{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 1329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 1.0433221663012122,
      "learning_rate": 2e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.639073777016932,
      "learning_rate": 2e-06,
      "loss": 0.6946,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.7202251476961028,
      "learning_rate": 2e-06,
      "loss": 0.6768,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.5648205065727682,
      "learning_rate": 2e-06,
      "loss": 0.6534,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.5663427056948547,
      "learning_rate": 2e-06,
      "loss": 0.6463,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.67219037646702,
      "learning_rate": 2e-06,
      "loss": 0.645,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.7293291103237033,
      "learning_rate": 2e-06,
      "loss": 0.6403,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.606670343583454,
      "learning_rate": 2e-06,
      "loss": 0.6415,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.6106478567461984,
      "learning_rate": 2e-06,
      "loss": 0.6391,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.5978361269381517,
      "learning_rate": 2e-06,
      "loss": 0.6378,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.6028189013253967,
      "learning_rate": 2e-06,
      "loss": 0.6284,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.5602920802184874,
      "learning_rate": 2e-06,
      "loss": 0.6275,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.5696554737179336,
      "learning_rate": 2e-06,
      "loss": 0.6285,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.5519212780094878,
      "learning_rate": 2e-06,
      "loss": 0.6233,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.6226564701139224,
      "learning_rate": 2e-06,
      "loss": 0.6236,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.578414112896948,
      "learning_rate": 2e-06,
      "loss": 0.6256,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.560590468875623,
      "learning_rate": 2e-06,
      "loss": 0.6215,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.6745507126017118,
      "learning_rate": 2e-06,
      "loss": 0.6186,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.5835704643656836,
      "learning_rate": 2e-06,
      "loss": 0.6128,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.6161003379265124,
      "learning_rate": 2e-06,
      "loss": 0.6191,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.5799021600589702,
      "learning_rate": 2e-06,
      "loss": 0.6157,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.5871408137293525,
      "learning_rate": 2e-06,
      "loss": 0.6071,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.5996398856149674,
      "learning_rate": 2e-06,
      "loss": 0.6161,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.6074803105770474,
      "learning_rate": 2e-06,
      "loss": 0.6146,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.7272738061336723,
      "learning_rate": 2e-06,
      "loss": 0.6088,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.5983560142487485,
      "learning_rate": 2e-06,
      "loss": 0.6114,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.6648262565960654,
      "learning_rate": 2e-06,
      "loss": 0.6068,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.6324772460964782,
      "learning_rate": 2e-06,
      "loss": 0.6135,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.6178474259098833,
      "learning_rate": 2e-06,
      "loss": 0.6069,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.5711786782249297,
      "learning_rate": 2e-06,
      "loss": 0.6129,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.6117454052823611,
      "learning_rate": 2e-06,
      "loss": 0.6059,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.5789633241754034,
      "learning_rate": 2e-06,
      "loss": 0.6093,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.6368076201701464,
      "learning_rate": 2e-06,
      "loss": 0.6048,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5973257471695644,
      "learning_rate": 2e-06,
      "loss": 0.604,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.6321021085384568,
      "learning_rate": 2e-06,
      "loss": 0.6053,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.5792324785881149,
      "learning_rate": 2e-06,
      "loss": 0.6044,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.6867314115008993,
      "learning_rate": 2e-06,
      "loss": 0.6114,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.558669606039837,
      "learning_rate": 2e-06,
      "loss": 0.6079,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.6450200232297684,
      "learning_rate": 2e-06,
      "loss": 0.6021,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.6753670485076574,
      "learning_rate": 2e-06,
      "loss": 0.6043,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.5902787885141577,
      "learning_rate": 2e-06,
      "loss": 0.6023,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.5827103227171749,
      "learning_rate": 2e-06,
      "loss": 0.6028,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.6029191976039738,
      "learning_rate": 2e-06,
      "loss": 0.5968,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.5905830019717299,
      "learning_rate": 2e-06,
      "loss": 0.6015,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.5996821522712708,
      "eval_runtime": 684.9534,
      "eval_samples_per_second": 17.433,
      "eval_steps_per_second": 0.546,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.671282012191834,
      "learning_rate": 2e-06,
      "loss": 0.6277,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.6834178089603739,
      "learning_rate": 2e-06,
      "loss": 0.5623,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.6320822783616262,
      "learning_rate": 2e-06,
      "loss": 0.5779,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.5808817902209307,
      "learning_rate": 2e-06,
      "loss": 0.5646,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.6807498912151833,
      "learning_rate": 2e-06,
      "loss": 0.5756,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.6204543058816169,
      "learning_rate": 2e-06,
      "loss": 0.5737,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.608323712679785,
      "learning_rate": 2e-06,
      "loss": 0.5738,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.5687101892765788,
      "learning_rate": 2e-06,
      "loss": 0.5658,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.6565782090611835,
      "learning_rate": 2e-06,
      "loss": 0.5719,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.6428269536950834,
      "learning_rate": 2e-06,
      "loss": 0.5689,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.6421601110374405,
      "learning_rate": 2e-06,
      "loss": 0.5735,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.6529414837889878,
      "learning_rate": 2e-06,
      "loss": 0.5751,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.5728269397244209,
      "learning_rate": 2e-06,
      "loss": 0.572,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.640185700522126,
      "learning_rate": 2e-06,
      "loss": 0.5716,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.5878364991667443,
      "learning_rate": 2e-06,
      "loss": 0.571,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.6364767638632319,
      "learning_rate": 2e-06,
      "loss": 0.577,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.7253155158105068,
      "learning_rate": 2e-06,
      "loss": 0.5689,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.710570920045244,
      "learning_rate": 2e-06,
      "loss": 0.5728,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.6116644852398595,
      "learning_rate": 2e-06,
      "loss": 0.5706,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.6314044719623159,
      "learning_rate": 2e-06,
      "loss": 0.5703,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.6499009761650647,
      "learning_rate": 2e-06,
      "loss": 0.5709,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.7685696771045755,
      "learning_rate": 2e-06,
      "loss": 0.5746,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.6308277603249194,
      "learning_rate": 2e-06,
      "loss": 0.5689,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5855543408676798,
      "learning_rate": 2e-06,
      "loss": 0.5625,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.5709521016211466,
      "learning_rate": 2e-06,
      "loss": 0.565,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.7644912495436733,
      "learning_rate": 2e-06,
      "loss": 0.5688,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.7035366511864779,
      "learning_rate": 2e-06,
      "loss": 0.5715,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.6274660684145352,
      "learning_rate": 2e-06,
      "loss": 0.5798,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.630407739158014,
      "learning_rate": 2e-06,
      "loss": 0.5621,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.5901781184132681,
      "learning_rate": 2e-06,
      "loss": 0.5786,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.5856430561603909,
      "learning_rate": 2e-06,
      "loss": 0.5694,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5866776036558572,
      "learning_rate": 2e-06,
      "loss": 0.568,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.5440635462751863,
      "learning_rate": 2e-06,
      "loss": 0.5683,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.6204370941058647,
      "learning_rate": 2e-06,
      "loss": 0.5641,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.6088853416387051,
      "learning_rate": 2e-06,
      "loss": 0.5678,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.5793505606196339,
      "learning_rate": 2e-06,
      "loss": 0.5623,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.5555970277272924,
      "learning_rate": 2e-06,
      "loss": 0.5731,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.6048979495356702,
      "learning_rate": 2e-06,
      "loss": 0.56,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.5838896165079868,
      "learning_rate": 2e-06,
      "loss": 0.5726,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.5754384308890258,
      "learning_rate": 2e-06,
      "loss": 0.5723,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.5599842869736887,
      "learning_rate": 2e-06,
      "loss": 0.5595,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.5566007585439673,
      "learning_rate": 2e-06,
      "loss": 0.5645,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.7951118636972577,
      "learning_rate": 2e-06,
      "loss": 0.5712,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.5934004439331788,
      "learning_rate": 2e-06,
      "loss": 0.5692,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5890958905220032,
      "eval_runtime": 688.034,
      "eval_samples_per_second": 17.355,
      "eval_steps_per_second": 0.544,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 0.7695589198319107,
      "learning_rate": 2e-06,
      "loss": 0.6066,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.6796467977288019,
      "learning_rate": 2e-06,
      "loss": 0.5346,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.65146361541612,
      "learning_rate": 2e-06,
      "loss": 0.5375,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.6575065498833618,
      "learning_rate": 2e-06,
      "loss": 0.5296,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.7994659883515206,
      "learning_rate": 2e-06,
      "loss": 0.537,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.6137120388880252,
      "learning_rate": 2e-06,
      "loss": 0.5406,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.6636708484460739,
      "learning_rate": 2e-06,
      "loss": 0.5421,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.843780414845656,
      "learning_rate": 2e-06,
      "loss": 0.5381,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.6622661729586036,
      "learning_rate": 2e-06,
      "loss": 0.5349,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.6898447006501295,
      "learning_rate": 2e-06,
      "loss": 0.5289,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.6299762568336674,
      "learning_rate": 2e-06,
      "loss": 0.5283,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.6342698129333159,
      "learning_rate": 2e-06,
      "loss": 0.5384,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.6432736924448,
      "learning_rate": 2e-06,
      "loss": 0.5449,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.6173507327715725,
      "learning_rate": 2e-06,
      "loss": 0.5378,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.6310487279992593,
      "learning_rate": 2e-06,
      "loss": 0.5424,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.6026925405654086,
      "learning_rate": 2e-06,
      "loss": 0.5393,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.6116542499858799,
      "learning_rate": 2e-06,
      "loss": 0.5363,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.6451420945397868,
      "learning_rate": 2e-06,
      "loss": 0.5357,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.609597509176618,
      "learning_rate": 2e-06,
      "loss": 0.5361,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.6626872262901026,
      "learning_rate": 2e-06,
      "loss": 0.5399,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.6013495623209242,
      "learning_rate": 2e-06,
      "loss": 0.538,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.604763595017652,
      "learning_rate": 2e-06,
      "loss": 0.5405,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.6057010342471794,
      "learning_rate": 2e-06,
      "loss": 0.544,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.5928048426766851,
      "learning_rate": 2e-06,
      "loss": 0.5332,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.5709750994328855,
      "learning_rate": 2e-06,
      "loss": 0.5387,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.6097998628451698,
      "learning_rate": 2e-06,
      "loss": 0.5366,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.5983755156717829,
      "learning_rate": 2e-06,
      "loss": 0.5375,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.5842997413765078,
      "learning_rate": 2e-06,
      "loss": 0.5411,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.5975160588760278,
      "learning_rate": 2e-06,
      "loss": 0.5286,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.6326814843118332,
      "learning_rate": 2e-06,
      "loss": 0.5404,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.602325813352809,
      "learning_rate": 2e-06,
      "loss": 0.541,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.6495304579400809,
      "learning_rate": 2e-06,
      "loss": 0.5393,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.5909957246573293,
      "learning_rate": 2e-06,
      "loss": 0.5404,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.561157246980902,
      "learning_rate": 2e-06,
      "loss": 0.5361,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.6258188208462561,
      "learning_rate": 2e-06,
      "loss": 0.5434,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.5675221720117387,
      "learning_rate": 2e-06,
      "loss": 0.5417,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.5798677955738262,
      "learning_rate": 2e-06,
      "loss": 0.5413,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5908574390550375,
      "learning_rate": 2e-06,
      "loss": 0.5431,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5780564726885579,
      "learning_rate": 2e-06,
      "loss": 0.5396,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.5801427165237595,
      "learning_rate": 2e-06,
      "loss": 0.5371,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.5959570249217664,
      "learning_rate": 2e-06,
      "loss": 0.5416,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.5649317364110549,
      "learning_rate": 2e-06,
      "loss": 0.5361,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.6566551599753087,
      "learning_rate": 2e-06,
      "loss": 0.5405,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.588388390450283,
      "learning_rate": 2e-06,
      "loss": 0.5356,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.5875794291496277,
      "eval_runtime": 685.3769,
      "eval_samples_per_second": 17.423,
      "eval_steps_per_second": 0.546,
      "step": 1329
    },
    {
      "epoch": 2.9991537376586743,
      "step": 1329,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.577867094603941,
      "train_runtime": 120642.776,
      "train_samples_per_second": 5.642,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 1329,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}