.9331538806639749,
      "grad_norm": 0.0244140625,
      "learning_rate": 0.0001,
      "loss": 0.003,
      "step": 650
    },
    {
      "epoch": 0.9403319874383131,
      "grad_norm": 0.220703125,
      "learning_rate": 0.0001,
      "loss": 0.9234,
      "step": 655
    },
    {
      "epoch": 0.9475100942126514,
      "grad_norm": 0.1494140625,
      "learning_rate": 0.0001,
      "loss": 0.7145,
      "step": 660
    },
    {
      "epoch": 0.9546882009869897,
      "grad_norm": 0.138671875,
      "learning_rate": 0.0001,
      "loss": 0.5764,
      "step": 665
    },
    {
      "epoch": 0.961866307761328,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.0001,
      "loss": 0.4568,
      "step": 670
    },
    {
      "epoch": 0.9690444145356663,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.0001,
      "loss": 0.2681,
      "step": 675
    },
    {
      "epoch": 0.9762225213100045,
      "grad_norm": 0.080078125,
      "learning_rate": 0.0001,
      "loss": 0.1399,
      "step": 680
    },
    {
      "epoch": 0.9834006280843428,
      "grad_norm": 0.068359375,
      "learning_rate": 0.0001,
      "loss": 0.0375,
      "step": 685
    },
    {
      "epoch": 0.990578734858681,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.0001,
      "loss": 0.0108,
      "step": 690
    },
    {
      "epoch": 0.9977568416330193,
      "grad_norm": 0.022216796875,
      "learning_rate": 0.0001,
      "loss": 0.0082,
      "step": 695
    },
    {
      "epoch": 1.0049349484073575,
      "grad_norm": 0.193359375,
      "learning_rate": 0.0001,
      "loss": 0.6031,
      "step": 700
    },
    {
      "epoch": 1.012113055181696,
      "grad_norm": 0.1640625,
      "learning_rate": 0.0001,
      "loss": 0.7291,
      "step": 705
    },
    {
      "epoch": 1.019291161956034,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0001,
      "loss": 0.5393,
      "step": 710
    },
    {
      "epoch": 1.0264692687303723,
      "grad_norm": 0.1416015625,
      "learning_rate": 0.0001,
      "loss": 0.413,
      "step": 715
    },
    {
      "epoch": 1.0336473755047106,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.0001,
      "loss": 0.3693,
      "step": 720
    },
    {
      "epoch": 1.0408254822790488,
      "grad_norm": 0.123046875,
      "learning_rate": 0.0001,
      "loss": 0.2104,
      "step": 725
    },
    {
      "epoch": 1.0480035890533872,
      "grad_norm": 0.055908203125,
      "learning_rate": 0.0001,
      "loss": 0.0834,
      "step": 730
    },
    {
      "epoch": 1.0551816958277254,
      "grad_norm": 0.0546875,
      "learning_rate": 0.0001,
      "loss": 0.0144,
      "step": 735
    },
    {
      "epoch": 1.0623598026020638,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.0001,
      "loss": 0.0119,
      "step": 740
    },
    {
      "epoch": 1.069537909376402,
      "grad_norm": 0.0034332275390625,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 745
    },
    {
      "epoch": 1.0767160161507403,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001,
      "loss": 0.5662,
      "step": 750
    },
    {
      "epoch": 1.0838941229250785,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 0.7079,
      "step": 755
    },
    {
      "epoch": 1.0910722296994169,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 0.5619,
      "step": 760
    },
    {
      "epoch": 1.098250336473755,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0001,
      "loss": 0.4236,
      "step": 765
    },
    {
      "epoch": 1.1054284432480934,
      "grad_norm": 0.11328125,
      "learning_rate": 0.0001,
      "loss": 0.3422,
      "step": 770
    },
    {
      "epoch": 1.1126065500224316,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.0001,
      "loss": 0.2757,
      "step": 775
    },
    {
      "epoch": 1.1197846567967698,
      "grad_norm": 0.1103515625,
      "learning_rate": 0.0001,
      "loss": 0.101,
      "step": 780
    },
    {
      "epoch": 1.1269627635711081,
      "grad_norm": 0.0615234375,
      "learning_rate": 0.0001,
      "loss": 0.0292,
      "step": 785
    },
    {
      "epoch": 1.1341408703454463,
      "grad_norm": 0.01123046875,
      "learning_rate": 0.0001,
      "loss": 0.0117,
      "step": 790
    },
    {
      "epoch": 1.1413189771197847,
      "grad_norm": 0.0311279296875,
      "learning_rate": 0.0001,
      "loss": 0.0068,
      "step": 795
    },
    {
      "epoch": 1.1484970838941229,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.0001,
      "loss": 0.5275,
      "step": 800
    },
    {
      "epoch": 1.1556751906684612,
      "grad_norm": 0.2060546875,
      "learning_rate": 0.0001,
      "loss": 0.7151,
      "step": 805
    },
    {
      "epoch": 1.1628532974427994,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0001,
      "loss": 0.5625,
      "step": 810
    },
    {
      "epoch": 1.1700314042171378,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0001,
      "loss": 0.4765,
      "step": 815
    },
    {
      "epoch": 1.177209510991476,
      "grad_norm": 0.1875,
      "learning_rate": 0.0001,
      "loss": 0.3728,
      "step": 820
    },
    {
      "epoch": 1.1843876177658144,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.0001,
      "loss": 0.2169,
      "step": 825
    },
    {
      "epoch": 1.1915657245401525,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.0001,
      "loss": 0.09,
      "step": 830
    },
    {
      "epoch": 1.198743831314491,
      "grad_norm": 0.06396484375,
      "learning_rate": 0.0001,
      "loss": 0.0261,
      "step": 835
    },
    {
      "epoch": 1.205921938088829,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.0001,
      "loss": 0.0169,
      "step": 840
    },
    {
      "epoch": 1.2131000448631672,
      "grad_norm": 0.01409912109375,
      "learning_rate": 0.0001,
      "loss": 0.0041,
      "step": 845
    },
    {
      "epoch": 1.2202781516375056,
      "grad_norm": 0.2265625,
      "learning_rate": 0.0001,
      "loss": 0.5508,
      "step": 850
    },
    {
      "epoch": 1.2274562584118438,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001,
      "loss": 0.7281,
      "step": 855
    },
    {
      "epoch": 1.2346343651861822,
      "grad_norm": 0.212890625,
      "learning_rate": 0.0001,
      "loss": 0.499,
      "step": 860
    },
    {
      "epoch": 1.2418124719605204,
      "grad_norm": 0.1767578125,
      "learning_rate": 0.0001,
      "loss": 0.5054,
      "step": 865
    },
    {
      "epoch": 1.2489905787348587,
      "grad_norm": 0.1513671875,
      "learning_rate": 0.0001,
      "loss": 0.3918,
      "step": 870
    },
    {
      "epoch": 1.256168685509197,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001,
      "loss": 0.2211,
      "step": 875
    },
    {
      "epoch": 1.263346792283535,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.0001,
      "loss": 0.099,
      "step": 880
    },
    {
      "epoch": 1.2705248990578735,
      "grad_norm": 0.0263671875,
      "learning_rate": 0.0001,
      "loss": 0.0239,
      "step": 885
    },
    {
      "epoch": 1.2777030058322119,
      "grad_norm": 0.055908203125,
      "learning_rate": 0.0001,
      "loss": 0.0203,
      "step": 890
    },
    {
      "epoch": 1.28488111260655,
      "grad_norm": 0.0172119140625,
      "learning_rate": 0.0001,
      "loss": 0.0053,
      "step": 895
    },
    {
      "epoch": 1.2920592193808882,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 0.4856,
      "step": 900
    },
    {
      "epoch": 1.2992373261552266,
      "grad_norm": 0.2138671875,
      "learning_rate": 0.0001,
      "loss": 0.7204,
      "step": 905
    },
    {
      "epoch": 1.3064154329295647,
      "grad_norm": 0.19140625,
      "learning_rate": 0.0001,
      "loss": 0.5374,
      "step": 910
    },
    {
      "epoch": 1.3135935397039031,
      "grad_norm": 0.216796875,
      "learning_rate": 0.0001,
      "loss": 0.48,
      "step": 915
    },
    {
      "epoch": 1.3207716464782413,
      "grad_norm": 0.19921875,
      "learning_rate": 0.0001,
      "loss": 0.3897,
      "step": 920
    },
    {
      "epoch": 1.3279497532525797,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.0001,
      "loss": 0.2242,
      "step": 925
    },
    {
      "epoch": 1.3351278600269179,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.0001,
      "loss": 0.1292,
      "step": 930
    },
    {
      "epoch": 1.3423059668012562,
      "grad_norm": 0.068359375,
      "learning_rate": 0.0001,
      "loss": 0.0242,
      "step": 935
    },
    {
      "epoch": 1.3494840735755944,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.0001,
      "loss": 0.0092,
      "step": 940
    },
    {
      "epoch": 1.3566621803499328,
      "grad_norm": 0.004241943359375,
      "learning_rate": 0.0001,
      "loss": 0.0039,
      "step": 945
    },
    {
      "epoch": 1.363840287124271,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0001,
      "loss": 0.5465,
      "step": 950
    },
    {
      "epoch": 1.3710183938986091,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.0001,
      "loss": 0.6114,
      "step": 955
    },
    {
      "epoch": 1.3781965006729475,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001,
      "loss": 0.5226,
      "step": 960
    },
    {
      "epoch": 1.385374607447286,
      "grad_norm": 0.205078125,
      "learning_rate": 0.0001,
      "loss": 0.4234,
      "step": 965
    },
    {
      "epoch": 1.392552714221624,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001,
      "loss": 0.3595,
      "step": 970
    },
    {
      "epoch": 1.3997308209959622,
      "grad_norm": 0.123046875,
      "learning_rate": 0.0001,
      "loss": 0.2464,
      "step": 975
    },
    {
      "epoch": 1.4069089277703006,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.0001,
      "loss": 0.11,
      "step": 980
    },
    {
      "epoch": 1.4140870345446388,
      "grad_norm": 0.05322265625,
      "learning_rate": 0.0001,
      "loss": 0.0205,
      "step": 985
    },
    {
      "epoch": 1.4212651413189772,
      "grad_norm": 0.0206298828125,
      "learning_rate": 0.0001,
      "loss": 0.0102,
      "step": 990
    },
    {
      "epoch": 1.4284432480933154,
      "grad_norm": 0.0250244140625,
      "learning_rate": 0.0001,
      "loss": 0.0044,
      "step": 995
    },
    {
      "epoch": 1.4356213548676537,
      "grad_norm": 0.23046875,
      "learning_rate": 0.0001,
      "loss": 0.4827,
      "step": 1000
    },
    {
      "epoch": 1.442799461641992,
      "grad_norm": 0.2314453125,
      "learning_rate": 0.0001,
      "loss": 0.6536,
      "step": 1005
    },
    {
      "epoch": 1.44997756841633,
      "grad_norm": 0.1953125,
      "learning_rate": 0.0001,
      "loss": 0.5993,
      "step": 1010
    },
    {
      "epoch": 1.4571556751906685,
      "grad_norm": 0.158203125,
      "learning_rate": 0.0001,
      "loss": 0.4176,
      "step": 1015
    },
    {
      "epoch": 1.4643337819650069,
      "grad_norm": 0.1689453125,
      "learning_rate": 0.0001,
      "loss": 0.307,
      "step": 1020
    },
    {
      "epoch": 1.471511888739345,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.0001,
      "loss": 0.2381,
      "step": 1025
    },
    {
      "epoch": 1.4786899955136832,
      "grad_norm": 0.06396484375,
      "learning_rate": 0.0001,
      "loss": 0.084,
      "step": 1030
    },
    {
      "epoch": 1.4858681022880216,
      "grad_norm": 0.01153564453125,
      "learning_rate": 0.0001,
      "loss": 0.0165,
      "step": 1035
    },
    {
      "epoch": 1.4930462090623597,
      "grad_norm": 0.0283203125,
      "learning_rate": 0.0001,
      "loss": 0.0059,
      "step": 1040
    },
    {
      "epoch": 1.500224315836698,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.0001,
      "loss": 0.0051,
      "step": 1045
    },
    {
      "epoch": 1.5074024226110363,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 0.5321,
      "step": 1050
    },
    {
      "epoch": 1.5074024226110363,
      "step": 1050,
      "total_flos": 4.83809405232513e+18,
      "train_loss": 0.43872410982492427,
      "train_runtime": 144968.4958,
      "train_samples_per_second": 0.464,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 5,
  "max_steps": 1050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.83809405232513e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}