{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2620,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003816793893129771,
      "grad_norm": 2.615494966506958,
      "learning_rate": 1.7175572519083972e-06,
      "loss": 0.162,
      "step": 10
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": 3.7720587253570557,
      "learning_rate": 3.6259541984732824e-06,
      "loss": 0.1953,
      "step": 20
    },
    {
      "epoch": 0.011450381679389313,
      "grad_norm": 3.1540627479553223,
      "learning_rate": 5.534351145038168e-06,
      "loss": 0.1651,
      "step": 30
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 2.391727924346924,
      "learning_rate": 7.4427480916030536e-06,
      "loss": 0.0976,
      "step": 40
    },
    {
      "epoch": 0.019083969465648856,
      "grad_norm": 1.7957884073257446,
      "learning_rate": 9.351145038167939e-06,
      "loss": 0.0483,
      "step": 50
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": 2.7055726051330566,
      "learning_rate": 1.1259541984732823e-05,
      "loss": 0.0618,
      "step": 60
    },
    {
      "epoch": 0.026717557251908396,
      "grad_norm": 0.7185584902763367,
      "learning_rate": 1.316793893129771e-05,
      "loss": 0.0452,
      "step": 70
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 0.3574228286743164,
      "learning_rate": 1.5076335877862596e-05,
      "loss": 0.0287,
      "step": 80
    },
    {
      "epoch": 0.03435114503816794,
      "grad_norm": 0.600852906703949,
      "learning_rate": 1.6984732824427482e-05,
      "loss": 0.0345,
      "step": 90
    },
    {
      "epoch": 0.03816793893129771,
      "grad_norm": 1.2814120054244995,
      "learning_rate": 1.8893129770992367e-05,
      "loss": 0.0375,
      "step": 100
    },
    {
      "epoch": 0.04198473282442748,
      "grad_norm": 0.7709506154060364,
      "learning_rate": 2.0801526717557255e-05,
      "loss": 0.0177,
      "step": 110
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": 0.749973714351654,
      "learning_rate": 2.270992366412214e-05,
      "loss": 0.0219,
      "step": 120
    },
    {
      "epoch": 0.04961832061068702,
      "grad_norm": 0.14578384160995483,
      "learning_rate": 2.4618320610687024e-05,
      "loss": 0.0226,
      "step": 130
    },
    {
      "epoch": 0.05343511450381679,
      "grad_norm": 1.139318585395813,
      "learning_rate": 2.652671755725191e-05,
      "loss": 0.0247,
      "step": 140
    },
    {
      "epoch": 0.05725190839694656,
      "grad_norm": 1.522550344467163,
      "learning_rate": 2.8435114503816796e-05,
      "loss": 0.0219,
      "step": 150
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": 0.010661217384040356,
      "learning_rate": 3.0343511450381677e-05,
      "loss": 0.0233,
      "step": 160
    },
    {
      "epoch": 0.0648854961832061,
      "grad_norm": 1.0627490282058716,
      "learning_rate": 3.2251908396946565e-05,
      "loss": 0.0143,
      "step": 170
    },
    {
      "epoch": 0.06870229007633588,
      "grad_norm": 0.4552942216396332,
      "learning_rate": 3.416030534351145e-05,
      "loss": 0.0271,
      "step": 180
    },
    {
      "epoch": 0.07251908396946564,
      "grad_norm": 0.6815011501312256,
      "learning_rate": 3.606870229007634e-05,
      "loss": 0.0185,
      "step": 190
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": 0.698657751083374,
      "learning_rate": 3.797709923664122e-05,
      "loss": 0.0162,
      "step": 200
    },
    {
      "epoch": 0.08015267175572519,
      "grad_norm": 0.5514554977416992,
      "learning_rate": 3.988549618320611e-05,
      "loss": 0.0277,
      "step": 210
    },
    {
      "epoch": 0.08396946564885496,
      "grad_norm": 0.09276178479194641,
      "learning_rate": 4.1793893129771e-05,
      "loss": 0.0176,
      "step": 220
    },
    {
      "epoch": 0.08778625954198473,
      "grad_norm": 1.0245144367218018,
      "learning_rate": 4.370229007633588e-05,
      "loss": 0.0219,
      "step": 230
    },
    {
      "epoch": 0.0916030534351145,
      "grad_norm": 0.5731092095375061,
      "learning_rate": 4.561068702290077e-05,
      "loss": 0.0188,
      "step": 240
    },
    {
      "epoch": 0.09541984732824428,
      "grad_norm": 0.11703433096408844,
      "learning_rate": 4.751908396946565e-05,
      "loss": 0.0153,
      "step": 250
    },
    {
      "epoch": 0.09923664122137404,
      "grad_norm": 0.3222142159938812,
      "learning_rate": 4.9427480916030536e-05,
      "loss": 0.0176,
      "step": 260
    },
    {
      "epoch": 0.10305343511450382,
      "grad_norm": 0.6780900359153748,
      "learning_rate": 4.9998912785867505e-05,
      "loss": 0.0143,
      "step": 270
    },
    {
      "epoch": 0.10687022900763359,
      "grad_norm": 0.8537261486053467,
      "learning_rate": 4.999358788306519e-05,
      "loss": 0.0223,
      "step": 280
    },
    {
      "epoch": 0.11068702290076336,
      "grad_norm": 0.17257721722126007,
      "learning_rate": 4.998382654320609e-05,
      "loss": 0.0178,
      "step": 290
    },
    {
      "epoch": 0.11450381679389313,
      "grad_norm": 0.7881976962089539,
      "learning_rate": 4.996963049895741e-05,
      "loss": 0.0146,
      "step": 300
    },
    {
      "epoch": 0.1183206106870229,
      "grad_norm": 0.6446636915206909,
      "learning_rate": 4.99510022701597e-05,
      "loss": 0.0109,
      "step": 310
    },
    {
      "epoch": 0.12213740458015267,
      "grad_norm": 0.6660375595092773,
      "learning_rate": 4.992794516337964e-05,
      "loss": 0.012,
      "step": 320
    },
    {
      "epoch": 0.12595419847328243,
      "grad_norm": 0.47002533078193665,
      "learning_rate": 4.9900463271323064e-05,
      "loss": 0.0133,
      "step": 330
    },
    {
      "epoch": 0.1297709923664122,
      "grad_norm": 0.9555854201316833,
      "learning_rate": 4.9868561472108496e-05,
      "loss": 0.0173,
      "step": 340
    },
    {
      "epoch": 0.13358778625954199,
      "grad_norm": 0.14546959102153778,
      "learning_rate": 4.9832245428401316e-05,
      "loss": 0.0172,
      "step": 350
    },
    {
      "epoch": 0.13740458015267176,
      "grad_norm": 0.27474039793014526,
      "learning_rate": 4.979152158640853e-05,
      "loss": 0.0174,
      "step": 360
    },
    {
      "epoch": 0.14122137404580154,
      "grad_norm": 0.2749495208263397,
      "learning_rate": 4.974639717473465e-05,
      "loss": 0.0172,
      "step": 370
    },
    {
      "epoch": 0.1450381679389313,
      "grad_norm": 0.19880647957324982,
      "learning_rate": 4.9696880203098525e-05,
      "loss": 0.012,
      "step": 380
    },
    {
      "epoch": 0.14885496183206107,
      "grad_norm": 0.7163119912147522,
      "learning_rate": 4.964297946091163e-05,
      "loss": 0.0138,
      "step": 390
    },
    {
      "epoch": 0.15267175572519084,
      "grad_norm": 0.4733160436153412,
      "learning_rate": 4.9584704515717884e-05,
      "loss": 0.0074,
      "step": 400
    },
    {
      "epoch": 0.15648854961832062,
      "grad_norm": 0.5145673155784607,
      "learning_rate": 4.952206571149541e-05,
      "loss": 0.0178,
      "step": 410
    },
    {
      "epoch": 0.16030534351145037,
      "grad_norm": 0.07867272943258286,
      "learning_rate": 4.945507416682046e-05,
      "loss": 0.0132,
      "step": 420
    },
    {
      "epoch": 0.16412213740458015,
      "grad_norm": 0.023460840806365013,
      "learning_rate": 4.938374177289378e-05,
      "loss": 0.0085,
      "step": 430
    },
    {
      "epoch": 0.16793893129770993,
      "grad_norm": 0.6247947812080383,
      "learning_rate": 4.930808119142993e-05,
      "loss": 0.0176,
      "step": 440
    },
    {
      "epoch": 0.1717557251908397,
      "grad_norm": 0.49582046270370483,
      "learning_rate": 4.922810585240981e-05,
      "loss": 0.0188,
      "step": 450
    },
    {
      "epoch": 0.17557251908396945,
      "grad_norm": 1.1747221946716309,
      "learning_rate": 4.914382995169673e-05,
      "loss": 0.0187,
      "step": 460
    },
    {
      "epoch": 0.17938931297709923,
      "grad_norm": 0.9253813624382019,
      "learning_rate": 4.905526844851667e-05,
      "loss": 0.0125,
      "step": 470
    },
    {
      "epoch": 0.183206106870229,
      "grad_norm": 0.32356423139572144,
      "learning_rate": 4.8962437062802924e-05,
      "loss": 0.0145,
      "step": 480
    },
    {
      "epoch": 0.18702290076335878,
      "grad_norm": 0.16892339289188385,
      "learning_rate": 4.886535227240579e-05,
      "loss": 0.0132,
      "step": 490
    },
    {
      "epoch": 0.19083969465648856,
      "grad_norm": 0.08704151958227158,
      "learning_rate": 4.8764031310167725e-05,
      "loss": 0.0145,
      "step": 500
    },
    {
      "epoch": 0.19083969465648856,
      "eval_loss": 0.03389899432659149,
      "eval_runtime": 140.2568,
      "eval_samples_per_second": 56.91,
      "eval_steps_per_second": 0.299,
      "step": 500
    },
    {
      "epoch": 0.1946564885496183,
      "grad_norm": 0.021338067948818207,
      "learning_rate": 4.865849216086438e-05,
      "loss": 0.0112,
      "step": 510
    },
    {
      "epoch": 0.1984732824427481,
      "grad_norm": 0.18011535704135895,
      "learning_rate": 4.854875355801233e-05,
      "loss": 0.0068,
      "step": 520
    },
    {
      "epoch": 0.20229007633587787,
      "grad_norm": 0.6645931005477905,
      "learning_rate": 4.843483498054381e-05,
      "loss": 0.0182,
      "step": 530
    },
    {
      "epoch": 0.20610687022900764,
      "grad_norm": 0.1481589674949646,
      "learning_rate": 4.83167566493491e-05,
      "loss": 0.0113,
      "step": 540
    },
    {
      "epoch": 0.2099236641221374,
      "grad_norm": 0.05964776873588562,
      "learning_rate": 4.819453952368731e-05,
      "loss": 0.0101,
      "step": 550
    },
    {
      "epoch": 0.21374045801526717,
      "grad_norm": 0.5340839624404907,
      "learning_rate": 4.8068205297465986e-05,
      "loss": 0.0181,
      "step": 560
    },
    {
      "epoch": 0.21755725190839695,
      "grad_norm": 0.28655287623405457,
      "learning_rate": 4.7937776395390434e-05,
      "loss": 0.0073,
      "step": 570
    },
    {
      "epoch": 0.22137404580152673,
      "grad_norm": 0.08776471763849258,
      "learning_rate": 4.7803275968983244e-05,
      "loss": 0.0129,
      "step": 580
    },
    {
      "epoch": 0.22519083969465647,
      "grad_norm": 0.11037462204694748,
      "learning_rate": 4.766472789247483e-05,
      "loss": 0.0088,
      "step": 590
    },
    {
      "epoch": 0.22900763358778625,
      "grad_norm": 0.21740970015525818,
      "learning_rate": 4.752215675856566e-05,
      "loss": 0.0115,
      "step": 600
    },
    {
      "epoch": 0.23282442748091603,
      "grad_norm": 0.07760237902402878,
      "learning_rate": 4.737558787406103e-05,
      "loss": 0.0118,
      "step": 610
    },
    {
      "epoch": 0.2366412213740458,
      "grad_norm": 0.2091819792985916,
      "learning_rate": 4.722504725537896e-05,
      "loss": 0.0096,
      "step": 620
    },
    {
      "epoch": 0.24045801526717558,
      "grad_norm": 1.0305904150009155,
      "learning_rate": 4.7070561623932265e-05,
      "loss": 0.0108,
      "step": 630
    },
    {
      "epoch": 0.24427480916030533,
      "grad_norm": 0.03920348733663559,
      "learning_rate": 4.691215840138537e-05,
      "loss": 0.0116,
      "step": 640
    },
    {
      "epoch": 0.2480916030534351,
      "grad_norm": 0.02367626503109932,
      "learning_rate": 4.674986570478695e-05,
      "loss": 0.0133,
      "step": 650
    },
    {
      "epoch": 0.25190839694656486,
      "grad_norm": 0.05315301567316055,
      "learning_rate": 4.6583712341578984e-05,
      "loss": 0.0087,
      "step": 660
    },
    {
      "epoch": 0.25572519083969464,
      "grad_norm": 0.10831905901432037,
      "learning_rate": 4.641372780448341e-05,
      "loss": 0.0084,
      "step": 670
    },
    {
      "epoch": 0.2595419847328244,
      "grad_norm": 0.078117236495018,
      "learning_rate": 4.6239942266267056e-05,
      "loss": 0.0058,
      "step": 680
    },
    {
      "epoch": 0.2633587786259542,
      "grad_norm": 0.28782543540000916,
      "learning_rate": 4.6062386574385886e-05,
      "loss": 0.0104,
      "step": 690
    },
    {
      "epoch": 0.26717557251908397,
      "grad_norm": 0.04873083531856537,
      "learning_rate": 4.5881092245509506e-05,
      "loss": 0.0118,
      "step": 700
    },
    {
      "epoch": 0.27099236641221375,
      "grad_norm": 0.26269766688346863,
      "learning_rate": 4.56960914599268e-05,
      "loss": 0.0077,
      "step": 710
    },
    {
      "epoch": 0.2748091603053435,
      "grad_norm": 0.3128824532032013,
      "learning_rate": 4.55074170558339e-05,
      "loss": 0.0107,
      "step": 720
    },
    {
      "epoch": 0.2786259541984733,
      "grad_norm": 1.1486977338790894,
      "learning_rate": 4.531510252350526e-05,
      "loss": 0.012,
      "step": 730
    },
    {
      "epoch": 0.2824427480916031,
      "grad_norm": 0.35734987258911133,
      "learning_rate": 4.511918199934907e-05,
      "loss": 0.0121,
      "step": 740
    },
    {
      "epoch": 0.2862595419847328,
      "grad_norm": 0.2775309681892395,
      "learning_rate": 4.491969025984789e-05,
      "loss": 0.0139,
      "step": 750
    },
    {
      "epoch": 0.2900763358778626,
      "grad_norm": 0.22545866668224335,
      "learning_rate": 4.471666271538578e-05,
      "loss": 0.0047,
      "step": 760
    },
    {
      "epoch": 0.29389312977099236,
      "grad_norm": 0.3366382420063019,
      "learning_rate": 4.451013540396281e-05,
      "loss": 0.008,
      "step": 770
    },
    {
      "epoch": 0.29770992366412213,
      "grad_norm": 0.645935595035553,
      "learning_rate": 4.430014498479819e-05,
      "loss": 0.0197,
      "step": 780
    },
    {
      "epoch": 0.3015267175572519,
      "grad_norm": 0.022258713841438293,
      "learning_rate": 4.408672873182322e-05,
      "loss": 0.0138,
      "step": 790
    },
    {
      "epoch": 0.3053435114503817,
      "grad_norm": 0.08058780431747437,
      "learning_rate": 4.386992452706499e-05,
      "loss": 0.01,
      "step": 800
    },
    {
      "epoch": 0.30916030534351147,
      "grad_norm": 0.5103694796562195,
      "learning_rate": 4.36497708539222e-05,
      "loss": 0.0127,
      "step": 810
    },
    {
      "epoch": 0.31297709923664124,
      "grad_norm": 0.2476615309715271,
      "learning_rate": 4.342630679033432e-05,
      "loss": 0.0129,
      "step": 820
    },
    {
      "epoch": 0.31679389312977096,
      "grad_norm": 0.2634897530078888,
      "learning_rate": 4.319957200184504e-05,
      "loss": 0.0052,
      "step": 830
    },
    {
      "epoch": 0.32061068702290074,
      "grad_norm": 0.31470030546188354,
      "learning_rate": 4.296960673456159e-05,
      "loss": 0.0165,
      "step": 840
    },
    {
      "epoch": 0.3244274809160305,
      "grad_norm": 0.19848482310771942,
      "learning_rate": 4.273645180801088e-05,
      "loss": 0.005,
      "step": 850
    },
    {
      "epoch": 0.3282442748091603,
      "grad_norm": 0.08697102218866348,
      "learning_rate": 4.2500148607893965e-05,
      "loss": 0.0082,
      "step": 860
    },
    {
      "epoch": 0.3320610687022901,
      "grad_norm": 0.38102781772613525,
      "learning_rate": 4.226073907873992e-05,
      "loss": 0.0126,
      "step": 870
    },
    {
      "epoch": 0.33587786259541985,
      "grad_norm": 0.14514830708503723,
      "learning_rate": 4.201826571646056e-05,
      "loss": 0.0058,
      "step": 880
    },
    {
      "epoch": 0.33969465648854963,
      "grad_norm": 0.43940168619155884,
      "learning_rate": 4.177277156080731e-05,
      "loss": 0.0078,
      "step": 890
    },
    {
      "epoch": 0.3435114503816794,
      "grad_norm": 0.05170935019850731,
      "learning_rate": 4.152430018773153e-05,
      "loss": 0.0082,
      "step": 900
    },
    {
      "epoch": 0.3473282442748092,
      "grad_norm": 0.01292837131768465,
      "learning_rate": 4.127289570164958e-05,
      "loss": 0.0156,
      "step": 910
    },
    {
      "epoch": 0.3511450381679389,
      "grad_norm": 0.21468913555145264,
      "learning_rate": 4.1018602727614264e-05,
      "loss": 0.0075,
      "step": 920
    },
    {
      "epoch": 0.3549618320610687,
      "grad_norm": 0.7786637544631958,
      "learning_rate": 4.0761466403393633e-05,
      "loss": 0.0167,
      "step": 930
    },
    {
      "epoch": 0.35877862595419846,
      "grad_norm": 0.06286737322807312,
      "learning_rate": 4.0501532371458993e-05,
      "loss": 0.0107,
      "step": 940
    },
    {
      "epoch": 0.36259541984732824,
      "grad_norm": 0.19294968247413635,
      "learning_rate": 4.0238846770883165e-05,
      "loss": 0.0103,
      "step": 950
    },
    {
      "epoch": 0.366412213740458,
      "grad_norm": 0.02884821780025959,
      "learning_rate": 3.9973456229150695e-05,
      "loss": 0.0133,
      "step": 960
    },
    {
      "epoch": 0.3702290076335878,
      "grad_norm": 0.36911624670028687,
      "learning_rate": 3.9705407853881324e-05,
      "loss": 0.0072,
      "step": 970
    },
    {
      "epoch": 0.37404580152671757,
      "grad_norm": 0.21048544347286224,
      "learning_rate": 3.9434749224468235e-05,
      "loss": 0.0047,
      "step": 980
    },
    {
      "epoch": 0.37786259541984735,
      "grad_norm": 0.09334168583154678,
      "learning_rate": 3.916152838363258e-05,
      "loss": 0.0125,
      "step": 990
    },
    {
      "epoch": 0.3816793893129771,
      "grad_norm": 0.49426600337028503,
      "learning_rate": 3.8885793828895756e-05,
      "loss": 0.0109,
      "step": 1000
    },
    {
      "epoch": 0.3816793893129771,
      "eval_loss": 0.032893069088459015,
      "eval_runtime": 140.214,
      "eval_samples_per_second": 56.927,
      "eval_steps_per_second": 0.3,
      "step": 1000
    },
    {
      "epoch": 0.38549618320610685,
      "grad_norm": 0.19869565963745117,
      "learning_rate": 3.8607594503970925e-05,
      "loss": 0.0144,
      "step": 1010
    },
    {
      "epoch": 0.3893129770992366,
      "grad_norm": 0.19766545295715332,
      "learning_rate": 3.832697979007539e-05,
      "loss": 0.0067,
      "step": 1020
    },
    {
      "epoch": 0.3931297709923664,
      "grad_norm": 0.4004887044429779,
      "learning_rate": 3.804399949716526e-05,
      "loss": 0.0047,
      "step": 1030
    },
    {
      "epoch": 0.3969465648854962,
      "grad_norm": 0.31220734119415283,
      "learning_rate": 3.775870385509402e-05,
      "loss": 0.0163,
      "step": 1040
    },
    {
      "epoch": 0.40076335877862596,
      "grad_norm": 0.12848161160945892,
      "learning_rate": 3.7471143504696625e-05,
      "loss": 0.0038,
      "step": 1050
    },
    {
      "epoch": 0.40458015267175573,
      "grad_norm": 0.39810845255851746,
      "learning_rate": 3.718136948880056e-05,
      "loss": 0.0077,
      "step": 1060
    },
    {
      "epoch": 0.4083969465648855,
      "grad_norm": 0.47316208481788635,
      "learning_rate": 3.6889433243165605e-05,
      "loss": 0.0141,
      "step": 1070
    },
    {
      "epoch": 0.4122137404580153,
      "grad_norm": 0.028033487498760223,
      "learning_rate": 3.6595386587353795e-05,
      "loss": 0.0049,
      "step": 1080
    },
    {
      "epoch": 0.41603053435114506,
      "grad_norm": 0.036221910268068314,
      "learning_rate": 3.6299281715531375e-05,
      "loss": 0.0083,
      "step": 1090
    },
    {
      "epoch": 0.4198473282442748,
      "grad_norm": 0.013016347773373127,
      "learning_rate": 3.600117118720408e-05,
      "loss": 0.0085,
      "step": 1100
    },
    {
      "epoch": 0.42366412213740456,
      "grad_norm": 0.07040252536535263,
      "learning_rate": 3.57011079178877e-05,
      "loss": 0.0102,
      "step": 1110
    },
    {
      "epoch": 0.42748091603053434,
      "grad_norm": 0.25287893414497375,
      "learning_rate": 3.53991451697155e-05,
      "loss": 0.0092,
      "step": 1120
    },
    {
      "epoch": 0.4312977099236641,
      "grad_norm": 0.08920171856880188,
      "learning_rate": 3.509533654198388e-05,
      "loss": 0.0156,
      "step": 1130
    },
    {
      "epoch": 0.4351145038167939,
      "grad_norm": 0.36695143580436707,
      "learning_rate": 3.478973596163843e-05,
      "loss": 0.0109,
      "step": 1140
    },
    {
      "epoch": 0.4389312977099237,
      "grad_norm": 0.022651812061667442,
      "learning_rate": 3.448239767370177e-05,
      "loss": 0.0057,
      "step": 1150
    },
    {
      "epoch": 0.44274809160305345,
      "grad_norm": 0.3203389644622803,
      "learning_rate": 3.4173376231644797e-05,
      "loss": 0.0075,
      "step": 1160
    },
    {
      "epoch": 0.44656488549618323,
      "grad_norm": 0.6244869232177734,
      "learning_rate": 3.386272648770333e-05,
      "loss": 0.0119,
      "step": 1170
    },
    {
      "epoch": 0.45038167938931295,
      "grad_norm": 0.16917894780635834,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.0065,
      "step": 1180
    },
    {
      "epoch": 0.4541984732824427,
      "grad_norm": 0.10675910860300064,
      "learning_rate": 3.323676293846501e-05,
      "loss": 0.0073,
      "step": 1190
    },
    {
      "epoch": 0.4580152671755725,
      "grad_norm": 0.8430480360984802,
      "learning_rate": 3.2921560243581675e-05,
      "loss": 0.0121,
      "step": 1200
    },
    {
      "epoch": 0.4618320610687023,
      "grad_norm": 0.1763671189546585,
      "learning_rate": 3.260495144791856e-05,
      "loss": 0.0067,
      "step": 1210
    },
    {
      "epoch": 0.46564885496183206,
      "grad_norm": 0.4134056568145752,
      "learning_rate": 3.2286992750489585e-05,
      "loss": 0.0115,
      "step": 1220
    },
    {
      "epoch": 0.46946564885496184,
      "grad_norm": 0.02143966406583786,
      "learning_rate": 3.1967740589920296e-05,
      "loss": 0.0075,
      "step": 1230
    },
    {
      "epoch": 0.4732824427480916,
      "grad_norm": 0.6696872115135193,
      "learning_rate": 3.1647251634429856e-05,
      "loss": 0.0089,
      "step": 1240
    },
    {
      "epoch": 0.4770992366412214,
      "grad_norm": 0.06671352684497833,
      "learning_rate": 3.1325582771772235e-05,
      "loss": 0.0147,
      "step": 1250
    },
    {
      "epoch": 0.48091603053435117,
      "grad_norm": 0.7138830423355103,
      "learning_rate": 3.100279109913848e-05,
      "loss": 0.0121,
      "step": 1260
    },
    {
      "epoch": 0.4847328244274809,
      "grad_norm": 0.15019002556800842,
      "learning_rate": 3.067893391302179e-05,
      "loss": 0.006,
      "step": 1270
    },
    {
      "epoch": 0.48854961832061067,
      "grad_norm": 0.29725247621536255,
      "learning_rate": 3.035406869904721e-05,
      "loss": 0.0123,
      "step": 1280
    },
    {
      "epoch": 0.49236641221374045,
      "grad_norm": 0.2249823957681656,
      "learning_rate": 3.0028253121767762e-05,
      "loss": 0.0092,
      "step": 1290
    },
    {
      "epoch": 0.4961832061068702,
      "grad_norm": 0.1760585904121399,
      "learning_rate": 2.970154501442881e-05,
      "loss": 0.0189,
      "step": 1300
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.32748275995254517,
      "learning_rate": 2.9374002368702514e-05,
      "loss": 0.0106,
      "step": 1310
    },
    {
      "epoch": 0.5038167938931297,
      "grad_norm": 0.5537404417991638,
      "learning_rate": 2.904568332439408e-05,
      "loss": 0.0073,
      "step": 1320
    },
    {
      "epoch": 0.5076335877862596,
      "grad_norm": 0.024763356894254684,
      "learning_rate": 2.8716646159121795e-05,
      "loss": 0.0039,
      "step": 1330
    },
    {
      "epoch": 0.5114503816793893,
      "grad_norm": 0.3292398452758789,
      "learning_rate": 2.8386949277972606e-05,
      "loss": 0.0128,
      "step": 1340
    },
    {
      "epoch": 0.5152671755725191,
      "grad_norm": 0.28704291582107544,
      "learning_rate": 2.805665120313501e-05,
      "loss": 0.0139,
      "step": 1350
    },
    {
      "epoch": 0.5190839694656488,
      "grad_norm": 0.3549763560295105,
      "learning_rate": 2.7725810563511157e-05,
      "loss": 0.007,
      "step": 1360
    },
    {
      "epoch": 0.5229007633587787,
      "grad_norm": 0.10086268186569214,
      "learning_rate": 2.7394486084310128e-05,
      "loss": 0.0063,
      "step": 1370
    },
    {
      "epoch": 0.5267175572519084,
      "grad_norm": 0.30678582191467285,
      "learning_rate": 2.7062736576623943e-05,
      "loss": 0.0092,
      "step": 1380
    },
    {
      "epoch": 0.5305343511450382,
      "grad_norm": 0.20195415616035461,
      "learning_rate": 2.6730620926988476e-05,
      "loss": 0.0094,
      "step": 1390
    },
    {
      "epoch": 0.5343511450381679,
      "grad_norm": 0.7400510907173157,
      "learning_rate": 2.6398198086930915e-05,
      "loss": 0.0183,
      "step": 1400
    },
    {
      "epoch": 0.5381679389312977,
      "grad_norm": 0.10865656286478043,
      "learning_rate": 2.6065527062505634e-05,
      "loss": 0.0109,
      "step": 1410
    },
    {
      "epoch": 0.5419847328244275,
      "grad_norm": 0.1100832000374794,
      "learning_rate": 2.573266690382051e-05,
      "loss": 0.0086,
      "step": 1420
    },
    {
      "epoch": 0.5458015267175572,
      "grad_norm": 0.07376679033041,
      "learning_rate": 2.5399676694555312e-05,
      "loss": 0.0213,
      "step": 1430
    },
    {
      "epoch": 0.549618320610687,
      "grad_norm": 0.30974867939949036,
      "learning_rate": 2.506661554147417e-05,
      "loss": 0.0091,
      "step": 1440
    },
    {
      "epoch": 0.5534351145038168,
      "grad_norm": 0.4819875955581665,
      "learning_rate": 2.473354256393397e-05,
      "loss": 0.0079,
      "step": 1450
    },
    {
      "epoch": 0.5572519083969466,
      "grad_norm": 0.08225909620523453,
      "learning_rate": 2.440051688339046e-05,
      "loss": 0.0147,
      "step": 1460
    },
    {
      "epoch": 0.5610687022900763,
      "grad_norm": 0.009925187565386295,
      "learning_rate": 2.4067597612904037e-05,
      "loss": 0.0135,
      "step": 1470
    },
    {
      "epoch": 0.5648854961832062,
      "grad_norm": 0.36840465664863586,
      "learning_rate": 2.3734843846646988e-05,
      "loss": 0.0128,
      "step": 1480
    },
    {
      "epoch": 0.5687022900763359,
      "grad_norm": 0.0662972629070282,
      "learning_rate": 2.3402314649414116e-05,
      "loss": 0.0114,
      "step": 1490
    },
    {
      "epoch": 0.5725190839694656,
      "grad_norm": 0.28558099269866943,
      "learning_rate": 2.307006904613851e-05,
      "loss": 0.0113,
      "step": 1500
    },
    {
      "epoch": 0.5725190839694656,
      "eval_loss": 0.030398810282349586,
      "eval_runtime": 140.1617,
      "eval_samples_per_second": 56.949,
      "eval_steps_per_second": 0.3,
      "step": 1500
    },
    {
      "epoch": 0.5763358778625954,
      "grad_norm": 0.39870354533195496,
      "learning_rate": 2.2738166011414527e-05,
      "loss": 0.0094,
      "step": 1510
    },
    {
      "epoch": 0.5801526717557252,
      "grad_norm": 0.3758524954319,
      "learning_rate": 2.2406664459029545e-05,
      "loss": 0.0089,
      "step": 1520
    },
    {
      "epoch": 0.583969465648855,
      "grad_norm": 0.028594927862286568,
      "learning_rate": 2.207562323150662e-05,
      "loss": 0.0074,
      "step": 1530
    },
    {
      "epoch": 0.5877862595419847,
      "grad_norm": 0.23170693218708038,
      "learning_rate": 2.174510108965977e-05,
      "loss": 0.0054,
      "step": 1540
    },
    {
      "epoch": 0.5916030534351145,
      "grad_norm": 0.5391947031021118,
      "learning_rate": 2.1415156702163734e-05,
      "loss": 0.0079,
      "step": 1550
    },
    {
      "epoch": 0.5954198473282443,
      "grad_norm": 0.12324138730764389,
      "learning_rate": 2.1085848635140122e-05,
      "loss": 0.0071,
      "step": 1560
    },
    {
      "epoch": 0.5992366412213741,
      "grad_norm": 0.03993413597345352,
      "learning_rate": 2.0757235341761732e-05,
      "loss": 0.008,
      "step": 1570
    },
    {
      "epoch": 0.6030534351145038,
      "grad_norm": 0.32654133439064026,
      "learning_rate": 2.0429375151876978e-05,
      "loss": 0.0094,
      "step": 1580
    },
    {
      "epoch": 0.6068702290076335,
      "grad_norm": 0.012670164927840233,
      "learning_rate": 2.0102326261656114e-05,
      "loss": 0.0086,
      "step": 1590
    },
    {
      "epoch": 0.6106870229007634,
      "grad_norm": 0.22735942900180817,
      "learning_rate": 1.9776146723261265e-05,
      "loss": 0.0146,
      "step": 1600
    },
    {
      "epoch": 0.6145038167938931,
      "grad_norm": 0.5669217109680176,
      "learning_rate": 1.9450894434541994e-05,
      "loss": 0.0181,
      "step": 1610
    },
    {
      "epoch": 0.6183206106870229,
      "grad_norm": 0.09971689432859421,
      "learning_rate": 1.9126627128758256e-05,
      "loss": 0.0034,
      "step": 1620
    },
    {
      "epoch": 0.6221374045801527,
      "grad_norm": 0.11938827484846115,
      "learning_rate": 1.8803402364332573e-05,
      "loss": 0.0128,
      "step": 1630
    },
    {
      "epoch": 0.6259541984732825,
      "grad_norm": 0.47636914253234863,
      "learning_rate": 1.8481277514633243e-05,
      "loss": 0.0115,
      "step": 1640
    },
    {
      "epoch": 0.6297709923664122,
      "grad_norm": 0.3907536566257477,
      "learning_rate": 1.8160309757790384e-05,
      "loss": 0.0076,
      "step": 1650
    },
    {
      "epoch": 0.6335877862595419,
      "grad_norm": 0.2356630116701126,
      "learning_rate": 1.784055606654664e-05,
      "loss": 0.0131,
      "step": 1660
    },
    {
      "epoch": 0.6374045801526718,
      "grad_norm": 0.09361109882593155,
      "learning_rate": 1.752207319814438e-05,
      "loss": 0.007,
      "step": 1670
    },
    {
      "epoch": 0.6412213740458015,
      "grad_norm": 0.3632112145423889,
      "learning_rate": 1.7204917684251086e-05,
      "loss": 0.0096,
      "step": 1680
    },
    {
      "epoch": 0.6450381679389313,
      "grad_norm": 0.44978809356689453,
      "learning_rate": 1.6889145820924797e-05,
      "loss": 0.0136,
      "step": 1690
    },
    {
      "epoch": 0.648854961832061,
      "grad_norm": 0.4278349280357361,
      "learning_rate": 1.6574813658621464e-05,
      "loss": 0.0061,
      "step": 1700
    },
    {
      "epoch": 0.6526717557251909,
      "grad_norm": 0.3191720247268677,
      "learning_rate": 1.6261976992245727e-05,
      "loss": 0.0255,
      "step": 1710
    },
    {
      "epoch": 0.6564885496183206,
      "grad_norm": 0.030014334246516228,
      "learning_rate": 1.5950691351247218e-05,
      "loss": 0.0103,
      "step": 1720
    },
    {
      "epoch": 0.6603053435114504,
      "grad_norm": 0.3003236651420593,
      "learning_rate": 1.5641011989763903e-05,
      "loss": 0.0086,
      "step": 1730
    },
    {
      "epoch": 0.6641221374045801,
      "grad_norm": 0.05489334836602211,
      "learning_rate": 1.5332993876814285e-05,
      "loss": 0.0055,
      "step": 1740
    },
    {
      "epoch": 0.6679389312977099,
      "grad_norm": 0.27562958002090454,
      "learning_rate": 1.5026691686540262e-05,
      "loss": 0.0066,
      "step": 1750
    },
    {
      "epoch": 0.6717557251908397,
      "grad_norm": 0.4876582622528076,
      "learning_rate": 1.472215978850229e-05,
      "loss": 0.0088,
      "step": 1760
    },
    {
      "epoch": 0.6755725190839694,
      "grad_norm": 0.08189146220684052,
      "learning_rate": 1.4419452238028647e-05,
      "loss": 0.0087,
      "step": 1770
    },
    {
      "epoch": 0.6793893129770993,
      "grad_norm": 0.3738853633403778,
      "learning_rate": 1.4118622766620387e-05,
      "loss": 0.0091,
      "step": 1780
    },
    {
      "epoch": 0.683206106870229,
      "grad_norm": 0.2992166578769684,
      "learning_rate": 1.3819724772413929e-05,
      "loss": 0.0206,
      "step": 1790
    },
    {
      "epoch": 0.6870229007633588,
      "grad_norm": 0.6133850812911987,
      "learning_rate": 1.3522811310702634e-05,
      "loss": 0.0112,
      "step": 1800
    },
    {
      "epoch": 0.6908396946564885,
      "grad_norm": 0.25099530816078186,
      "learning_rate": 1.3227935084519385e-05,
      "loss": 0.0092,
      "step": 1810
    },
    {
      "epoch": 0.6946564885496184,
      "grad_norm": 0.4365796744823456,
      "learning_rate": 1.2935148435281643e-05,
      "loss": 0.0194,
      "step": 1820
    },
    {
      "epoch": 0.6984732824427481,
      "grad_norm": 0.5801776051521301,
      "learning_rate": 1.2644503333500673e-05,
      "loss": 0.0078,
      "step": 1830
    },
    {
      "epoch": 0.7022900763358778,
      "grad_norm": 0.0873272716999054,
      "learning_rate": 1.2356051369556593e-05,
      "loss": 0.0059,
      "step": 1840
    },
    {
      "epoch": 0.7061068702290076,
      "grad_norm": 0.03350086137652397,
      "learning_rate": 1.2069843744540999e-05,
      "loss": 0.0063,
      "step": 1850
    },
    {
      "epoch": 0.7099236641221374,
      "grad_norm": 0.33509764075279236,
      "learning_rate": 1.1785931261168537e-05,
      "loss": 0.0056,
      "step": 1860
    },
    {
      "epoch": 0.7137404580152672,
      "grad_norm": 0.12034814059734344,
      "learning_rate": 1.1504364314759311e-05,
      "loss": 0.0073,
      "step": 1870
    },
    {
      "epoch": 0.7175572519083969,
      "grad_norm": 0.5151724815368652,
      "learning_rate": 1.1225192884293578e-05,
      "loss": 0.0099,
      "step": 1880
    },
    {
      "epoch": 0.7213740458015268,
      "grad_norm": 0.32692572474479675,
      "learning_rate": 1.0948466523540296e-05,
      "loss": 0.008,
      "step": 1890
    },
    {
      "epoch": 0.7251908396946565,
      "grad_norm": 0.005217437632381916,
      "learning_rate": 1.0674234352261175e-05,
      "loss": 0.0071,
      "step": 1900
    },
    {
      "epoch": 0.7290076335877863,
      "grad_norm": 0.2179807722568512,
      "learning_rate": 1.0402545047491818e-05,
      "loss": 0.0166,
      "step": 1910
    },
    {
      "epoch": 0.732824427480916,
      "grad_norm": 0.6623926162719727,
      "learning_rate": 1.0133446834901344e-05,
      "loss": 0.0081,
      "step": 1920
    },
    {
      "epoch": 0.7366412213740458,
      "grad_norm": 0.27897024154663086,
      "learning_rate": 9.866987480232218e-06,
      "loss": 0.0109,
      "step": 1930
    },
    {
      "epoch": 0.7404580152671756,
      "grad_norm": 0.026624036952853203,
      "learning_rate": 9.603214280821707e-06,
      "loss": 0.0168,
      "step": 1940
    },
    {
      "epoch": 0.7442748091603053,
      "grad_norm": 0.505171537399292,
      "learning_rate": 9.342174057206402e-06,
      "loss": 0.0055,
      "step": 1950
    },
    {
      "epoch": 0.7480916030534351,
      "grad_norm": 0.5251939296722412,
      "learning_rate": 9.083913144811499e-06,
      "loss": 0.0067,
      "step": 1960
    },
    {
      "epoch": 0.7519083969465649,
      "grad_norm": 0.2802061438560486,
      "learning_rate": 8.828477385726055e-06,
      "loss": 0.0073,
      "step": 1970
    },
    {
      "epoch": 0.7557251908396947,
      "grad_norm": 0.4821580648422241,
      "learning_rate": 8.575912120565956e-06,
      "loss": 0.0077,
      "step": 1980
    },
    {
      "epoch": 0.7595419847328244,
      "grad_norm": 0.16226717829704285,
      "learning_rate": 8.326262180425746e-06,
      "loss": 0.0063,
      "step": 1990
    },
    {
      "epoch": 0.7633587786259542,
      "grad_norm": 0.2521667182445526,
      "learning_rate": 8.079571878921002e-06,
      "loss": 0.0058,
      "step": 2000
    },
    {
      "epoch": 0.7633587786259542,
      "eval_loss": 0.028967689722776413,
      "eval_runtime": 140.2457,
      "eval_samples_per_second": 56.914,
      "eval_steps_per_second": 0.299,
      "step": 2000
    },
    {
      "epoch": 0.767175572519084,
      "grad_norm": 0.40514904260635376,
      "learning_rate": 7.83588500432256e-06,
      "loss": 0.0112,
      "step": 2010
    },
    {
      "epoch": 0.7709923664122137,
      "grad_norm": 1.045690894126892,
      "learning_rate": 7.595244811783944e-06,
      "loss": 0.0058,
      "step": 2020
    },
    {
      "epoch": 0.7748091603053435,
      "grad_norm": 0.5543403625488281,
      "learning_rate": 7.357694015663416e-06,
      "loss": 0.0102,
      "step": 2030
    },
    {
      "epoch": 0.7786259541984732,
      "grad_norm": 0.14902685582637787,
      "learning_rate": 7.123274781942107e-06,
      "loss": 0.0041,
      "step": 2040
    },
    {
      "epoch": 0.7824427480916031,
      "grad_norm": 0.0032010909635573626,
      "learning_rate": 6.892028720739388e-06,
      "loss": 0.0159,
      "step": 2050
    },
    {
      "epoch": 0.7862595419847328,
      "grad_norm": 0.05139963701367378,
      "learning_rate": 6.663996878926943e-06,
      "loss": 0.0064,
      "step": 2060
    },
    {
      "epoch": 0.7900763358778626,
      "grad_norm": 0.3358862102031708,
      "learning_rate": 6.439219732842869e-06,
      "loss": 0.0098,
      "step": 2070
    },
    {
      "epoch": 0.7938931297709924,
      "grad_norm": 0.15072062611579895,
      "learning_rate": 6.217737181106978e-06,
      "loss": 0.0065,
      "step": 2080
    },
    {
      "epoch": 0.7977099236641222,
      "grad_norm": 0.002467066515237093,
      "learning_rate": 5.999588537538639e-06,
      "loss": 0.0037,
      "step": 2090
    },
    {
      "epoch": 0.8015267175572519,
      "grad_norm": 0.034411050379276276,
      "learning_rate": 5.784812524178529e-06,
      "loss": 0.0074,
      "step": 2100
    },
    {
      "epoch": 0.8053435114503816,
      "grad_norm": 0.08725389838218689,
      "learning_rate": 5.573447264415288e-06,
      "loss": 0.0185,
      "step": 2110
    },
    {
      "epoch": 0.8091603053435115,
      "grad_norm": 0.2480231672525406,
      "learning_rate": 5.365530276218531e-06,
      "loss": 0.0071,
      "step": 2120
    },
    {
      "epoch": 0.8129770992366412,
      "grad_norm": 0.5087897181510925,
      "learning_rate": 5.161098465479308e-06,
      "loss": 0.0243,
      "step": 2130
    },
    {
      "epoch": 0.816793893129771,
      "grad_norm": 0.3457648456096649,
      "learning_rate": 4.96018811945918e-06,
      "loss": 0.0073,
      "step": 2140
    },
    {
      "epoch": 0.8206106870229007,
      "grad_norm": 0.39516162872314453,
      "learning_rate": 4.762834900349117e-06,
      "loss": 0.0122,
      "step": 2150
    },
    {
      "epoch": 0.8244274809160306,
      "grad_norm": 0.3586041331291199,
      "learning_rate": 4.56907383893935e-06,
      "loss": 0.0073,
      "step": 2160
    },
    {
      "epoch": 0.8282442748091603,
      "grad_norm": 0.06679055839776993,
      "learning_rate": 4.378939328401338e-06,
      "loss": 0.0052,
      "step": 2170
    },
    {
      "epoch": 0.8320610687022901,
      "grad_norm": 0.40074533224105835,
      "learning_rate": 4.192465118182814e-06,
      "loss": 0.0064,
      "step": 2180
    },
    {
      "epoch": 0.8358778625954199,
      "grad_norm": 0.13426686823368073,
      "learning_rate": 4.0096843080172195e-06,
      "loss": 0.0139,
      "step": 2190
    },
    {
      "epoch": 0.8396946564885496,
      "grad_norm": 0.08818082511425018,
      "learning_rate": 3.8306293420483505e-06,
      "loss": 0.0104,
      "step": 2200
    },
    {
      "epoch": 0.8435114503816794,
      "grad_norm": 0.676325261592865,
      "learning_rate": 3.6553320030714626e-06,
      "loss": 0.0065,
      "step": 2210
    },
    {
      "epoch": 0.8473282442748091,
      "grad_norm": 0.31104177236557007,
      "learning_rate": 3.483823406891701e-06,
      "loss": 0.0074,
      "step": 2220
    },
    {
      "epoch": 0.851145038167939,
      "grad_norm": 0.358847975730896,
      "learning_rate": 3.3161339968009768e-06,
      "loss": 0.0103,
      "step": 2230
    },
    {
      "epoch": 0.8549618320610687,
      "grad_norm": 0.4074176251888275,
      "learning_rate": 3.1522935381741643e-06,
      "loss": 0.0106,
      "step": 2240
    },
    {
      "epoch": 0.8587786259541985,
      "grad_norm": 0.22954821586608887,
      "learning_rate": 2.9923311131856783e-06,
      "loss": 0.0087,
      "step": 2250
    },
    {
      "epoch": 0.8625954198473282,
      "grad_norm": 0.33302852511405945,
      "learning_rate": 2.836275115647294e-06,
      "loss": 0.013,
      "step": 2260
    },
    {
      "epoch": 0.8664122137404581,
      "grad_norm": 0.09198283404111862,
      "learning_rate": 2.6841532459681627e-06,
      "loss": 0.0067,
      "step": 2270
    },
    {
      "epoch": 0.8702290076335878,
      "grad_norm": 0.03521020710468292,
      "learning_rate": 2.5359925062378884e-06,
      "loss": 0.0092,
      "step": 2280
    },
    {
      "epoch": 0.8740458015267175,
      "grad_norm": 0.40850088000297546,
      "learning_rate": 2.3918191954336144e-06,
      "loss": 0.0064,
      "step": 2290
    },
    {
      "epoch": 0.8778625954198473,
      "grad_norm": 0.002618383150547743,
      "learning_rate": 2.2516589047518273e-06,
      "loss": 0.0069,
      "step": 2300
    },
    {
      "epoch": 0.8816793893129771,
      "grad_norm": 0.28037503361701965,
      "learning_rate": 2.1155365130658717e-06,
      "loss": 0.0063,
      "step": 2310
    },
    {
      "epoch": 0.8854961832061069,
      "grad_norm": 0.06269484013319016,
      "learning_rate": 1.9834761825098773e-06,
      "loss": 0.0043,
      "step": 2320
    },
    {
      "epoch": 0.8893129770992366,
      "grad_norm": 0.6617615222930908,
      "learning_rate": 1.8555013541899036e-06,
      "loss": 0.0148,
      "step": 2330
    },
    {
      "epoch": 0.8931297709923665,
      "grad_norm": 0.06300811469554901,
      "learning_rate": 1.7316347440230557e-06,
      "loss": 0.0116,
      "step": 2340
    },
    {
      "epoch": 0.8969465648854962,
      "grad_norm": 0.15155254304409027,
      "learning_rate": 1.61189833870537e-06,
      "loss": 0.0035,
      "step": 2350
    },
    {
      "epoch": 0.9007633587786259,
      "grad_norm": 0.7464874386787415,
      "learning_rate": 1.496313391809076e-06,
      "loss": 0.0131,
      "step": 2360
    },
    {
      "epoch": 0.9045801526717557,
      "grad_norm": 0.7433227896690369,
      "learning_rate": 1.3849004200100546e-06,
      "loss": 0.0084,
      "step": 2370
    },
    {
      "epoch": 0.9083969465648855,
      "grad_norm": 0.4609885513782501,
      "learning_rate": 1.2776791994460553e-06,
      "loss": 0.0091,
      "step": 2380
    },
    {
      "epoch": 0.9122137404580153,
      "grad_norm": 0.03363984078168869,
      "learning_rate": 1.1746687622063573e-06,
      "loss": 0.0109,
      "step": 2390
    },
    {
      "epoch": 0.916030534351145,
      "grad_norm": 0.34646764397621155,
      "learning_rate": 1.0758873929535424e-06,
      "loss": 0.0058,
      "step": 2400
    },
    {
      "epoch": 0.9198473282442748,
      "grad_norm": 0.28582972288131714,
      "learning_rate": 9.813526256778894e-07,
      "loss": 0.0054,
      "step": 2410
    },
    {
      "epoch": 0.9236641221374046,
      "grad_norm": 0.5931139588356018,
      "learning_rate": 8.910812405850566e-07,
      "loss": 0.0118,
      "step": 2420
    },
    {
      "epoch": 0.9274809160305344,
      "grad_norm": 0.44896554946899414,
      "learning_rate": 8.050892611175253e-07,
      "loss": 0.0119,
      "step": 2430
    },
    {
      "epoch": 0.9312977099236641,
      "grad_norm": 0.19585078954696655,
      "learning_rate": 7.233919511104082e-07,
      "loss": 0.0132,
      "step": 2440
    },
    {
      "epoch": 0.9351145038167938,
      "grad_norm": 0.24196402728557587,
      "learning_rate": 6.460038120820688e-07,
      "loss": 0.0051,
      "step": 2450
    },
    {
      "epoch": 0.9389312977099237,
      "grad_norm": 0.2216787487268448,
      "learning_rate": 5.729385806600484e-07,
      "loss": 0.0039,
      "step": 2460
    },
    {
      "epoch": 0.9427480916030534,
      "grad_norm": 0.008937466889619827,
      "learning_rate": 5.042092261427822e-07,
      "loss": 0.0151,
      "step": 2470
    },
    {
      "epoch": 0.9465648854961832,
      "grad_norm": 0.2098822146654129,
      "learning_rate": 4.3982794819751316e-07,
      "loss": 0.0045,
      "step": 2480
    },
    {
      "epoch": 0.950381679389313,
      "grad_norm": 0.09708132594823837,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.0059,
      "step": 2490
    },
    {
      "epoch": 0.9541984732824428,
      "grad_norm": 0.10786189138889313,
      "learning_rate": 3.2415455968004826e-07,
      "loss": 0.0032,
      "step": 2500
    },
    {
      "epoch": 0.9541984732824428,
      "eval_loss": 0.027030499652028084,
      "eval_runtime": 140.2791,
      "eval_samples_per_second": 56.901,
      "eval_steps_per_second": 0.299,
      "step": 2500
    },
    {
      "epoch": 0.9580152671755725,
      "grad_norm": 0.5997936725616455,
      "learning_rate": 2.7288298148238913e-07,
      "loss": 0.0164,
      "step": 2510
    },
    {
      "epoch": 0.9618320610687023,
      "grad_norm": 1.1892848014831543,
      "learning_rate": 2.2600054096122703e-07,
      "loss": 0.0095,
      "step": 2520
    },
    {
      "epoch": 0.9656488549618321,
      "grad_norm": 0.014309865422546864,
      "learning_rate": 1.8351555989082892e-07,
      "loss": 0.006,
      "step": 2530
    },
    {
      "epoch": 0.9694656488549618,
      "grad_norm": 0.23357251286506653,
      "learning_rate": 1.4543557948317744e-07,
      "loss": 0.0084,
      "step": 2540
    },
    {
      "epoch": 0.9732824427480916,
      "grad_norm": 0.4700785279273987,
      "learning_rate": 1.1176735904937508e-07,
      "loss": 0.0079,
      "step": 2550
    },
    {
      "epoch": 0.9770992366412213,
      "grad_norm": 0.005513277370482683,
      "learning_rate": 8.251687479986503e-08,
      "loss": 0.0176,
      "step": 2560
    },
    {
      "epoch": 0.9809160305343512,
      "grad_norm": 0.32526788115501404,
      "learning_rate": 5.768931878361583e-08,
      "loss": 0.0091,
      "step": 2570
    },
    {
      "epoch": 0.9847328244274809,
      "grad_norm": 0.29356321692466736,
      "learning_rate": 3.728909796652525e-08,
      "loss": 0.0022,
      "step": 2580
    },
    {
      "epoch": 0.9885496183206107,
      "grad_norm": 0.03470044955611229,
      "learning_rate": 2.1319833449179317e-08,
      "loss": 0.0055,
      "step": 2590
    },
    {
      "epoch": 0.9923664122137404,
      "grad_norm": 0.004818221088498831,
      "learning_rate": 9.78435982407766e-09,
      "loss": 0.0093,
      "step": 2600
    },
    {
      "epoch": 0.9961832061068703,
      "grad_norm": 0.03156821429729462,
      "learning_rate": 2.6847246725053565e-09,
      "loss": 0.0034,
      "step": 2610
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0063484120182693005,
      "learning_rate": 2.2188201059814007e-11,
      "loss": 0.0075,
      "step": 2620
    }
  ],
  "logging_steps": 10,
  "max_steps": 2620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3731098682179103e+18,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}