{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 30,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 0.7641538977622986,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4714,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.05706603452563286,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0194,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.007792987395077944,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0044,
      "step": 30
    },
    {
      "epoch": 0.06666666666666667,
      "eval_loss": 0.004266363102942705,
      "eval_runtime": 215.0719,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.013519592583179474,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0041,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.017202626913785934,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.004,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.009044675156474113,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0039,
      "step": 60
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.003868637140840292,
      "eval_runtime": 214.9966,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 0.007734662853181362,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0039,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.00847636815160513,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0038,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.010983753949403763,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0039,
      "step": 90
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.0037890244275331497,
      "eval_runtime": 215.057,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.232,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.039544351398944855,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0038,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 0.011466417461633682,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0038,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.020617613568902016,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0038,
      "step": 120
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.0038526125717908144,
      "eval_runtime": 214.983,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 0.233,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 0.012847725301980972,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0038,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.02477414160966873,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0038,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.014771663583815098,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0038,
      "step": 150
    },
    {
      "epoch": 0.3333333333333333,
      "eval_loss": 0.003661703085526824,
      "eval_runtime": 215.005,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.017922697588801384,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0037,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 0.033902786672115326,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0036,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.020672762766480446,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0036,
      "step": 180
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.0034463535994291306,
      "eval_runtime": 215.0519,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 0.021494735032320023,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0035,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.03562169522047043,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0032,
      "step": 200
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 0.014103920198976994,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0034,
      "step": 210
    },
    {
      "epoch": 0.4666666666666667,
      "eval_loss": 0.003306599799543619,
      "eval_runtime": 215.0517,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 210
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.019676154479384422,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0032,
      "step": 220
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 0.011821040883660316,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0034,
      "step": 230
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.010281533934175968,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0028,
      "step": 240
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.0027289013378322124,
      "eval_runtime": 215.069,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 240
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.0231550931930542,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0028,
      "step": 250
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.02239130064845085,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0029,
      "step": 260
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.022564468905329704,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0026,
      "step": 270
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.002367404056712985,
      "eval_runtime": 215.0087,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 270
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.01638098619878292,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0024,
      "step": 280
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 0.03278963640332222,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0024,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.03586648404598236,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0022,
      "step": 300
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.002185327000916004,
      "eval_runtime": 215.0432,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.233,
      "step": 300
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 0.018881576135754585,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0022,
      "step": 310
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.062055736780166626,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0019,
      "step": 320
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 0.02213781699538231,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0025,
      "step": 330
    },
    {
      "epoch": 0.7333333333333333,
      "eval_loss": 0.002024175366386771,
      "eval_runtime": 215.0776,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 330
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.030647626146674156,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0021,
      "step": 340
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.02288457192480564,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.002,
      "step": 350
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.021721992641687393,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0019,
      "step": 360
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0019156673224642873,
      "eval_runtime": 215.0243,
      "eval_samples_per_second": 9.301,
      "eval_steps_per_second": 0.233,
      "step": 360
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 0.028448602184653282,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0018,
      "step": 370
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.017557110637426376,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0018,
      "step": 380
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 0.026540469378232956,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0021,
      "step": 390
    },
    {
      "epoch": 0.8666666666666667,
      "eval_loss": 0.0018348968587815762,
      "eval_runtime": 214.9922,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 0.233,
      "step": 390
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.015121403150260448,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0016,
      "step": 400
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 0.035505831241607666,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0016,
      "step": 410
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.0437658354640007,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0017,
      "step": 420
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.001731859752908349,
      "eval_runtime": 215.067,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 420
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 0.02948390692472458,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0018,
      "step": 430
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.031176254153251648,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0017,
      "step": 440
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.020768124610185623,
      "learning_rate": 5e-05,
      "loss": 0.0017,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.0017366266110911965,
      "eval_runtime": 215.0611,
      "eval_samples_per_second": 9.3,
      "eval_steps_per_second": 0.232,
      "step": 450
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.01959955506026745,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0016,
      "step": 460
    },
    {
      "epoch": 1.0444444444444445,
      "grad_norm": 0.028036223724484444,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0017,
      "step": 470
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.017765428870916367,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0017,
      "step": 480
    },
    {
      "epoch": 1.0666666666666667,
      "eval_loss": 0.0016992929158732295,
      "eval_runtime": 215.0184,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 480
    },
    {
      "epoch": 1.0888888888888888,
      "grad_norm": 0.023638742044568062,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0017,
      "step": 490
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.042691878974437714,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0017,
      "step": 500
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 0.02193632535636425,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0015,
      "step": 510
    },
    {
      "epoch": 1.1333333333333333,
      "eval_loss": 0.0016052849823608994,
      "eval_runtime": 215.0768,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 0.232,
      "step": 510
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.02485978789627552,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0014,
      "step": 520
    },
    {
      "epoch": 1.1777777777777778,
      "grad_norm": 0.031728435307741165,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0017,
      "step": 530
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.014328447170555592,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0015,
      "step": 540
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.001597618917003274,
      "eval_runtime": 215.0417,
      "eval_samples_per_second": 9.301,
      "eval_steps_per_second": 0.233,
      "step": 540
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.03361846134066582,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0014,
      "step": 550
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.025456570088863373,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0013,
      "step": 560
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 0.022314872592687607,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0014,
      "step": 570
    },
    {
      "epoch": 1.2666666666666666,
      "eval_loss": 0.0015569779789075255,
      "eval_runtime": 215.007,
      "eval_samples_per_second": 9.302,
      "eval_steps_per_second": 0.233,
      "step": 570
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 0.023371824994683266,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0013,
      "step": 580
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 0.05439267307519913,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0017,
      "step": 590
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.024191023781895638,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0017,
      "step": 600
    },
    {
      "epoch": 1.3333333333333333,
      "eval_loss": 0.001447125687263906,
      "eval_runtime": 214.3438,
      "eval_samples_per_second": 9.331,
      "eval_steps_per_second": 0.233,
      "step": 600
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 0.028389817103743553,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0015,
      "step": 610
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 0.02619648166000843,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0015,
      "step": 620
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.03590937331318855,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0014,
      "step": 630
    },
    {
      "epoch": 1.4,
      "eval_loss": 0.0013506748946383595,
      "eval_runtime": 214.2897,
      "eval_samples_per_second": 9.333,
      "eval_steps_per_second": 0.233,
      "step": 630
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.017976148054003716,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0012,
      "step": 640
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.020171979442238808,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0013,
      "step": 650
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.02652370184659958,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0012,
      "step": 660
    },
    {
      "epoch": 1.4666666666666668,
      "eval_loss": 0.001308620790950954,
      "eval_runtime": 214.5085,
      "eval_samples_per_second": 9.324,
      "eval_steps_per_second": 0.233,
      "step": 660
    },
    {
      "epoch": 1.488888888888889,
      "grad_norm": 0.03529377654194832,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.001,
      "step": 670
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.024932963773608208,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0014,
      "step": 680
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.033637382090091705,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0012,
      "step": 690
    },
    {
      "epoch": 1.5333333333333332,
      "eval_loss": 0.001253950409591198,
      "eval_runtime": 214.564,
      "eval_samples_per_second": 9.321,
      "eval_steps_per_second": 0.233,
      "step": 690
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.02963503636419773,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0014,
      "step": 700
    },
    {
      "epoch": 1.5777777777777777,
      "grad_norm": 0.03318825364112854,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0013,
      "step": 710
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.03878423571586609,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0012,
      "step": 720
    },
    {
      "epoch": 1.6,
      "eval_loss": 0.0012294509215280414,
      "eval_runtime": 214.5656,
      "eval_samples_per_second": 9.321,
      "eval_steps_per_second": 0.233,
      "step": 720
    },
    {
      "epoch": 1.6222222222222222,
      "grad_norm": 0.024266881868243217,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0011,
      "step": 730
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 0.0440036915242672,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.001,
      "step": 740
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.06052534282207489,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0011,
      "step": 750
    },
    {
      "epoch": 1.6666666666666665,
      "eval_loss": 0.001226729596965015,
      "eval_runtime": 214.5149,
      "eval_samples_per_second": 9.323,
      "eval_steps_per_second": 0.233,
      "step": 750
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.09705264121294022,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0013,
      "step": 760
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.04110162332653999,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.001,
      "step": 770
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.024598602205514908,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0009,
      "step": 780
    },
    {
      "epoch": 1.7333333333333334,
      "eval_loss": 0.0011484515853226185,
      "eval_runtime": 214.5902,
      "eval_samples_per_second": 9.32,
      "eval_steps_per_second": 0.233,
      "step": 780
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.03334140032529831,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0011,
      "step": 790
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.04029354080557823,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0011,
      "step": 800
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.03721322864294052,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0012,
      "step": 810
    },
    {
      "epoch": 1.8,
      "eval_loss": 0.0011356236645951867,
      "eval_runtime": 214.4957,
      "eval_samples_per_second": 9.324,
      "eval_steps_per_second": 0.233,
      "step": 810
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 0.03811410814523697,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0014,
      "step": 820
    },
    {
      "epoch": 1.8444444444444446,
      "grad_norm": 0.03319837152957916,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0011,
      "step": 830
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.04190688952803612,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0012,
      "step": 840
    },
    {
      "epoch": 1.8666666666666667,
      "eval_loss": 0.0011292207054793835,
      "eval_runtime": 214.5416,
      "eval_samples_per_second": 9.322,
      "eval_steps_per_second": 0.233,
      "step": 840
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.02963530644774437,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.001,
      "step": 850
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 0.03373124450445175,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0012,
      "step": 860
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 0.03655708208680153,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0012,
      "step": 870
    },
    {
      "epoch": 1.9333333333333333,
      "eval_loss": 0.0011296386364847422,
      "eval_runtime": 214.4559,
      "eval_samples_per_second": 9.326,
      "eval_steps_per_second": 0.233,
      "step": 870
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.0480160191655159,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.001,
      "step": 880
    },
    {
      "epoch": 1.9777777777777779,
      "grad_norm": 0.03997540473937988,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.001,
      "step": 890
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.038164664059877396,
      "learning_rate": 0.0,
      "loss": 0.001,
      "step": 900
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.001129699987359345,
      "eval_runtime": 214.5889,
      "eval_samples_per_second": 9.32,
      "eval_steps_per_second": 0.233,
      "step": 900
    },
    {
      "epoch": 2.0,
      "step": 900,
      "total_flos": 3.320673433989153e+18,
      "train_loss": 0.00749445440661576,
      "train_runtime": 18806.7916,
      "train_samples_per_second": 1.914,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 10,
  "max_steps": 900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.320673433989153e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}