{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.937007874015748,
  "eval_steps": 50,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03937007874015748,
      "grad_norm": 6.53125,
      "learning_rate": 4.982283464566929e-05,
      "loss": 1.8746,
      "step": 10
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 7.3125,
      "learning_rate": 4.96259842519685e-05,
      "loss": 1.3375,
      "step": 20
    },
    {
      "epoch": 0.11811023622047244,
      "grad_norm": 4.625,
      "learning_rate": 4.9429133858267716e-05,
      "loss": 1.0609,
      "step": 30
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 3.5625,
      "learning_rate": 4.923228346456693e-05,
      "loss": 0.5504,
      "step": 40
    },
    {
      "epoch": 0.1968503937007874,
      "grad_norm": 6.90625,
      "learning_rate": 4.903543307086614e-05,
      "loss": 0.643,
      "step": 50
    },
    {
      "epoch": 0.1968503937007874,
      "eval_loss": 0.699931800365448,
      "eval_runtime": 390.1328,
      "eval_samples_per_second": 0.323,
      "eval_steps_per_second": 0.041,
      "step": 50
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 5.3125,
      "learning_rate": 4.8838582677165356e-05,
      "loss": 0.6455,
      "step": 60
    },
    {
      "epoch": 0.2755905511811024,
      "grad_norm": 5.75,
      "learning_rate": 4.864173228346457e-05,
      "loss": 0.702,
      "step": 70
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 6.3125,
      "learning_rate": 4.844488188976378e-05,
      "loss": 0.7064,
      "step": 80
    },
    {
      "epoch": 0.3543307086614173,
      "grad_norm": 5.46875,
      "learning_rate": 4.8248031496063e-05,
      "loss": 0.6121,
      "step": 90
    },
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 14.6875,
      "learning_rate": 4.805118110236221e-05,
      "loss": 0.5825,
      "step": 100
    },
    {
      "epoch": 0.3937007874015748,
      "eval_loss": 0.5567026138305664,
      "eval_runtime": 392.9728,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 100
    },
    {
      "epoch": 0.4330708661417323,
      "grad_norm": 6.9375,
      "learning_rate": 4.7854330708661424e-05,
      "loss": 0.698,
      "step": 110
    },
    {
      "epoch": 0.47244094488188976,
      "grad_norm": 17.0,
      "learning_rate": 4.765748031496064e-05,
      "loss": 0.6193,
      "step": 120
    },
    {
      "epoch": 0.5118110236220472,
      "grad_norm": 8.8125,
      "learning_rate": 4.7460629921259844e-05,
      "loss": 0.4977,
      "step": 130
    },
    {
      "epoch": 0.5511811023622047,
      "grad_norm": 2.03125,
      "learning_rate": 4.726377952755906e-05,
      "loss": 0.5993,
      "step": 140
    },
    {
      "epoch": 0.5905511811023622,
      "grad_norm": 6.03125,
      "learning_rate": 4.7066929133858264e-05,
      "loss": 0.6029,
      "step": 150
    },
    {
      "epoch": 0.5905511811023622,
      "eval_loss": 0.4967447817325592,
      "eval_runtime": 392.5501,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 150
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 4.90625,
      "learning_rate": 4.687007874015748e-05,
      "loss": 0.491,
      "step": 160
    },
    {
      "epoch": 0.6692913385826772,
      "grad_norm": 2.78125,
      "learning_rate": 4.667322834645669e-05,
      "loss": 0.4837,
      "step": 170
    },
    {
      "epoch": 0.7086614173228346,
      "grad_norm": 3.375,
      "learning_rate": 4.6476377952755905e-05,
      "loss": 0.4797,
      "step": 180
    },
    {
      "epoch": 0.7480314960629921,
      "grad_norm": 2.375,
      "learning_rate": 4.627952755905512e-05,
      "loss": 0.3365,
      "step": 190
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 4.75,
      "learning_rate": 4.608267716535433e-05,
      "loss": 0.4249,
      "step": 200
    },
    {
      "epoch": 0.7874015748031497,
      "eval_loss": 0.440073162317276,
      "eval_runtime": 392.0517,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 200
    },
    {
      "epoch": 0.8267716535433071,
      "grad_norm": 2.375,
      "learning_rate": 4.5885826771653545e-05,
      "loss": 0.3682,
      "step": 210
    },
    {
      "epoch": 0.8661417322834646,
      "grad_norm": 3.484375,
      "learning_rate": 4.568897637795276e-05,
      "loss": 0.3686,
      "step": 220
    },
    {
      "epoch": 0.905511811023622,
      "grad_norm": 7.0,
      "learning_rate": 4.549212598425197e-05,
      "loss": 0.4809,
      "step": 230
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 4.25,
      "learning_rate": 4.5295275590551186e-05,
      "loss": 0.3912,
      "step": 240
    },
    {
      "epoch": 0.984251968503937,
      "grad_norm": 5.875,
      "learning_rate": 4.50984251968504e-05,
      "loss": 0.4155,
      "step": 250
    },
    {
      "epoch": 0.984251968503937,
      "eval_loss": 0.3927951455116272,
      "eval_runtime": 392.2278,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 250
    },
    {
      "epoch": 1.0236220472440944,
      "grad_norm": 1.3828125,
      "learning_rate": 4.490157480314961e-05,
      "loss": 0.5424,
      "step": 260
    },
    {
      "epoch": 1.0629921259842519,
      "grad_norm": 3.9375,
      "learning_rate": 4.470472440944882e-05,
      "loss": 0.263,
      "step": 270
    },
    {
      "epoch": 1.1023622047244095,
      "grad_norm": 6.84375,
      "learning_rate": 4.450787401574803e-05,
      "loss": 0.3224,
      "step": 280
    },
    {
      "epoch": 1.141732283464567,
      "grad_norm": 4.15625,
      "learning_rate": 4.431102362204725e-05,
      "loss": 0.2446,
      "step": 290
    },
    {
      "epoch": 1.1811023622047245,
      "grad_norm": 2.8125,
      "learning_rate": 4.411417322834646e-05,
      "loss": 0.3062,
      "step": 300
    },
    {
      "epoch": 1.1811023622047245,
      "eval_loss": 0.3687995970249176,
      "eval_runtime": 391.3589,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 300
    },
    {
      "epoch": 1.220472440944882,
      "grad_norm": 4.84375,
      "learning_rate": 4.391732283464567e-05,
      "loss": 0.3115,
      "step": 310
    },
    {
      "epoch": 1.2598425196850394,
      "grad_norm": 4.25,
      "learning_rate": 4.372047244094488e-05,
      "loss": 0.3673,
      "step": 320
    },
    {
      "epoch": 1.2992125984251968,
      "grad_norm": 3.140625,
      "learning_rate": 4.3523622047244094e-05,
      "loss": 0.3222,
      "step": 330
    },
    {
      "epoch": 1.3385826771653544,
      "grad_norm": 5.6875,
      "learning_rate": 4.332677165354331e-05,
      "loss": 0.3801,
      "step": 340
    },
    {
      "epoch": 1.3779527559055118,
      "grad_norm": 2.546875,
      "learning_rate": 4.312992125984252e-05,
      "loss": 0.2251,
      "step": 350
    },
    {
      "epoch": 1.3779527559055118,
      "eval_loss": 0.3665054440498352,
      "eval_runtime": 391.3902,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 350
    },
    {
      "epoch": 1.4173228346456692,
      "grad_norm": 2.03125,
      "learning_rate": 4.2933070866141735e-05,
      "loss": 0.2679,
      "step": 360
    },
    {
      "epoch": 1.4566929133858268,
      "grad_norm": 1.328125,
      "learning_rate": 4.273622047244095e-05,
      "loss": 0.2813,
      "step": 370
    },
    {
      "epoch": 1.4960629921259843,
      "grad_norm": 1.390625,
      "learning_rate": 4.253937007874016e-05,
      "loss": 0.2844,
      "step": 380
    },
    {
      "epoch": 1.5354330708661417,
      "grad_norm": 5.65625,
      "learning_rate": 4.2342519685039375e-05,
      "loss": 0.3505,
      "step": 390
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 1.09375,
      "learning_rate": 4.214566929133858e-05,
      "loss": 0.3531,
      "step": 400
    },
    {
      "epoch": 1.574803149606299,
      "eval_loss": 0.3396887481212616,
      "eval_runtime": 391.3612,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 400
    },
    {
      "epoch": 1.6141732283464567,
      "grad_norm": 3.078125,
      "learning_rate": 4.1948818897637795e-05,
      "loss": 0.2256,
      "step": 410
    },
    {
      "epoch": 1.6535433070866141,
      "grad_norm": 3.203125,
      "learning_rate": 4.175196850393701e-05,
      "loss": 0.2727,
      "step": 420
    },
    {
      "epoch": 1.6929133858267718,
      "grad_norm": 0.96875,
      "learning_rate": 4.155511811023622e-05,
      "loss": 0.2102,
      "step": 430
    },
    {
      "epoch": 1.7322834645669292,
      "grad_norm": 1.703125,
      "learning_rate": 4.1358267716535436e-05,
      "loss": 0.2144,
      "step": 440
    },
    {
      "epoch": 1.7716535433070866,
      "grad_norm": 3.6875,
      "learning_rate": 4.116141732283465e-05,
      "loss": 0.292,
      "step": 450
    },
    {
      "epoch": 1.7716535433070866,
      "eval_loss": 0.328838050365448,
      "eval_runtime": 391.3656,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 450
    },
    {
      "epoch": 1.811023622047244,
      "grad_norm": 3.15625,
      "learning_rate": 4.096456692913386e-05,
      "loss": 0.1833,
      "step": 460
    },
    {
      "epoch": 1.8503937007874016,
      "grad_norm": 2.890625,
      "learning_rate": 4.076771653543307e-05,
      "loss": 0.3426,
      "step": 470
    },
    {
      "epoch": 1.889763779527559,
      "grad_norm": 2.203125,
      "learning_rate": 4.057086614173228e-05,
      "loss": 0.2083,
      "step": 480
    },
    {
      "epoch": 1.9291338582677167,
      "grad_norm": 2.578125,
      "learning_rate": 4.03740157480315e-05,
      "loss": 0.2044,
      "step": 490
    },
    {
      "epoch": 1.968503937007874,
      "grad_norm": 1.078125,
      "learning_rate": 4.017716535433071e-05,
      "loss": 0.2456,
      "step": 500
    },
    {
      "epoch": 1.968503937007874,
      "eval_loss": 0.3150576651096344,
      "eval_runtime": 391.6407,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 500
    },
    {
      "epoch": 2.0078740157480315,
      "grad_norm": 1.2265625,
      "learning_rate": 3.9980314960629924e-05,
      "loss": 0.1765,
      "step": 510
    },
    {
      "epoch": 2.047244094488189,
      "grad_norm": 2.40625,
      "learning_rate": 3.978346456692914e-05,
      "loss": 0.2012,
      "step": 520
    },
    {
      "epoch": 2.0866141732283463,
      "grad_norm": 2.03125,
      "learning_rate": 3.958661417322835e-05,
      "loss": 0.1815,
      "step": 530
    },
    {
      "epoch": 2.1259842519685037,
      "grad_norm": 1.75,
      "learning_rate": 3.938976377952756e-05,
      "loss": 0.1611,
      "step": 540
    },
    {
      "epoch": 2.1653543307086616,
      "grad_norm": 5.25,
      "learning_rate": 3.919291338582677e-05,
      "loss": 0.1983,
      "step": 550
    },
    {
      "epoch": 2.1653543307086616,
      "eval_loss": 0.328311026096344,
      "eval_runtime": 391.8457,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 550
    },
    {
      "epoch": 2.204724409448819,
      "grad_norm": 3.796875,
      "learning_rate": 3.8996062992125985e-05,
      "loss": 0.1401,
      "step": 560
    },
    {
      "epoch": 2.2440944881889764,
      "grad_norm": 2.765625,
      "learning_rate": 3.87992125984252e-05,
      "loss": 0.1833,
      "step": 570
    },
    {
      "epoch": 2.283464566929134,
      "grad_norm": 5.875,
      "learning_rate": 3.860236220472441e-05,
      "loss": 0.15,
      "step": 580
    },
    {
      "epoch": 2.322834645669291,
      "grad_norm": 4.75,
      "learning_rate": 3.8405511811023625e-05,
      "loss": 0.1264,
      "step": 590
    },
    {
      "epoch": 2.362204724409449,
      "grad_norm": 4.59375,
      "learning_rate": 3.820866141732284e-05,
      "loss": 0.1442,
      "step": 600
    },
    {
      "epoch": 2.362204724409449,
      "eval_loss": 0.3593440055847168,
      "eval_runtime": 391.6698,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 600
    },
    {
      "epoch": 2.4015748031496065,
      "grad_norm": 7.3125,
      "learning_rate": 3.801181102362205e-05,
      "loss": 0.2459,
      "step": 610
    },
    {
      "epoch": 2.440944881889764,
      "grad_norm": 3.0,
      "learning_rate": 3.7814960629921266e-05,
      "loss": 0.3254,
      "step": 620
    },
    {
      "epoch": 2.4803149606299213,
      "grad_norm": 1.0703125,
      "learning_rate": 3.761811023622047e-05,
      "loss": 0.1388,
      "step": 630
    },
    {
      "epoch": 2.5196850393700787,
      "grad_norm": 3.234375,
      "learning_rate": 3.7421259842519686e-05,
      "loss": 0.2223,
      "step": 640
    },
    {
      "epoch": 2.559055118110236,
      "grad_norm": 4.3125,
      "learning_rate": 3.72244094488189e-05,
      "loss": 0.1785,
      "step": 650
    },
    {
      "epoch": 2.559055118110236,
      "eval_loss": 0.3212270438671112,
      "eval_runtime": 391.2961,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 650
    },
    {
      "epoch": 2.5984251968503935,
      "grad_norm": 2.5,
      "learning_rate": 3.702755905511811e-05,
      "loss": 0.1669,
      "step": 660
    },
    {
      "epoch": 2.637795275590551,
      "grad_norm": 4.375,
      "learning_rate": 3.683070866141733e-05,
      "loss": 0.1427,
      "step": 670
    },
    {
      "epoch": 2.677165354330709,
      "grad_norm": 1.4140625,
      "learning_rate": 3.6633858267716534e-05,
      "loss": 0.0923,
      "step": 680
    },
    {
      "epoch": 2.716535433070866,
      "grad_norm": 9.9375,
      "learning_rate": 3.643700787401575e-05,
      "loss": 0.173,
      "step": 690
    },
    {
      "epoch": 2.7559055118110236,
      "grad_norm": 1.046875,
      "learning_rate": 3.624015748031496e-05,
      "loss": 0.1616,
      "step": 700
    },
    {
      "epoch": 2.7559055118110236,
      "eval_loss": 0.3147011399269104,
      "eval_runtime": 392.1825,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 700
    },
    {
      "epoch": 2.795275590551181,
      "grad_norm": 1.8203125,
      "learning_rate": 3.6043307086614174e-05,
      "loss": 0.1383,
      "step": 710
    },
    {
      "epoch": 2.8346456692913384,
      "grad_norm": 1.2578125,
      "learning_rate": 3.584645669291339e-05,
      "loss": 0.1297,
      "step": 720
    },
    {
      "epoch": 2.8740157480314963,
      "grad_norm": 1.28125,
      "learning_rate": 3.56496062992126e-05,
      "loss": 0.1964,
      "step": 730
    },
    {
      "epoch": 2.9133858267716537,
      "grad_norm": 2.828125,
      "learning_rate": 3.5452755905511815e-05,
      "loss": 0.1198,
      "step": 740
    },
    {
      "epoch": 2.952755905511811,
      "grad_norm": 2.140625,
      "learning_rate": 3.525590551181103e-05,
      "loss": 0.1465,
      "step": 750
    },
    {
      "epoch": 2.952755905511811,
      "eval_loss": 0.307710200548172,
      "eval_runtime": 391.3214,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 750
    },
    {
      "epoch": 2.9921259842519685,
      "grad_norm": 2.9375,
      "learning_rate": 3.505905511811024e-05,
      "loss": 0.1428,
      "step": 760
    },
    {
      "epoch": 3.031496062992126,
      "grad_norm": 3.515625,
      "learning_rate": 3.4862204724409455e-05,
      "loss": 0.1267,
      "step": 770
    },
    {
      "epoch": 3.0708661417322833,
      "grad_norm": 2.03125,
      "learning_rate": 3.466535433070866e-05,
      "loss": 0.1742,
      "step": 780
    },
    {
      "epoch": 3.1102362204724407,
      "grad_norm": 1.8828125,
      "learning_rate": 3.4468503937007875e-05,
      "loss": 0.0641,
      "step": 790
    },
    {
      "epoch": 3.1496062992125986,
      "grad_norm": 2.328125,
      "learning_rate": 3.427165354330709e-05,
      "loss": 0.1361,
      "step": 800
    },
    {
      "epoch": 3.1496062992125986,
      "eval_loss": 0.3324497640132904,
      "eval_runtime": 392.3287,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 800
    },
    {
      "epoch": 3.188976377952756,
      "grad_norm": 0.353515625,
      "learning_rate": 3.40748031496063e-05,
      "loss": 0.1086,
      "step": 810
    },
    {
      "epoch": 3.2283464566929134,
      "grad_norm": 3.359375,
      "learning_rate": 3.387795275590551e-05,
      "loss": 0.1085,
      "step": 820
    },
    {
      "epoch": 3.267716535433071,
      "grad_norm": 2.375,
      "learning_rate": 3.368110236220472e-05,
      "loss": 0.1379,
      "step": 830
    },
    {
      "epoch": 3.3070866141732282,
      "grad_norm": 1.140625,
      "learning_rate": 3.3484251968503936e-05,
      "loss": 0.0975,
      "step": 840
    },
    {
      "epoch": 3.3464566929133857,
      "grad_norm": 3.609375,
      "learning_rate": 3.328740157480315e-05,
      "loss": 0.1394,
      "step": 850
    },
    {
      "epoch": 3.3464566929133857,
      "eval_loss": 0.3458271324634552,
      "eval_runtime": 391.2978,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 850
    },
    {
      "epoch": 3.3858267716535435,
      "grad_norm": 4.0625,
      "learning_rate": 3.309055118110236e-05,
      "loss": 0.1068,
      "step": 860
    },
    {
      "epoch": 3.425196850393701,
      "grad_norm": 0.3125,
      "learning_rate": 3.289370078740158e-05,
      "loss": 0.1289,
      "step": 870
    },
    {
      "epoch": 3.4645669291338583,
      "grad_norm": 2.78125,
      "learning_rate": 3.269685039370079e-05,
      "loss": 0.082,
      "step": 880
    },
    {
      "epoch": 3.5039370078740157,
      "grad_norm": 6.03125,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.1572,
      "step": 890
    },
    {
      "epoch": 3.543307086614173,
      "grad_norm": 1.2109375,
      "learning_rate": 3.230314960629922e-05,
      "loss": 0.0585,
      "step": 900
    },
    {
      "epoch": 3.543307086614173,
      "eval_loss": 0.331504225730896,
      "eval_runtime": 391.6546,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 900
    },
    {
      "epoch": 3.5826771653543306,
      "grad_norm": 2.765625,
      "learning_rate": 3.210629921259843e-05,
      "loss": 0.0771,
      "step": 910
    },
    {
      "epoch": 3.622047244094488,
      "grad_norm": 8.625,
      "learning_rate": 3.1909448818897644e-05,
      "loss": 0.1289,
      "step": 920
    },
    {
      "epoch": 3.661417322834646,
      "grad_norm": 2.71875,
      "learning_rate": 3.171259842519685e-05,
      "loss": 0.0746,
      "step": 930
    },
    {
      "epoch": 3.7007874015748032,
      "grad_norm": 2.046875,
      "learning_rate": 3.1515748031496065e-05,
      "loss": 0.0742,
      "step": 940
    },
    {
      "epoch": 3.7401574803149606,
      "grad_norm": 1.9921875,
      "learning_rate": 3.131889763779527e-05,
      "loss": 0.0463,
      "step": 950
    },
    {
      "epoch": 3.7401574803149606,
      "eval_loss": 0.3349454402923584,
      "eval_runtime": 391.4254,
      "eval_samples_per_second": 0.322,
      "eval_steps_per_second": 0.041,
      "step": 950
    },
    {
      "epoch": 3.779527559055118,
      "grad_norm": 0.69921875,
      "learning_rate": 3.1122047244094485e-05,
      "loss": 0.0996,
      "step": 960
    },
    {
      "epoch": 3.8188976377952755,
      "grad_norm": 3.328125,
      "learning_rate": 3.09251968503937e-05,
      "loss": 0.0763,
      "step": 970
    },
    {
      "epoch": 3.8582677165354333,
      "grad_norm": 3.484375,
      "learning_rate": 3.072834645669291e-05,
      "loss": 0.1023,
      "step": 980
    },
    {
      "epoch": 3.8976377952755907,
      "grad_norm": 1.1953125,
      "learning_rate": 3.0531496062992126e-05,
      "loss": 0.1219,
      "step": 990
    },
    {
      "epoch": 3.937007874015748,
      "grad_norm": 3.421875,
      "learning_rate": 3.033464566929134e-05,
      "loss": 0.0852,
      "step": 1000
    },
    {
      "epoch": 3.937007874015748,
      "eval_loss": 0.3313491940498352,
      "eval_runtime": 392.3484,
      "eval_samples_per_second": 0.321,
      "eval_steps_per_second": 0.041,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2475980336448854e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}