{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.05,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005,
      "grad_norm": 5.616273880004883,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.9513,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.260721206665039,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.7789,
      "step": 20
    },
    {
      "epoch": 0.015,
      "grad_norm": 5.373858451843262,
      "learning_rate": 5.8e-06,
      "loss": 1.6535,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 4.073526859283447,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.4488,
      "step": 40
    },
    {
      "epoch": 0.025,
      "grad_norm": 4.743659973144531,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.4239,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.532003879547119,
      "learning_rate": 1.18e-05,
      "loss": 1.4531,
      "step": 60
    },
    {
      "epoch": 0.035,
      "grad_norm": 4.564126491546631,
      "learning_rate": 1.38e-05,
      "loss": 1.4279,
      "step": 70
    },
    {
      "epoch": 0.04,
      "grad_norm": 4.471712112426758,
      "learning_rate": 1.58e-05,
      "loss": 1.3619,
      "step": 80
    },
    {
      "epoch": 0.045,
      "grad_norm": 5.032183647155762,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 1.3614,
      "step": 90
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.518551349639893,
      "learning_rate": 1.98e-05,
      "loss": 1.3551,
      "step": 100
    },
    {
      "epoch": 1.005,
      "grad_norm": 6.518773555755615,
      "learning_rate": 1.990526315789474e-05,
      "loss": 0.8287,
      "step": 110
    },
    {
      "epoch": 1.01,
      "grad_norm": 3.6112170219421387,
      "learning_rate": 1.98e-05,
      "loss": 0.7035,
      "step": 120
    },
    {
      "epoch": 1.015,
      "grad_norm": 5.7912726402282715,
      "learning_rate": 1.9694736842105263e-05,
      "loss": 0.8074,
      "step": 130
    },
    {
      "epoch": 1.02,
      "grad_norm": 3.595136880874634,
      "learning_rate": 1.9589473684210527e-05,
      "loss": 0.7915,
      "step": 140
    },
    {
      "epoch": 1.025,
      "grad_norm": 4.417491912841797,
      "learning_rate": 1.9484210526315793e-05,
      "loss": 0.8106,
      "step": 150
    },
    {
      "epoch": 1.03,
      "grad_norm": 4.246488094329834,
      "learning_rate": 1.9378947368421053e-05,
      "loss": 0.8249,
      "step": 160
    },
    {
      "epoch": 1.035,
      "grad_norm": 5.055039882659912,
      "learning_rate": 1.9273684210526317e-05,
      "loss": 0.8426,
      "step": 170
    },
    {
      "epoch": 1.04,
      "grad_norm": 4.677482604980469,
      "learning_rate": 1.916842105263158e-05,
      "loss": 0.8494,
      "step": 180
    },
    {
      "epoch": 1.045,
      "grad_norm": 4.659126281738281,
      "learning_rate": 1.9063157894736843e-05,
      "loss": 0.8388,
      "step": 190
    },
    {
      "epoch": 1.05,
      "grad_norm": 4.688161849975586,
      "learning_rate": 1.8957894736842106e-05,
      "loss": 0.8079,
      "step": 200
    },
    {
      "epoch": 2.005,
      "grad_norm": 5.431162357330322,
      "learning_rate": 1.885263157894737e-05,
      "loss": 0.3679,
      "step": 210
    },
    {
      "epoch": 2.01,
      "grad_norm": 3.8187713623046875,
      "learning_rate": 1.8747368421052633e-05,
      "loss": 0.358,
      "step": 220
    },
    {
      "epoch": 2.015,
      "grad_norm": 3.1807172298431396,
      "learning_rate": 1.8642105263157896e-05,
      "loss": 0.3387,
      "step": 230
    },
    {
      "epoch": 2.02,
      "grad_norm": 4.693820953369141,
      "learning_rate": 1.853684210526316e-05,
      "loss": 0.3047,
      "step": 240
    },
    {
      "epoch": 2.025,
      "grad_norm": 4.142691135406494,
      "learning_rate": 1.8431578947368423e-05,
      "loss": 0.3039,
      "step": 250
    },
    {
      "epoch": 2.03,
      "grad_norm": 3.9841394424438477,
      "learning_rate": 1.8326315789473686e-05,
      "loss": 0.3011,
      "step": 260
    },
    {
      "epoch": 2.035,
      "grad_norm": 4.5235676765441895,
      "learning_rate": 1.822105263157895e-05,
      "loss": 0.3537,
      "step": 270
    },
    {
      "epoch": 2.04,
      "grad_norm": 4.285941123962402,
      "learning_rate": 1.8115789473684213e-05,
      "loss": 0.3105,
      "step": 280
    },
    {
      "epoch": 2.045,
      "grad_norm": 3.71958327293396,
      "learning_rate": 1.8010526315789476e-05,
      "loss": 0.3346,
      "step": 290
    },
    {
      "epoch": 2.05,
      "grad_norm": 3.477006196975708,
      "learning_rate": 1.790526315789474e-05,
      "loss": 0.3125,
      "step": 300
    },
    {
      "epoch": 3.005,
      "grad_norm": 2.9285550117492676,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 0.1397,
      "step": 310
    },
    {
      "epoch": 3.01,
      "grad_norm": 2.792161703109741,
      "learning_rate": 1.7694736842105266e-05,
      "loss": 0.1566,
      "step": 320
    },
    {
      "epoch": 3.015,
      "grad_norm": 2.6446938514709473,
      "learning_rate": 1.758947368421053e-05,
      "loss": 0.1583,
      "step": 330
    },
    {
      "epoch": 3.02,
      "grad_norm": 3.135241985321045,
      "learning_rate": 1.748421052631579e-05,
      "loss": 0.1536,
      "step": 340
    },
    {
      "epoch": 3.025,
      "grad_norm": 2.987708568572998,
      "learning_rate": 1.7378947368421052e-05,
      "loss": 0.1542,
      "step": 350
    },
    {
      "epoch": 3.03,
      "grad_norm": 2.5585477352142334,
      "learning_rate": 1.727368421052632e-05,
      "loss": 0.1742,
      "step": 360
    },
    {
      "epoch": 3.035,
      "grad_norm": 2.899765729904175,
      "learning_rate": 1.7168421052631582e-05,
      "loss": 0.1611,
      "step": 370
    },
    {
      "epoch": 3.04,
      "grad_norm": 2.752307176589966,
      "learning_rate": 1.7063157894736845e-05,
      "loss": 0.2076,
      "step": 380
    },
    {
      "epoch": 3.045,
      "grad_norm": 2.4184489250183105,
      "learning_rate": 1.6957894736842105e-05,
      "loss": 0.1744,
      "step": 390
    },
    {
      "epoch": 3.05,
      "grad_norm": 2.342548131942749,
      "learning_rate": 1.685263157894737e-05,
      "loss": 0.1657,
      "step": 400
    },
    {
      "epoch": 4.005,
      "grad_norm": 3.1114871501922607,
      "learning_rate": 1.6747368421052632e-05,
      "loss": 0.0931,
      "step": 410
    },
    {
      "epoch": 4.01,
      "grad_norm": 2.3490405082702637,
      "learning_rate": 1.66421052631579e-05,
      "loss": 0.097,
      "step": 420
    },
    {
      "epoch": 4.015,
      "grad_norm": 2.8796679973602295,
      "learning_rate": 1.653684210526316e-05,
      "loss": 0.1063,
      "step": 430
    },
    {
      "epoch": 4.02,
      "grad_norm": 2.324800491333008,
      "learning_rate": 1.643157894736842e-05,
      "loss": 0.1073,
      "step": 440
    },
    {
      "epoch": 4.025,
      "grad_norm": 2.4009687900543213,
      "learning_rate": 1.6326315789473685e-05,
      "loss": 0.0968,
      "step": 450
    },
    {
      "epoch": 4.03,
      "grad_norm": 2.9474356174468994,
      "learning_rate": 1.6221052631578948e-05,
      "loss": 0.0925,
      "step": 460
    },
    {
      "epoch": 4.035,
      "grad_norm": 2.1847965717315674,
      "learning_rate": 1.611578947368421e-05,
      "loss": 0.114,
      "step": 470
    },
    {
      "epoch": 4.04,
      "grad_norm": 1.7918593883514404,
      "learning_rate": 1.6010526315789475e-05,
      "loss": 0.1036,
      "step": 480
    },
    {
      "epoch": 4.045,
      "grad_norm": 2.242753505706787,
      "learning_rate": 1.5905263157894738e-05,
      "loss": 0.0939,
      "step": 490
    },
    {
      "epoch": 4.05,
      "grad_norm": 4.071936130523682,
      "learning_rate": 1.58e-05,
      "loss": 0.1138,
      "step": 500
    },
    {
      "epoch": 5.005,
      "grad_norm": 1.5614343881607056,
      "learning_rate": 1.5694736842105264e-05,
      "loss": 0.0469,
      "step": 510
    },
    {
      "epoch": 5.01,
      "grad_norm": 2.1511878967285156,
      "learning_rate": 1.5589473684210528e-05,
      "loss": 0.0544,
      "step": 520
    },
    {
      "epoch": 5.015,
      "grad_norm": 1.4617661237716675,
      "learning_rate": 1.548421052631579e-05,
      "loss": 0.0565,
      "step": 530
    },
    {
      "epoch": 5.02,
      "grad_norm": 2.533205270767212,
      "learning_rate": 1.5378947368421054e-05,
      "loss": 0.0582,
      "step": 540
    },
    {
      "epoch": 5.025,
      "grad_norm": 2.398082733154297,
      "learning_rate": 1.5273684210526318e-05,
      "loss": 0.065,
      "step": 550
    },
    {
      "epoch": 5.03,
      "grad_norm": 1.9306875467300415,
      "learning_rate": 1.516842105263158e-05,
      "loss": 0.0631,
      "step": 560
    },
    {
      "epoch": 5.035,
      "grad_norm": 2.3642289638519287,
      "learning_rate": 1.5063157894736844e-05,
      "loss": 0.0641,
      "step": 570
    },
    {
      "epoch": 5.04,
      "grad_norm": 1.4011757373809814,
      "learning_rate": 1.4957894736842107e-05,
      "loss": 0.0773,
      "step": 580
    },
    {
      "epoch": 5.045,
      "grad_norm": 2.026855945587158,
      "learning_rate": 1.4852631578947369e-05,
      "loss": 0.0664,
      "step": 590
    },
    {
      "epoch": 5.05,
      "grad_norm": 2.1766583919525146,
      "learning_rate": 1.4747368421052632e-05,
      "loss": 0.0545,
      "step": 600
    },
    {
      "epoch": 6.005,
      "grad_norm": 1.652336835861206,
      "learning_rate": 1.4642105263157896e-05,
      "loss": 0.0482,
      "step": 610
    },
    {
      "epoch": 6.01,
      "grad_norm": 1.5396881103515625,
      "learning_rate": 1.4536842105263159e-05,
      "loss": 0.0349,
      "step": 620
    },
    {
      "epoch": 6.015,
      "grad_norm": 2.64931321144104,
      "learning_rate": 1.4431578947368424e-05,
      "loss": 0.0491,
      "step": 630
    },
    {
      "epoch": 6.02,
      "grad_norm": 1.5272787809371948,
      "learning_rate": 1.4326315789473685e-05,
      "loss": 0.0471,
      "step": 640
    },
    {
      "epoch": 6.025,
      "grad_norm": 1.5077707767486572,
      "learning_rate": 1.4221052631578949e-05,
      "loss": 0.0413,
      "step": 650
    },
    {
      "epoch": 6.03,
      "grad_norm": 1.2149569988250732,
      "learning_rate": 1.4115789473684212e-05,
      "loss": 0.0442,
      "step": 660
    },
    {
      "epoch": 6.035,
      "grad_norm": 1.6021332740783691,
      "learning_rate": 1.4010526315789475e-05,
      "loss": 0.0386,
      "step": 670
    },
    {
      "epoch": 6.04,
      "grad_norm": 1.8967393636703491,
      "learning_rate": 1.3905263157894737e-05,
      "loss": 0.047,
      "step": 680
    },
    {
      "epoch": 6.045,
      "grad_norm": 1.5336661338806152,
      "learning_rate": 1.38e-05,
      "loss": 0.0381,
      "step": 690
    },
    {
      "epoch": 6.05,
      "grad_norm": 2.3286962509155273,
      "learning_rate": 1.3694736842105265e-05,
      "loss": 0.0479,
      "step": 700
    },
    {
      "epoch": 7.005,
      "grad_norm": 1.4702962636947632,
      "learning_rate": 1.3589473684210528e-05,
      "loss": 0.0231,
      "step": 710
    },
    {
      "epoch": 7.01,
      "grad_norm": 1.7746834754943848,
      "learning_rate": 1.3484210526315792e-05,
      "loss": 0.0291,
      "step": 720
    },
    {
      "epoch": 7.015,
      "grad_norm": 1.37478768825531,
      "learning_rate": 1.3378947368421053e-05,
      "loss": 0.0368,
      "step": 730
    },
    {
      "epoch": 7.02,
      "grad_norm": 1.2662794589996338,
      "learning_rate": 1.3273684210526316e-05,
      "loss": 0.034,
      "step": 740
    },
    {
      "epoch": 7.025,
      "grad_norm": 0.6514212489128113,
      "learning_rate": 1.316842105263158e-05,
      "loss": 0.0295,
      "step": 750
    },
    {
      "epoch": 7.03,
      "grad_norm": 0.9872649908065796,
      "learning_rate": 1.3063157894736845e-05,
      "loss": 0.0248,
      "step": 760
    },
    {
      "epoch": 7.035,
      "grad_norm": 0.9525852203369141,
      "learning_rate": 1.2957894736842108e-05,
      "loss": 0.0254,
      "step": 770
    },
    {
      "epoch": 7.04,
      "grad_norm": 1.5137120485305786,
      "learning_rate": 1.285263157894737e-05,
      "loss": 0.0238,
      "step": 780
    },
    {
      "epoch": 7.045,
      "grad_norm": 3.0998730659484863,
      "learning_rate": 1.2747368421052633e-05,
      "loss": 0.0337,
      "step": 790
    },
    {
      "epoch": 7.05,
      "grad_norm": 1.361088752746582,
      "learning_rate": 1.2642105263157896e-05,
      "loss": 0.0399,
      "step": 800
    },
    {
      "epoch": 8.005,
      "grad_norm": 0.9619424343109131,
      "learning_rate": 1.2536842105263158e-05,
      "loss": 0.0215,
      "step": 810
    },
    {
      "epoch": 8.01,
      "grad_norm": 1.0369452238082886,
      "learning_rate": 1.2431578947368421e-05,
      "loss": 0.0247,
      "step": 820
    },
    {
      "epoch": 8.015,
      "grad_norm": 1.344269871711731,
      "learning_rate": 1.2326315789473686e-05,
      "loss": 0.025,
      "step": 830
    },
    {
      "epoch": 8.02,
      "grad_norm": 1.2112865447998047,
      "learning_rate": 1.2221052631578949e-05,
      "loss": 0.0216,
      "step": 840
    },
    {
      "epoch": 8.025,
      "grad_norm": 1.7333956956863403,
      "learning_rate": 1.2115789473684212e-05,
      "loss": 0.0183,
      "step": 850
    },
    {
      "epoch": 8.03,
      "grad_norm": 2.0652589797973633,
      "learning_rate": 1.2010526315789474e-05,
      "loss": 0.0241,
      "step": 860
    },
    {
      "epoch": 8.035,
      "grad_norm": 0.624588131904602,
      "learning_rate": 1.1905263157894737e-05,
      "loss": 0.0202,
      "step": 870
    },
    {
      "epoch": 8.04,
      "grad_norm": 1.0641587972640991,
      "learning_rate": 1.18e-05,
      "loss": 0.019,
      "step": 880
    },
    {
      "epoch": 8.045,
      "grad_norm": 1.1550590991973877,
      "learning_rate": 1.1694736842105264e-05,
      "loss": 0.0214,
      "step": 890
    },
    {
      "epoch": 8.05,
      "grad_norm": 1.3287566900253296,
      "learning_rate": 1.1589473684210529e-05,
      "loss": 0.0292,
      "step": 900
    },
    {
      "epoch": 9.005,
      "grad_norm": 1.3364150524139404,
      "learning_rate": 1.148421052631579e-05,
      "loss": 0.0213,
      "step": 910
    },
    {
      "epoch": 9.01,
      "grad_norm": 0.7193664908409119,
      "learning_rate": 1.1378947368421054e-05,
      "loss": 0.0082,
      "step": 920
    },
    {
      "epoch": 9.015,
      "grad_norm": 1.0872008800506592,
      "learning_rate": 1.1273684210526317e-05,
      "loss": 0.0151,
      "step": 930
    },
    {
      "epoch": 9.02,
      "grad_norm": 0.22245873510837555,
      "learning_rate": 1.116842105263158e-05,
      "loss": 0.0128,
      "step": 940
    },
    {
      "epoch": 9.025,
      "grad_norm": 0.9914424419403076,
      "learning_rate": 1.1063157894736842e-05,
      "loss": 0.0174,
      "step": 950
    },
    {
      "epoch": 9.03,
      "grad_norm": 0.9509072303771973,
      "learning_rate": 1.0957894736842105e-05,
      "loss": 0.0181,
      "step": 960
    },
    {
      "epoch": 9.035,
      "grad_norm": 0.40795469284057617,
      "learning_rate": 1.085263157894737e-05,
      "loss": 0.0202,
      "step": 970
    },
    {
      "epoch": 9.04,
      "grad_norm": 1.3863106966018677,
      "learning_rate": 1.0747368421052633e-05,
      "loss": 0.0172,
      "step": 980
    },
    {
      "epoch": 9.045,
      "grad_norm": 0.6388317942619324,
      "learning_rate": 1.0642105263157897e-05,
      "loss": 0.0185,
      "step": 990
    },
    {
      "epoch": 9.05,
      "grad_norm": 1.0237617492675781,
      "learning_rate": 1.0536842105263158e-05,
      "loss": 0.0193,
      "step": 1000
    },
    {
      "epoch": 10.005,
      "grad_norm": 0.2478121817111969,
      "learning_rate": 1.0431578947368421e-05,
      "loss": 0.0111,
      "step": 1010
    },
    {
      "epoch": 10.01,
      "grad_norm": 1.0051342248916626,
      "learning_rate": 1.0326315789473685e-05,
      "loss": 0.0102,
      "step": 1020
    },
    {
      "epoch": 10.015,
      "grad_norm": 0.9585472345352173,
      "learning_rate": 1.0221052631578948e-05,
      "loss": 0.0141,
      "step": 1030
    },
    {
      "epoch": 10.02,
      "grad_norm": 1.248799204826355,
      "learning_rate": 1.0115789473684213e-05,
      "loss": 0.0088,
      "step": 1040
    },
    {
      "epoch": 10.025,
      "grad_norm": 1.050134301185608,
      "learning_rate": 1.0010526315789474e-05,
      "loss": 0.0097,
      "step": 1050
    },
    {
      "epoch": 10.03,
      "grad_norm": 0.2019995152950287,
      "learning_rate": 9.905263157894738e-06,
      "loss": 0.011,
      "step": 1060
    },
    {
      "epoch": 10.035,
      "grad_norm": 0.9100256562232971,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.0149,
      "step": 1070
    },
    {
      "epoch": 10.04,
      "grad_norm": 0.8645588159561157,
      "learning_rate": 9.694736842105263e-06,
      "loss": 0.011,
      "step": 1080
    },
    {
      "epoch": 10.045,
      "grad_norm": 0.9465664029121399,
      "learning_rate": 9.589473684210528e-06,
      "loss": 0.0116,
      "step": 1090
    },
    {
      "epoch": 10.05,
      "grad_norm": 0.7357518076896667,
      "learning_rate": 9.484210526315791e-06,
      "loss": 0.0132,
      "step": 1100
    },
    {
      "epoch": 11.005,
      "grad_norm": 0.0960564911365509,
      "learning_rate": 9.378947368421052e-06,
      "loss": 0.0079,
      "step": 1110
    },
    {
      "epoch": 11.01,
      "grad_norm": 0.07488369941711426,
      "learning_rate": 9.273684210526317e-06,
      "loss": 0.0079,
      "step": 1120
    },
    {
      "epoch": 11.015,
      "grad_norm": 0.4596630334854126,
      "learning_rate": 9.168421052631579e-06,
      "loss": 0.0073,
      "step": 1130
    },
    {
      "epoch": 11.02,
      "grad_norm": 0.915014386177063,
      "learning_rate": 9.063157894736842e-06,
      "loss": 0.0058,
      "step": 1140
    },
    {
      "epoch": 11.025,
      "grad_norm": 0.4357207119464874,
      "learning_rate": 8.957894736842107e-06,
      "loss": 0.0082,
      "step": 1150
    },
    {
      "epoch": 11.03,
      "grad_norm": 0.6345843076705933,
      "learning_rate": 8.852631578947369e-06,
      "loss": 0.009,
      "step": 1160
    },
    {
      "epoch": 11.035,
      "grad_norm": 0.2351154237985611,
      "learning_rate": 8.747368421052632e-06,
      "loss": 0.0071,
      "step": 1170
    },
    {
      "epoch": 11.04,
      "grad_norm": 0.5750226378440857,
      "learning_rate": 8.642105263157895e-06,
      "loss": 0.0065,
      "step": 1180
    },
    {
      "epoch": 11.045,
      "grad_norm": 0.49880605936050415,
      "learning_rate": 8.536842105263159e-06,
      "loss": 0.0061,
      "step": 1190
    },
    {
      "epoch": 11.05,
      "grad_norm": 0.6473588347434998,
      "learning_rate": 8.431578947368422e-06,
      "loss": 0.0091,
      "step": 1200
    },
    {
      "epoch": 12.005,
      "grad_norm": 0.02745138294994831,
      "learning_rate": 8.326315789473685e-06,
      "loss": 0.0027,
      "step": 1210
    },
    {
      "epoch": 12.01,
      "grad_norm": 0.6922830939292908,
      "learning_rate": 8.221052631578948e-06,
      "loss": 0.0058,
      "step": 1220
    },
    {
      "epoch": 12.015,
      "grad_norm": 0.6273651719093323,
      "learning_rate": 8.115789473684212e-06,
      "loss": 0.0034,
      "step": 1230
    },
    {
      "epoch": 12.02,
      "grad_norm": 1.0830379724502563,
      "learning_rate": 8.010526315789473e-06,
      "loss": 0.0063,
      "step": 1240
    },
    {
      "epoch": 12.025,
      "grad_norm": 0.824835479259491,
      "learning_rate": 7.905263157894737e-06,
      "loss": 0.0064,
      "step": 1250
    },
    {
      "epoch": 12.03,
      "grad_norm": 0.5051027536392212,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.0029,
      "step": 1260
    },
    {
      "epoch": 12.035,
      "grad_norm": 0.6191169619560242,
      "learning_rate": 7.694736842105263e-06,
      "loss": 0.0036,
      "step": 1270
    },
    {
      "epoch": 12.04,
      "grad_norm": 0.03212520107626915,
      "learning_rate": 7.589473684210526e-06,
      "loss": 0.001,
      "step": 1280
    },
    {
      "epoch": 12.045,
      "grad_norm": 0.027301745489239693,
      "learning_rate": 7.4842105263157905e-06,
      "loss": 0.0024,
      "step": 1290
    },
    {
      "epoch": 12.05,
      "grad_norm": 0.6917107701301575,
      "learning_rate": 7.378947368421053e-06,
      "loss": 0.002,
      "step": 1300
    },
    {
      "epoch": 13.005,
      "grad_norm": 0.009404812939465046,
      "learning_rate": 7.273684210526316e-06,
      "loss": 0.0023,
      "step": 1310
    },
    {
      "epoch": 13.01,
      "grad_norm": 0.5634567737579346,
      "learning_rate": 7.16842105263158e-06,
      "loss": 0.001,
      "step": 1320
    },
    {
      "epoch": 13.015,
      "grad_norm": 0.02036663331091404,
      "learning_rate": 7.063157894736843e-06,
      "loss": 0.0025,
      "step": 1330
    },
    {
      "epoch": 13.02,
      "grad_norm": 0.05707384645938873,
      "learning_rate": 6.957894736842106e-06,
      "loss": 0.0012,
      "step": 1340
    },
    {
      "epoch": 13.025,
      "grad_norm": 0.022448807954788208,
      "learning_rate": 6.8526315789473685e-06,
      "loss": 0.0008,
      "step": 1350
    },
    {
      "epoch": 13.03,
      "grad_norm": 0.012089096009731293,
      "learning_rate": 6.747368421052633e-06,
      "loss": 0.0039,
      "step": 1360
    },
    {
      "epoch": 13.035,
      "grad_norm": 0.14159785211086273,
      "learning_rate": 6.642105263157895e-06,
      "loss": 0.0005,
      "step": 1370
    },
    {
      "epoch": 13.04,
      "grad_norm": 0.05650542676448822,
      "learning_rate": 6.536842105263158e-06,
      "loss": 0.0011,
      "step": 1380
    },
    {
      "epoch": 13.045,
      "grad_norm": 0.030941806733608246,
      "learning_rate": 6.431578947368422e-06,
      "loss": 0.0024,
      "step": 1390
    },
    {
      "epoch": 13.05,
      "grad_norm": 0.022141387686133385,
      "learning_rate": 6.326315789473685e-06,
      "loss": 0.0035,
      "step": 1400
    },
    {
      "epoch": 14.005,
      "grad_norm": 0.010789740830659866,
      "learning_rate": 6.221052631578947e-06,
      "loss": 0.0002,
      "step": 1410
    },
    {
      "epoch": 14.01,
      "grad_norm": 0.008089865557849407,
      "learning_rate": 6.1157894736842106e-06,
      "loss": 0.0002,
      "step": 1420
    },
    {
      "epoch": 14.015,
      "grad_norm": 0.009247499518096447,
      "learning_rate": 6.010526315789475e-06,
      "loss": 0.0004,
      "step": 1430
    },
    {
      "epoch": 14.02,
      "grad_norm": 0.005500028375536203,
      "learning_rate": 5.905263157894737e-06,
      "loss": 0.0019,
      "step": 1440
    },
    {
      "epoch": 14.025,
      "grad_norm": 0.04416996240615845,
      "learning_rate": 5.8e-06,
      "loss": 0.0013,
      "step": 1450
    },
    {
      "epoch": 14.03,
      "grad_norm": 0.10680264979600906,
      "learning_rate": 5.694736842105264e-06,
      "loss": 0.0012,
      "step": 1460
    },
    {
      "epoch": 14.035,
      "grad_norm": 0.008884921669960022,
      "learning_rate": 5.589473684210527e-06,
      "loss": 0.0002,
      "step": 1470
    },
    {
      "epoch": 14.04,
      "grad_norm": 0.179422989487648,
      "learning_rate": 5.484210526315789e-06,
      "loss": 0.0009,
      "step": 1480
    },
    {
      "epoch": 14.045,
      "grad_norm": 0.7773061990737915,
      "learning_rate": 5.3789473684210535e-06,
      "loss": 0.0003,
      "step": 1490
    },
    {
      "epoch": 14.05,
      "grad_norm": 0.04718916490674019,
      "learning_rate": 5.273684210526317e-06,
      "loss": 0.0009,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.758292910191411e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}