{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9988716502115658,
  "eval_steps": 500,
  "global_step": 1772,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 1.1533478871584986,
      "learning_rate": 5e-06,
      "loss": 0.744,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.964708516920586,
      "learning_rate": 5e-06,
      "loss": 0.6804,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.7414689176853874,
      "learning_rate": 5e-06,
      "loss": 0.6629,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.6402562297823468,
      "learning_rate": 5e-06,
      "loss": 0.6403,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.6438158764026781,
      "learning_rate": 5e-06,
      "loss": 0.6334,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.6086347979873902,
      "learning_rate": 5e-06,
      "loss": 0.6331,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.637737303544012,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.6180779913246882,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.7628906889304371,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.6560412532230508,
      "learning_rate": 5e-06,
      "loss": 0.6273,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.5971484737001814,
      "learning_rate": 5e-06,
      "loss": 0.6183,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.62454415866273,
      "learning_rate": 5e-06,
      "loss": 0.6169,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.9358718838187522,
      "learning_rate": 5e-06,
      "loss": 0.6184,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.6707162435124239,
      "learning_rate": 5e-06,
      "loss": 0.6134,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.607779817667474,
      "learning_rate": 5e-06,
      "loss": 0.6135,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.5866694919013473,
      "learning_rate": 5e-06,
      "loss": 0.6163,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.6395663339457631,
      "learning_rate": 5e-06,
      "loss": 0.6124,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.5802311797909204,
      "learning_rate": 5e-06,
      "loss": 0.6086,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.5655529914842923,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.5978170679918469,
      "learning_rate": 5e-06,
      "loss": 0.6094,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.5598729087663762,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.6135515117029436,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.5982246973373736,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.634679350959857,
      "learning_rate": 5e-06,
      "loss": 0.6056,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.5848371303406198,
      "learning_rate": 5e-06,
      "loss": 0.5998,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.7237357300883238,
      "learning_rate": 5e-06,
      "loss": 0.6029,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.5758396058045636,
      "learning_rate": 5e-06,
      "loss": 0.5982,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.551647922547292,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.6070055411621582,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.6071346856787038,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.5694826541205662,
      "learning_rate": 5e-06,
      "loss": 0.5972,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.5219595834784061,
      "learning_rate": 5e-06,
      "loss": 0.6006,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.5425184695486164,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5849183234601607,
      "learning_rate": 5e-06,
      "loss": 0.5956,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.6577639097966262,
      "learning_rate": 5e-06,
      "loss": 0.5968,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.6147316484890941,
      "learning_rate": 5e-06,
      "loss": 0.596,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.5747506292979353,
      "learning_rate": 5e-06,
      "loss": 0.6027,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.5687682085546433,
      "learning_rate": 5e-06,
      "loss": 0.5999,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.616324958523922,
      "learning_rate": 5e-06,
      "loss": 0.5941,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.5900329665323057,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.5841528129448796,
      "learning_rate": 5e-06,
      "loss": 0.5939,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.586906708055177,
      "learning_rate": 5e-06,
      "loss": 0.5944,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.5824744589920343,
      "learning_rate": 5e-06,
      "loss": 0.5887,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.7143042613195987,
      "learning_rate": 5e-06,
      "loss": 0.5935,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.5913009643554688,
      "eval_runtime": 359.8373,
      "eval_samples_per_second": 33.184,
      "eval_steps_per_second": 0.52,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.7349947461827919,
      "learning_rate": 5e-06,
      "loss": 0.6021,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.5967862073767953,
      "learning_rate": 5e-06,
      "loss": 0.528,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.5908248473188383,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.5783595460572618,
      "learning_rate": 5e-06,
      "loss": 0.5306,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.6027833555237775,
      "learning_rate": 5e-06,
      "loss": 0.541,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.5779961111728702,
      "learning_rate": 5e-06,
      "loss": 0.5393,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.609691227257698,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.6288262969758429,
      "learning_rate": 5e-06,
      "loss": 0.5336,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.6441493312512533,
      "learning_rate": 5e-06,
      "loss": 0.5393,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.5801582242360297,
      "learning_rate": 5e-06,
      "loss": 0.5371,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.6407989788015263,
      "learning_rate": 5e-06,
      "loss": 0.5422,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.6145932063398675,
      "learning_rate": 5e-06,
      "loss": 0.5438,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.5894609854660963,
      "learning_rate": 5e-06,
      "loss": 0.5415,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.5712716247350705,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.5545979807457848,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.6116638284685687,
      "learning_rate": 5e-06,
      "loss": 0.5463,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.603741984926436,
      "learning_rate": 5e-06,
      "loss": 0.539,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.5576981790641173,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.5585863324687254,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.6685966084888875,
      "learning_rate": 5e-06,
      "loss": 0.5407,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.563715043671093,
      "learning_rate": 5e-06,
      "loss": 0.5418,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.664496256459769,
      "learning_rate": 5e-06,
      "loss": 0.5456,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.5712447353649974,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5486833946787922,
      "learning_rate": 5e-06,
      "loss": 0.5345,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.6092638196410558,
      "learning_rate": 5e-06,
      "loss": 0.537,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.5716085259389777,
      "learning_rate": 5e-06,
      "loss": 0.5407,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.5372993001292306,
      "learning_rate": 5e-06,
      "loss": 0.5437,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.5950554022209111,
      "learning_rate": 5e-06,
      "loss": 0.5516,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.5644998290854271,
      "learning_rate": 5e-06,
      "loss": 0.5347,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.7194589295267496,
      "learning_rate": 5e-06,
      "loss": 0.5506,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.654147586643372,
      "learning_rate": 5e-06,
      "loss": 0.5424,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5858691889312596,
      "learning_rate": 5e-06,
      "loss": 0.5412,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.6698089700161991,
      "learning_rate": 5e-06,
      "loss": 0.5414,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.5539764143704193,
      "learning_rate": 5e-06,
      "loss": 0.5372,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.5902260571431798,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.6653827196776052,
      "learning_rate": 5e-06,
      "loss": 0.5364,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.5629278214932536,
      "learning_rate": 5e-06,
      "loss": 0.5471,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.716393148987963,
      "learning_rate": 5e-06,
      "loss": 0.5343,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.5869857580731778,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.5932511634770244,
      "learning_rate": 5e-06,
      "loss": 0.5461,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.5548454392387719,
      "learning_rate": 5e-06,
      "loss": 0.5342,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.6292606426061244,
      "learning_rate": 5e-06,
      "loss": 0.5391,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.6964512767642522,
      "learning_rate": 5e-06,
      "loss": 0.5457,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.597052250032102,
      "learning_rate": 5e-06,
      "loss": 0.5435,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5871431231498718,
      "eval_runtime": 359.7238,
      "eval_samples_per_second": 33.195,
      "eval_steps_per_second": 0.52,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 1.0307272915735466,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.7570634539626596,
      "learning_rate": 5e-06,
      "loss": 0.4779,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.7952962689694523,
      "learning_rate": 5e-06,
      "loss": 0.4796,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.6214258578581712,
      "learning_rate": 5e-06,
      "loss": 0.472,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.6061682325391837,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.5893935434044923,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.5983033582412839,
      "learning_rate": 5e-06,
      "loss": 0.4855,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.6061301651629116,
      "learning_rate": 5e-06,
      "loss": 0.482,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.7208585763313551,
      "learning_rate": 5e-06,
      "loss": 0.48,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.6130737469375042,
      "learning_rate": 5e-06,
      "loss": 0.475,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.5687127566641503,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.7034322954282024,
      "learning_rate": 5e-06,
      "loss": 0.4839,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.5935224377076785,
      "learning_rate": 5e-06,
      "loss": 0.4907,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.7990706799966594,
      "learning_rate": 5e-06,
      "loss": 0.485,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.6024785296050031,
      "learning_rate": 5e-06,
      "loss": 0.489,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.6533399713336523,
      "learning_rate": 5e-06,
      "loss": 0.487,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.6341103214680793,
      "learning_rate": 5e-06,
      "loss": 0.4849,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.6145632264645421,
      "learning_rate": 5e-06,
      "loss": 0.4844,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.7153893920420706,
      "learning_rate": 5e-06,
      "loss": 0.4848,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.7079536947244722,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.5750394845236195,
      "learning_rate": 5e-06,
      "loss": 0.4863,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.5940313086667759,
      "learning_rate": 5e-06,
      "loss": 0.4896,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.5915949703706999,
      "learning_rate": 5e-06,
      "loss": 0.4922,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.6599431703449483,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.5987887803366096,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.79487550387113,
      "learning_rate": 5e-06,
      "loss": 0.4871,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.712422302635071,
      "learning_rate": 5e-06,
      "loss": 0.4877,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.6372686005869476,
      "learning_rate": 5e-06,
      "loss": 0.4915,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.6258750499046419,
      "learning_rate": 5e-06,
      "loss": 0.4809,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.6254081356701218,
      "learning_rate": 5e-06,
      "loss": 0.4913,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.5772656389234755,
      "learning_rate": 5e-06,
      "loss": 0.4919,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.5958356234239867,
      "learning_rate": 5e-06,
      "loss": 0.4901,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.5845924683927192,
      "learning_rate": 5e-06,
      "loss": 0.4913,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.5627157674386412,
      "learning_rate": 5e-06,
      "loss": 0.4884,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.5821830745956523,
      "learning_rate": 5e-06,
      "loss": 0.4945,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.6229685304395023,
      "learning_rate": 5e-06,
      "loss": 0.4934,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.5845914499963646,
      "learning_rate": 5e-06,
      "loss": 0.4933,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5574457219985247,
      "learning_rate": 5e-06,
      "loss": 0.495,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5996150224624698,
      "learning_rate": 5e-06,
      "loss": 0.4919,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.5752771355797817,
      "learning_rate": 5e-06,
      "loss": 0.4901,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.6240736677369982,
      "learning_rate": 5e-06,
      "loss": 0.4938,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.614687551114313,
      "learning_rate": 5e-06,
      "loss": 0.4889,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.6546354143056629,
      "learning_rate": 5e-06,
      "loss": 0.493,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.5981369023208123,
      "learning_rate": 5e-06,
      "loss": 0.4899,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.6006776094436646,
      "eval_runtime": 359.5275,
      "eval_samples_per_second": 33.213,
      "eval_steps_per_second": 0.52,
      "step": 1329
    },
    {
      "epoch": 3.0014104372355432,
      "grad_norm": 1.7818284423885802,
      "learning_rate": 5e-06,
      "loss": 0.5325,
      "step": 1330
    },
    {
      "epoch": 3.0239774330042315,
      "grad_norm": 0.7669244086926804,
      "learning_rate": 5e-06,
      "loss": 0.4154,
      "step": 1340
    },
    {
      "epoch": 3.0465444287729198,
      "grad_norm": 0.6707220051250778,
      "learning_rate": 5e-06,
      "loss": 0.4178,
      "step": 1350
    },
    {
      "epoch": 3.069111424541608,
      "grad_norm": 0.6712211926030488,
      "learning_rate": 5e-06,
      "loss": 0.4179,
      "step": 1360
    },
    {
      "epoch": 3.0916784203102963,
      "grad_norm": 0.6852453014581671,
      "learning_rate": 5e-06,
      "loss": 0.4199,
      "step": 1370
    },
    {
      "epoch": 3.1142454160789845,
      "grad_norm": 0.6952511595354455,
      "learning_rate": 5e-06,
      "loss": 0.4172,
      "step": 1380
    },
    {
      "epoch": 3.136812411847673,
      "grad_norm": 0.6739341752053783,
      "learning_rate": 5e-06,
      "loss": 0.4196,
      "step": 1390
    },
    {
      "epoch": 3.159379407616361,
      "grad_norm": 0.6810240432279709,
      "learning_rate": 5e-06,
      "loss": 0.4217,
      "step": 1400
    },
    {
      "epoch": 3.1819464033850493,
      "grad_norm": 0.6451044056426664,
      "learning_rate": 5e-06,
      "loss": 0.4228,
      "step": 1410
    },
    {
      "epoch": 3.2045133991537376,
      "grad_norm": 0.7365176770943456,
      "learning_rate": 5e-06,
      "loss": 0.4264,
      "step": 1420
    },
    {
      "epoch": 3.227080394922426,
      "grad_norm": 0.6889861565739961,
      "learning_rate": 5e-06,
      "loss": 0.4236,
      "step": 1430
    },
    {
      "epoch": 3.249647390691114,
      "grad_norm": 0.6619155809062343,
      "learning_rate": 5e-06,
      "loss": 0.429,
      "step": 1440
    },
    {
      "epoch": 3.272214386459803,
      "grad_norm": 0.6938859033729257,
      "learning_rate": 5e-06,
      "loss": 0.4315,
      "step": 1450
    },
    {
      "epoch": 3.294781382228491,
      "grad_norm": 0.6269637473408832,
      "learning_rate": 5e-06,
      "loss": 0.4311,
      "step": 1460
    },
    {
      "epoch": 3.3173483779971793,
      "grad_norm": 0.6871689545622378,
      "learning_rate": 5e-06,
      "loss": 0.429,
      "step": 1470
    },
    {
      "epoch": 3.3399153737658676,
      "grad_norm": 0.6431121820988837,
      "learning_rate": 5e-06,
      "loss": 0.4268,
      "step": 1480
    },
    {
      "epoch": 3.362482369534556,
      "grad_norm": 0.6227148520808465,
      "learning_rate": 5e-06,
      "loss": 0.4291,
      "step": 1490
    },
    {
      "epoch": 3.385049365303244,
      "grad_norm": 0.6926627432900843,
      "learning_rate": 5e-06,
      "loss": 0.4369,
      "step": 1500
    },
    {
      "epoch": 3.4076163610719323,
      "grad_norm": 0.6753898611704962,
      "learning_rate": 5e-06,
      "loss": 0.4289,
      "step": 1510
    },
    {
      "epoch": 3.4301833568406206,
      "grad_norm": 0.6235946356953773,
      "learning_rate": 5e-06,
      "loss": 0.4285,
      "step": 1520
    },
    {
      "epoch": 3.452750352609309,
      "grad_norm": 0.6452950491570345,
      "learning_rate": 5e-06,
      "loss": 0.4339,
      "step": 1530
    },
    {
      "epoch": 3.475317348377997,
      "grad_norm": 0.6466567653039634,
      "learning_rate": 5e-06,
      "loss": 0.4298,
      "step": 1540
    },
    {
      "epoch": 3.4978843441466854,
      "grad_norm": 0.7157977999949227,
      "learning_rate": 5e-06,
      "loss": 0.4367,
      "step": 1550
    },
    {
      "epoch": 3.5204513399153736,
      "grad_norm": 0.746147622100308,
      "learning_rate": 5e-06,
      "loss": 0.4333,
      "step": 1560
    },
    {
      "epoch": 3.543018335684062,
      "grad_norm": 0.63252883620392,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 1570
    },
    {
      "epoch": 3.56558533145275,
      "grad_norm": 0.645023562996112,
      "learning_rate": 5e-06,
      "loss": 0.4287,
      "step": 1580
    },
    {
      "epoch": 3.5881523272214384,
      "grad_norm": 0.6438099493606649,
      "learning_rate": 5e-06,
      "loss": 0.4288,
      "step": 1590
    },
    {
      "epoch": 3.610719322990127,
      "grad_norm": 0.6919344965122289,
      "learning_rate": 5e-06,
      "loss": 0.4322,
      "step": 1600
    },
    {
      "epoch": 3.6332863187588154,
      "grad_norm": 0.6663827038922323,
      "learning_rate": 5e-06,
      "loss": 0.4353,
      "step": 1610
    },
    {
      "epoch": 3.6558533145275036,
      "grad_norm": 0.6633293647142574,
      "learning_rate": 5e-06,
      "loss": 0.4321,
      "step": 1620
    },
    {
      "epoch": 3.678420310296192,
      "grad_norm": 0.6568725046800021,
      "learning_rate": 5e-06,
      "loss": 0.4352,
      "step": 1630
    },
    {
      "epoch": 3.70098730606488,
      "grad_norm": 0.673099496711102,
      "learning_rate": 5e-06,
      "loss": 0.436,
      "step": 1640
    },
    {
      "epoch": 3.7235543018335684,
      "grad_norm": 0.6438662463205753,
      "learning_rate": 5e-06,
      "loss": 0.4321,
      "step": 1650
    },
    {
      "epoch": 3.7461212976022567,
      "grad_norm": 0.6523537779817469,
      "learning_rate": 5e-06,
      "loss": 0.4308,
      "step": 1660
    },
    {
      "epoch": 3.768688293370945,
      "grad_norm": 0.6785421362215835,
      "learning_rate": 5e-06,
      "loss": 0.4363,
      "step": 1670
    },
    {
      "epoch": 3.791255289139633,
      "grad_norm": 0.6620925087943027,
      "learning_rate": 5e-06,
      "loss": 0.4421,
      "step": 1680
    },
    {
      "epoch": 3.8138222849083214,
      "grad_norm": 0.6148218995999806,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 1690
    },
    {
      "epoch": 3.83638928067701,
      "grad_norm": 0.7122084725034734,
      "learning_rate": 5e-06,
      "loss": 0.431,
      "step": 1700
    },
    {
      "epoch": 3.8589562764456984,
      "grad_norm": 0.6454980786635541,
      "learning_rate": 5e-06,
      "loss": 0.4398,
      "step": 1710
    },
    {
      "epoch": 3.8815232722143866,
      "grad_norm": 0.6274368423659055,
      "learning_rate": 5e-06,
      "loss": 0.4387,
      "step": 1720
    },
    {
      "epoch": 3.904090267983075,
      "grad_norm": 0.6324679361432074,
      "learning_rate": 5e-06,
      "loss": 0.4365,
      "step": 1730
    },
    {
      "epoch": 3.926657263751763,
      "grad_norm": 0.6304335216014254,
      "learning_rate": 5e-06,
      "loss": 0.4373,
      "step": 1740
    },
    {
      "epoch": 3.9492242595204514,
      "grad_norm": 0.6460344821987493,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1750
    },
    {
      "epoch": 3.9717912552891397,
      "grad_norm": 0.6439249065834609,
      "learning_rate": 5e-06,
      "loss": 0.4362,
      "step": 1760
    },
    {
      "epoch": 3.994358251057828,
      "grad_norm": 0.6241101368641281,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 1770
    },
    {
      "epoch": 3.9988716502115658,
      "eval_loss": 0.6362190246582031,
      "eval_runtime": 359.9366,
      "eval_samples_per_second": 33.175,
      "eval_steps_per_second": 0.52,
      "step": 1772
    },
    {
      "epoch": 3.9988716502115658,
      "step": 1772,
      "total_flos": 6752101308825600.0,
      "train_loss": 0.5187085666788351,
      "train_runtime": 82722.7317,
      "train_samples_per_second": 10.97,
      "train_steps_per_second": 0.021
    }
  ],
  "logging_steps": 10,
  "max_steps": 1772,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 6752101308825600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}