{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 10.000000953674316,
      "learning_rate": 2.132196162046908e-06,
      "loss": 25.0099,
      "step": 10
    },
    {
      "epoch": 0.0064,
      "grad_norm": 10.0,
      "learning_rate": 4.264392324093816e-06,
      "loss": 21.1499,
      "step": 20
    },
    {
      "epoch": 0.0096,
      "grad_norm": 9.999999046325684,
      "learning_rate": 6.396588486140726e-06,
      "loss": 19.6111,
      "step": 30
    },
    {
      "epoch": 0.0128,
      "grad_norm": 10.0,
      "learning_rate": 8.528784648187633e-06,
      "loss": 22.3722,
      "step": 40
    },
    {
      "epoch": 0.016,
      "grad_norm": 9.999999046325684,
      "learning_rate": 1.0660980810234541e-05,
      "loss": 20.1462,
      "step": 50
    },
    {
      "epoch": 0.0192,
      "grad_norm": 10.0,
      "learning_rate": 1.2793176972281452e-05,
      "loss": 20.4235,
      "step": 60
    },
    {
      "epoch": 0.0224,
      "grad_norm": 10.0,
      "learning_rate": 1.4925373134328357e-05,
      "loss": 20.7853,
      "step": 70
    },
    {
      "epoch": 0.0256,
      "grad_norm": 10.0,
      "learning_rate": 1.7057569296375266e-05,
      "loss": 19.5459,
      "step": 80
    },
    {
      "epoch": 0.0288,
      "grad_norm": 9.999999046325684,
      "learning_rate": 1.9189765458422178e-05,
      "loss": 18.4778,
      "step": 90
    },
    {
      "epoch": 0.032,
      "grad_norm": 9.999999046325684,
      "learning_rate": 2.1321961620469083e-05,
      "loss": 16.2191,
      "step": 100
    },
    {
      "epoch": 0.0352,
      "grad_norm": 10.0,
      "learning_rate": 2.345415778251599e-05,
      "loss": 18.5773,
      "step": 110
    },
    {
      "epoch": 0.0384,
      "grad_norm": 9.999999046325684,
      "learning_rate": 2.5586353944562904e-05,
      "loss": 15.9389,
      "step": 120
    },
    {
      "epoch": 0.0416,
      "grad_norm": 10.0,
      "learning_rate": 2.771855010660981e-05,
      "loss": 15.6064,
      "step": 130
    },
    {
      "epoch": 0.0448,
      "grad_norm": 10.000000953674316,
      "learning_rate": 2.9850746268656714e-05,
      "loss": 15.6366,
      "step": 140
    },
    {
      "epoch": 0.048,
      "grad_norm": 10.000000953674316,
      "learning_rate": 3.1982942430703626e-05,
      "loss": 16.7232,
      "step": 150
    },
    {
      "epoch": 0.0512,
      "grad_norm": 10.0,
      "learning_rate": 3.411513859275053e-05,
      "loss": 13.2957,
      "step": 160
    },
    {
      "epoch": 0.0544,
      "grad_norm": 10.0,
      "learning_rate": 3.624733475479744e-05,
      "loss": 13.3429,
      "step": 170
    },
    {
      "epoch": 0.0576,
      "grad_norm": 9.999999046325684,
      "learning_rate": 3.8379530916844355e-05,
      "loss": 13.3301,
      "step": 180
    },
    {
      "epoch": 0.0608,
      "grad_norm": 10.000000953674316,
      "learning_rate": 4.051172707889126e-05,
      "loss": 15.1708,
      "step": 190
    },
    {
      "epoch": 0.064,
      "grad_norm": 10.0,
      "learning_rate": 4.2643923240938166e-05,
      "loss": 14.8533,
      "step": 200
    },
    {
      "epoch": 0.0672,
      "grad_norm": 10.0,
      "learning_rate": 4.477611940298508e-05,
      "loss": 11.6389,
      "step": 210
    },
    {
      "epoch": 0.0704,
      "grad_norm": 9.999999046325684,
      "learning_rate": 4.690831556503198e-05,
      "loss": 12.2515,
      "step": 220
    },
    {
      "epoch": 0.0736,
      "grad_norm": 10.0,
      "learning_rate": 4.904051172707889e-05,
      "loss": 12.6637,
      "step": 230
    },
    {
      "epoch": 0.0768,
      "grad_norm": 9.999999046325684,
      "learning_rate": 5.117270788912581e-05,
      "loss": 10.6091,
      "step": 240
    },
    {
      "epoch": 0.08,
      "grad_norm": 9.999999046325684,
      "learning_rate": 5.330490405117271e-05,
      "loss": 10.9362,
      "step": 250
    },
    {
      "epoch": 0.0832,
      "grad_norm": 10.0,
      "learning_rate": 5.543710021321962e-05,
      "loss": 12.4545,
      "step": 260
    },
    {
      "epoch": 0.0864,
      "grad_norm": 10.000000953674316,
      "learning_rate": 5.756929637526652e-05,
      "loss": 11.5238,
      "step": 270
    },
    {
      "epoch": 0.0896,
      "grad_norm": 10.0,
      "learning_rate": 5.970149253731343e-05,
      "loss": 10.8966,
      "step": 280
    },
    {
      "epoch": 0.0928,
      "grad_norm": 10.0,
      "learning_rate": 6.183368869936035e-05,
      "loss": 10.5903,
      "step": 290
    },
    {
      "epoch": 0.096,
      "grad_norm": 10.0,
      "learning_rate": 6.396588486140725e-05,
      "loss": 10.4872,
      "step": 300
    },
    {
      "epoch": 0.0992,
      "grad_norm": 10.0,
      "learning_rate": 6.609808102345416e-05,
      "loss": 9.9663,
      "step": 310
    },
    {
      "epoch": 0.1024,
      "grad_norm": 9.999999046325684,
      "learning_rate": 6.823027718550106e-05,
      "loss": 9.4655,
      "step": 320
    },
    {
      "epoch": 0.1056,
      "grad_norm": 10.0,
      "learning_rate": 7.036247334754798e-05,
      "loss": 10.487,
      "step": 330
    },
    {
      "epoch": 0.1088,
      "grad_norm": 10.000001907348633,
      "learning_rate": 7.249466950959489e-05,
      "loss": 9.3626,
      "step": 340
    },
    {
      "epoch": 0.112,
      "grad_norm": 10.0,
      "learning_rate": 7.46268656716418e-05,
      "loss": 9.864,
      "step": 350
    },
    {
      "epoch": 0.1152,
      "grad_norm": 9.999999046325684,
      "learning_rate": 7.675906183368871e-05,
      "loss": 8.8008,
      "step": 360
    },
    {
      "epoch": 0.1184,
      "grad_norm": 10.0,
      "learning_rate": 7.889125799573562e-05,
      "loss": 9.7772,
      "step": 370
    },
    {
      "epoch": 0.1216,
      "grad_norm": 10.0,
      "learning_rate": 8.102345415778252e-05,
      "loss": 8.7418,
      "step": 380
    },
    {
      "epoch": 0.1248,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.315565031982943e-05,
      "loss": 9.1157,
      "step": 390
    },
    {
      "epoch": 0.128,
      "grad_norm": 10.000000953674316,
      "learning_rate": 8.528784648187633e-05,
      "loss": 8.1395,
      "step": 400
    },
    {
      "epoch": 0.1312,
      "grad_norm": 10.0,
      "learning_rate": 8.742004264392325e-05,
      "loss": 8.8305,
      "step": 410
    },
    {
      "epoch": 0.1344,
      "grad_norm": 10.0,
      "learning_rate": 8.955223880597016e-05,
      "loss": 9.2089,
      "step": 420
    },
    {
      "epoch": 0.1376,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.168443496801706e-05,
      "loss": 8.5206,
      "step": 430
    },
    {
      "epoch": 0.1408,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.381663113006397e-05,
      "loss": 8.8993,
      "step": 440
    },
    {
      "epoch": 0.144,
      "grad_norm": 10.0,
      "learning_rate": 9.594882729211087e-05,
      "loss": 8.8173,
      "step": 450
    },
    {
      "epoch": 0.1472,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.808102345415778e-05,
      "loss": 8.3408,
      "step": 460
    },
    {
      "epoch": 0.1504,
      "grad_norm": 10.0,
      "learning_rate": 9.998877161464182e-05,
      "loss": 7.5853,
      "step": 470
    },
    {
      "epoch": 0.1536,
      "grad_norm": 10.0,
      "learning_rate": 9.987648776105997e-05,
      "loss": 7.4544,
      "step": 480
    },
    {
      "epoch": 0.1568,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.97642039074781e-05,
      "loss": 8.0499,
      "step": 490
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.0,
      "learning_rate": 9.965192005389625e-05,
      "loss": 8.2335,
      "step": 500
    },
    {
      "epoch": 0.1632,
      "grad_norm": 10.0,
      "learning_rate": 9.95396362003144e-05,
      "loss": 7.0574,
      "step": 510
    },
    {
      "epoch": 0.1664,
      "grad_norm": 10.0,
      "learning_rate": 9.942735234673256e-05,
      "loss": 6.8412,
      "step": 520
    },
    {
      "epoch": 0.1696,
      "grad_norm": 10.0,
      "learning_rate": 9.931506849315069e-05,
      "loss": 7.1418,
      "step": 530
    },
    {
      "epoch": 0.1728,
      "grad_norm": 10.0,
      "learning_rate": 9.920278463956883e-05,
      "loss": 7.1722,
      "step": 540
    },
    {
      "epoch": 0.176,
      "grad_norm": 10.0,
      "learning_rate": 9.909050078598698e-05,
      "loss": 6.7641,
      "step": 550
    },
    {
      "epoch": 0.1792,
      "grad_norm": 10.0,
      "learning_rate": 9.897821693240512e-05,
      "loss": 6.3646,
      "step": 560
    },
    {
      "epoch": 0.1824,
      "grad_norm": 10.0,
      "learning_rate": 9.886593307882327e-05,
      "loss": 6.3469,
      "step": 570
    },
    {
      "epoch": 0.1856,
      "grad_norm": 10.0,
      "learning_rate": 9.875364922524142e-05,
      "loss": 6.38,
      "step": 580
    },
    {
      "epoch": 0.1888,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.864136537165956e-05,
      "loss": 5.8154,
      "step": 590
    },
    {
      "epoch": 0.192,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.852908151807771e-05,
      "loss": 5.6794,
      "step": 600
    },
    {
      "epoch": 0.1952,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.841679766449586e-05,
      "loss": 5.4415,
      "step": 610
    },
    {
      "epoch": 0.1984,
      "grad_norm": 10.0,
      "learning_rate": 9.8304513810914e-05,
      "loss": 4.7814,
      "step": 620
    },
    {
      "epoch": 0.2016,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.819222995733213e-05,
      "loss": 4.8304,
      "step": 630
    },
    {
      "epoch": 0.2048,
      "grad_norm": 10.0,
      "learning_rate": 9.807994610375028e-05,
      "loss": 4.9017,
      "step": 640
    },
    {
      "epoch": 0.208,
      "grad_norm": 10.0,
      "learning_rate": 9.796766225016843e-05,
      "loss": 4.5826,
      "step": 650
    },
    {
      "epoch": 0.2112,
      "grad_norm": 10.0,
      "learning_rate": 9.785537839658657e-05,
      "loss": 4.4032,
      "step": 660
    },
    {
      "epoch": 0.2144,
      "grad_norm": 10.0,
      "learning_rate": 9.774309454300472e-05,
      "loss": 4.4789,
      "step": 670
    },
    {
      "epoch": 0.2176,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.763081068942287e-05,
      "loss": 3.5318,
      "step": 680
    },
    {
      "epoch": 0.2208,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.751852683584101e-05,
      "loss": 3.9803,
      "step": 690
    },
    {
      "epoch": 0.224,
      "grad_norm": 10.0,
      "learning_rate": 9.740624298225916e-05,
      "loss": 3.3411,
      "step": 700
    },
    {
      "epoch": 0.2272,
      "grad_norm": 10.0,
      "learning_rate": 9.729395912867731e-05,
      "loss": 3.8421,
      "step": 710
    },
    {
      "epoch": 0.2304,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.718167527509545e-05,
      "loss": 3.8598,
      "step": 720
    },
    {
      "epoch": 0.2336,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.706939142151358e-05,
      "loss": 3.6175,
      "step": 730
    },
    {
      "epoch": 0.2368,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.695710756793174e-05,
      "loss": 3.3833,
      "step": 740
    },
    {
      "epoch": 0.24,
      "grad_norm": 10.0,
      "learning_rate": 9.684482371434989e-05,
      "loss": 3.1501,
      "step": 750
    },
    {
      "epoch": 0.2432,
      "grad_norm": 10.0,
      "learning_rate": 9.673253986076802e-05,
      "loss": 3.2144,
      "step": 760
    },
    {
      "epoch": 0.2464,
      "grad_norm": 10.0,
      "learning_rate": 9.662025600718617e-05,
      "loss": 3.1372,
      "step": 770
    },
    {
      "epoch": 0.2496,
      "grad_norm": 10.0,
      "learning_rate": 9.650797215360432e-05,
      "loss": 2.728,
      "step": 780
    },
    {
      "epoch": 0.2528,
      "grad_norm": 10.0,
      "learning_rate": 9.639568830002246e-05,
      "loss": 2.7485,
      "step": 790
    },
    {
      "epoch": 0.256,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.628340444644061e-05,
      "loss": 2.7431,
      "step": 800
    },
    {
      "epoch": 0.2592,
      "grad_norm": 10.0,
      "learning_rate": 9.617112059285875e-05,
      "loss": 2.534,
      "step": 810
    },
    {
      "epoch": 0.2624,
      "grad_norm": 10.0,
      "learning_rate": 9.605883673927689e-05,
      "loss": 2.6129,
      "step": 820
    },
    {
      "epoch": 0.2656,
      "grad_norm": 10.0,
      "learning_rate": 9.594655288569504e-05,
      "loss": 2.6607,
      "step": 830
    },
    {
      "epoch": 0.2688,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.583426903211319e-05,
      "loss": 2.5158,
      "step": 840
    },
    {
      "epoch": 0.272,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.572198517853134e-05,
      "loss": 2.2633,
      "step": 850
    },
    {
      "epoch": 0.2752,
      "grad_norm": 10.0,
      "learning_rate": 9.560970132494948e-05,
      "loss": 2.4407,
      "step": 860
    },
    {
      "epoch": 0.2784,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.549741747136763e-05,
      "loss": 2.1584,
      "step": 870
    },
    {
      "epoch": 0.2816,
      "grad_norm": 10.0,
      "learning_rate": 9.538513361778578e-05,
      "loss": 2.1552,
      "step": 880
    },
    {
      "epoch": 0.2848,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.527284976420391e-05,
      "loss": 1.8968,
      "step": 890
    },
    {
      "epoch": 0.288,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.516056591062205e-05,
      "loss": 1.9182,
      "step": 900
    },
    {
      "epoch": 0.2912,
      "grad_norm": 10.0,
      "learning_rate": 9.50482820570402e-05,
      "loss": 1.9413,
      "step": 910
    },
    {
      "epoch": 0.2944,
      "grad_norm": 10.0,
      "learning_rate": 9.493599820345834e-05,
      "loss": 1.8959,
      "step": 920
    },
    {
      "epoch": 0.2976,
      "grad_norm": 10.0,
      "learning_rate": 9.482371434987649e-05,
      "loss": 1.9225,
      "step": 930
    },
    {
      "epoch": 0.3008,
      "grad_norm": 10.0,
      "learning_rate": 9.471143049629464e-05,
      "loss": 1.8802,
      "step": 940
    },
    {
      "epoch": 0.304,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.459914664271278e-05,
      "loss": 1.8896,
      "step": 950
    },
    {
      "epoch": 0.3072,
      "grad_norm": 10.0,
      "learning_rate": 9.448686278913093e-05,
      "loss": 1.7142,
      "step": 960
    },
    {
      "epoch": 0.3104,
      "grad_norm": 10.0,
      "learning_rate": 9.437457893554908e-05,
      "loss": 1.6888,
      "step": 970
    },
    {
      "epoch": 0.3136,
      "grad_norm": 10.0,
      "learning_rate": 9.426229508196722e-05,
      "loss": 1.6177,
      "step": 980
    },
    {
      "epoch": 0.3168,
      "grad_norm": 10.0,
      "learning_rate": 9.415001122838537e-05,
      "loss": 1.645,
      "step": 990
    },
    {
      "epoch": 0.32,
      "grad_norm": 10.0,
      "learning_rate": 9.40377273748035e-05,
      "loss": 1.6792,
      "step": 1000
    },
    {
      "epoch": 0.3232,
      "grad_norm": 10.0,
      "learning_rate": 9.392544352122165e-05,
      "loss": 1.8599,
      "step": 1010
    },
    {
      "epoch": 0.3264,
      "grad_norm": 10.0,
      "learning_rate": 9.381315966763979e-05,
      "loss": 1.6779,
      "step": 1020
    },
    {
      "epoch": 0.3296,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.370087581405794e-05,
      "loss": 1.4669,
      "step": 1030
    },
    {
      "epoch": 0.3328,
      "grad_norm": 10.0,
      "learning_rate": 9.358859196047609e-05,
      "loss": 1.3649,
      "step": 1040
    },
    {
      "epoch": 0.336,
      "grad_norm": 10.0,
      "learning_rate": 9.347630810689423e-05,
      "loss": 1.3987,
      "step": 1050
    },
    {
      "epoch": 0.3392,
      "grad_norm": 9.999998092651367,
      "learning_rate": 9.336402425331238e-05,
      "loss": 1.2421,
      "step": 1060
    },
    {
      "epoch": 0.3424,
      "grad_norm": 9.999998092651367,
      "learning_rate": 9.325174039973053e-05,
      "loss": 1.3011,
      "step": 1070
    },
    {
      "epoch": 0.3456,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.313945654614867e-05,
      "loss": 1.2287,
      "step": 1080
    },
    {
      "epoch": 0.3488,
      "grad_norm": 10.0,
      "learning_rate": 9.30271726925668e-05,
      "loss": 1.1587,
      "step": 1090
    },
    {
      "epoch": 0.352,
      "grad_norm": 10.0,
      "learning_rate": 9.291488883898496e-05,
      "loss": 1.2415,
      "step": 1100
    },
    {
      "epoch": 0.3552,
      "grad_norm": 10.0,
      "learning_rate": 9.280260498540311e-05,
      "loss": 1.1415,
      "step": 1110
    },
    {
      "epoch": 0.3584,
      "grad_norm": 9.999998092651367,
      "learning_rate": 9.269032113182124e-05,
      "loss": 1.1941,
      "step": 1120
    },
    {
      "epoch": 0.3616,
      "grad_norm": 10.0,
      "learning_rate": 9.25780372782394e-05,
      "loss": 1.1668,
      "step": 1130
    },
    {
      "epoch": 0.3648,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.246575342465755e-05,
      "loss": 1.0887,
      "step": 1140
    },
    {
      "epoch": 0.368,
      "grad_norm": 9.999998092651367,
      "learning_rate": 9.235346957107568e-05,
      "loss": 1.0604,
      "step": 1150
    },
    {
      "epoch": 0.3712,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.224118571749383e-05,
      "loss": 0.9446,
      "step": 1160
    },
    {
      "epoch": 0.3744,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.212890186391197e-05,
      "loss": 0.9737,
      "step": 1170
    },
    {
      "epoch": 0.3776,
      "grad_norm": 10.0,
      "learning_rate": 9.201661801033011e-05,
      "loss": 0.9654,
      "step": 1180
    },
    {
      "epoch": 0.3808,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.190433415674826e-05,
      "loss": 1.0253,
      "step": 1190
    },
    {
      "epoch": 0.384,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.179205030316641e-05,
      "loss": 0.8597,
      "step": 1200
    },
    {
      "epoch": 0.3872,
      "grad_norm": 9.999998092651367,
      "learning_rate": 9.167976644958456e-05,
      "loss": 0.8202,
      "step": 1210
    },
    {
      "epoch": 0.3904,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.15674825960027e-05,
      "loss": 0.8386,
      "step": 1220
    },
    {
      "epoch": 0.3936,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.145519874242085e-05,
      "loss": 0.8318,
      "step": 1230
    },
    {
      "epoch": 0.3968,
      "grad_norm": 10.0,
      "learning_rate": 9.1342914888839e-05,
      "loss": 0.8571,
      "step": 1240
    },
    {
      "epoch": 0.4,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.123063103525713e-05,
      "loss": 0.8326,
      "step": 1250
    },
    {
      "epoch": 0.4032,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.111834718167527e-05,
      "loss": 0.7655,
      "step": 1260
    },
    {
      "epoch": 0.4064,
      "grad_norm": 10.0,
      "learning_rate": 9.100606332809342e-05,
      "loss": 0.747,
      "step": 1270
    },
    {
      "epoch": 0.4096,
      "grad_norm": 10.0,
      "learning_rate": 9.089377947451156e-05,
      "loss": 0.8671,
      "step": 1280
    },
    {
      "epoch": 0.4128,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.078149562092971e-05,
      "loss": 0.8758,
      "step": 1290
    },
    {
      "epoch": 0.416,
      "grad_norm": 10.000000953674316,
      "learning_rate": 9.066921176734786e-05,
      "loss": 0.8714,
      "step": 1300
    },
    {
      "epoch": 0.4192,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.055692791376601e-05,
      "loss": 0.8022,
      "step": 1310
    },
    {
      "epoch": 0.4224,
      "grad_norm": 8.615378379821777,
      "learning_rate": 9.044464406018415e-05,
      "loss": 0.7234,
      "step": 1320
    },
    {
      "epoch": 0.4256,
      "grad_norm": 10.0,
      "learning_rate": 9.03323602066023e-05,
      "loss": 0.7416,
      "step": 1330
    },
    {
      "epoch": 0.4288,
      "grad_norm": 10.0,
      "learning_rate": 9.022007635302045e-05,
      "loss": 0.6898,
      "step": 1340
    },
    {
      "epoch": 0.432,
      "grad_norm": 9.999999046325684,
      "learning_rate": 9.010779249943859e-05,
      "loss": 0.6261,
      "step": 1350
    },
    {
      "epoch": 0.4352,
      "grad_norm": 10.0,
      "learning_rate": 8.999550864585672e-05,
      "loss": 0.6267,
      "step": 1360
    },
    {
      "epoch": 0.4384,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.988322479227488e-05,
      "loss": 0.6171,
      "step": 1370
    },
    {
      "epoch": 0.4416,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.977094093869301e-05,
      "loss": 0.5677,
      "step": 1380
    },
    {
      "epoch": 0.4448,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.965865708511116e-05,
      "loss": 0.5227,
      "step": 1390
    },
    {
      "epoch": 0.448,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.954637323152931e-05,
      "loss": 0.5775,
      "step": 1400
    },
    {
      "epoch": 0.4512,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.943408937794746e-05,
      "loss": 0.6166,
      "step": 1410
    },
    {
      "epoch": 0.4544,
      "grad_norm": 10.0,
      "learning_rate": 8.93218055243656e-05,
      "loss": 0.6165,
      "step": 1420
    },
    {
      "epoch": 0.4576,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.920952167078375e-05,
      "loss": 0.5849,
      "step": 1430
    },
    {
      "epoch": 0.4608,
      "grad_norm": 10.0,
      "learning_rate": 8.909723781720189e-05,
      "loss": 0.6439,
      "step": 1440
    },
    {
      "epoch": 0.464,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.898495396362003e-05,
      "loss": 0.5886,
      "step": 1450
    },
    {
      "epoch": 0.4672,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.887267011003818e-05,
      "loss": 0.5935,
      "step": 1460
    },
    {
      "epoch": 0.4704,
      "grad_norm": 10.0,
      "learning_rate": 8.876038625645633e-05,
      "loss": 0.5868,
      "step": 1470
    },
    {
      "epoch": 0.4736,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.864810240287447e-05,
      "loss": 0.5489,
      "step": 1480
    },
    {
      "epoch": 0.4768,
      "grad_norm": 10.0,
      "learning_rate": 8.853581854929262e-05,
      "loss": 0.5106,
      "step": 1490
    },
    {
      "epoch": 0.48,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.842353469571077e-05,
      "loss": 0.4885,
      "step": 1500
    },
    {
      "epoch": 0.4832,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.83112508421289e-05,
      "loss": 0.5323,
      "step": 1510
    },
    {
      "epoch": 0.4864,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.819896698854705e-05,
      "loss": 0.4359,
      "step": 1520
    },
    {
      "epoch": 0.4896,
      "grad_norm": 7.423900604248047,
      "learning_rate": 8.808668313496519e-05,
      "loss": 0.4789,
      "step": 1530
    },
    {
      "epoch": 0.4928,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.797439928138334e-05,
      "loss": 0.4367,
      "step": 1540
    },
    {
      "epoch": 0.496,
      "grad_norm": 7.3594489097595215,
      "learning_rate": 8.786211542780148e-05,
      "loss": 0.465,
      "step": 1550
    },
    {
      "epoch": 0.4992,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.774983157421963e-05,
      "loss": 0.4244,
      "step": 1560
    },
    {
      "epoch": 0.5024,
      "grad_norm": 10.0,
      "learning_rate": 8.763754772063778e-05,
      "loss": 0.4311,
      "step": 1570
    },
    {
      "epoch": 0.5056,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.752526386705592e-05,
      "loss": 0.4787,
      "step": 1580
    },
    {
      "epoch": 0.5088,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.741298001347407e-05,
      "loss": 0.4777,
      "step": 1590
    },
    {
      "epoch": 0.512,
      "grad_norm": 10.0,
      "learning_rate": 8.730069615989222e-05,
      "loss": 0.469,
      "step": 1600
    },
    {
      "epoch": 0.5152,
      "grad_norm": 10.0,
      "learning_rate": 8.718841230631036e-05,
      "loss": 0.4519,
      "step": 1610
    },
    {
      "epoch": 0.5184,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.70761284527285e-05,
      "loss": 0.4084,
      "step": 1620
    },
    {
      "epoch": 0.5216,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.696384459914664e-05,
      "loss": 0.3627,
      "step": 1630
    },
    {
      "epoch": 0.5248,
      "grad_norm": 8.502776145935059,
      "learning_rate": 8.68515607455648e-05,
      "loss": 0.3742,
      "step": 1640
    },
    {
      "epoch": 0.528,
      "grad_norm": 10.0,
      "learning_rate": 8.673927689198293e-05,
      "loss": 0.3525,
      "step": 1650
    },
    {
      "epoch": 0.5312,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.662699303840108e-05,
      "loss": 0.3889,
      "step": 1660
    },
    {
      "epoch": 0.5344,
      "grad_norm": 10.0,
      "learning_rate": 8.651470918481923e-05,
      "loss": 0.5584,
      "step": 1670
    },
    {
      "epoch": 0.5376,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.640242533123737e-05,
      "loss": 0.3988,
      "step": 1680
    },
    {
      "epoch": 0.5408,
      "grad_norm": 8.782861709594727,
      "learning_rate": 8.629014147765552e-05,
      "loss": 0.3439,
      "step": 1690
    },
    {
      "epoch": 0.544,
      "grad_norm": 8.174032211303711,
      "learning_rate": 8.617785762407367e-05,
      "loss": 0.3265,
      "step": 1700
    },
    {
      "epoch": 0.5472,
      "grad_norm": 4.737403392791748,
      "learning_rate": 8.606557377049181e-05,
      "loss": 0.329,
      "step": 1710
    },
    {
      "epoch": 0.5504,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.595328991690995e-05,
      "loss": 0.3093,
      "step": 1720
    },
    {
      "epoch": 0.5536,
      "grad_norm": 10.0,
      "learning_rate": 8.58410060633281e-05,
      "loss": 0.3119,
      "step": 1730
    },
    {
      "epoch": 0.5568,
      "grad_norm": 10.0,
      "learning_rate": 8.572872220974623e-05,
      "loss": 0.3227,
      "step": 1740
    },
    {
      "epoch": 0.56,
      "grad_norm": 9.882418632507324,
      "learning_rate": 8.561643835616438e-05,
      "loss": 0.2979,
      "step": 1750
    },
    {
      "epoch": 0.5632,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.550415450258253e-05,
      "loss": 0.2693,
      "step": 1760
    },
    {
      "epoch": 0.5664,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.539187064900069e-05,
      "loss": 0.3187,
      "step": 1770
    },
    {
      "epoch": 0.5696,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.527958679541882e-05,
      "loss": 0.291,
      "step": 1780
    },
    {
      "epoch": 0.5728,
      "grad_norm": 7.839264869689941,
      "learning_rate": 8.516730294183697e-05,
      "loss": 0.2833,
      "step": 1790
    },
    {
      "epoch": 0.576,
      "grad_norm": 4.611258029937744,
      "learning_rate": 8.505501908825511e-05,
      "loss": 0.2525,
      "step": 1800
    },
    {
      "epoch": 0.5792,
      "grad_norm": 4.125186443328857,
      "learning_rate": 8.494273523467325e-05,
      "loss": 0.2727,
      "step": 1810
    },
    {
      "epoch": 0.5824,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.48304513810914e-05,
      "loss": 0.2718,
      "step": 1820
    },
    {
      "epoch": 0.5856,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.471816752750955e-05,
      "loss": 0.2787,
      "step": 1830
    },
    {
      "epoch": 0.5888,
      "grad_norm": 4.507540225982666,
      "learning_rate": 8.460588367392769e-05,
      "loss": 0.2903,
      "step": 1840
    },
    {
      "epoch": 0.592,
      "grad_norm": 8.763723373413086,
      "learning_rate": 8.449359982034584e-05,
      "loss": 0.2821,
      "step": 1850
    },
    {
      "epoch": 0.5952,
      "grad_norm": 6.04974365234375,
      "learning_rate": 8.438131596676399e-05,
      "loss": 0.2469,
      "step": 1860
    },
    {
      "epoch": 0.5984,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.426903211318214e-05,
      "loss": 0.2389,
      "step": 1870
    },
    {
      "epoch": 0.6016,
      "grad_norm": 10.0,
      "learning_rate": 8.415674825960028e-05,
      "loss": 0.2749,
      "step": 1880
    },
    {
      "epoch": 0.6048,
      "grad_norm": 10.0,
      "learning_rate": 8.404446440601843e-05,
      "loss": 0.2829,
      "step": 1890
    },
    {
      "epoch": 0.608,
      "grad_norm": 9.99999713897705,
      "learning_rate": 8.393218055243656e-05,
      "loss": 0.2725,
      "step": 1900
    },
    {
      "epoch": 0.6112,
      "grad_norm": 10.000001907348633,
      "learning_rate": 8.38198966988547e-05,
      "loss": 0.2698,
      "step": 1910
    },
    {
      "epoch": 0.6144,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.370761284527285e-05,
      "loss": 0.2678,
      "step": 1920
    },
    {
      "epoch": 0.6176,
      "grad_norm": 10.0,
      "learning_rate": 8.3595328991691e-05,
      "loss": 0.2741,
      "step": 1930
    },
    {
      "epoch": 0.6208,
      "grad_norm": 10.0,
      "learning_rate": 8.348304513810914e-05,
      "loss": 0.2475,
      "step": 1940
    },
    {
      "epoch": 0.624,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.337076128452729e-05,
      "loss": 0.2711,
      "step": 1950
    },
    {
      "epoch": 0.6272,
      "grad_norm": 10.0,
      "learning_rate": 8.325847743094544e-05,
      "loss": 0.2592,
      "step": 1960
    },
    {
      "epoch": 0.6304,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.314619357736358e-05,
      "loss": 0.2348,
      "step": 1970
    },
    {
      "epoch": 0.6336,
      "grad_norm": 7.087158679962158,
      "learning_rate": 8.303390972378173e-05,
      "loss": 0.2185,
      "step": 1980
    },
    {
      "epoch": 0.6368,
      "grad_norm": 6.557620048522949,
      "learning_rate": 8.292162587019986e-05,
      "loss": 0.2443,
      "step": 1990
    },
    {
      "epoch": 0.64,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.280934201661802e-05,
      "loss": 0.2012,
      "step": 2000
    },
    {
      "epoch": 0.6432,
      "grad_norm": 8.828990936279297,
      "learning_rate": 8.269705816303615e-05,
      "loss": 0.1992,
      "step": 2010
    },
    {
      "epoch": 0.6464,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.25847743094543e-05,
      "loss": 0.2005,
      "step": 2020
    },
    {
      "epoch": 0.6496,
      "grad_norm": 10.0,
      "learning_rate": 8.247249045587245e-05,
      "loss": 0.2244,
      "step": 2030
    },
    {
      "epoch": 0.6528,
      "grad_norm": 10.0,
      "learning_rate": 8.236020660229059e-05,
      "loss": 0.3351,
      "step": 2040
    },
    {
      "epoch": 0.656,
      "grad_norm": 10.0,
      "learning_rate": 8.224792274870874e-05,
      "loss": 0.3391,
      "step": 2050
    },
    {
      "epoch": 0.6592,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.213563889512689e-05,
      "loss": 0.2319,
      "step": 2060
    },
    {
      "epoch": 0.6624,
      "grad_norm": 10.0,
      "learning_rate": 8.202335504154503e-05,
      "loss": 0.2222,
      "step": 2070
    },
    {
      "epoch": 0.6656,
      "grad_norm": 8.043660163879395,
      "learning_rate": 8.191107118796317e-05,
      "loss": 0.1829,
      "step": 2080
    },
    {
      "epoch": 0.6688,
      "grad_norm": 5.343007564544678,
      "learning_rate": 8.179878733438132e-05,
      "loss": 0.1756,
      "step": 2090
    },
    {
      "epoch": 0.672,
      "grad_norm": 3.530430316925049,
      "learning_rate": 8.168650348079947e-05,
      "loss": 0.1959,
      "step": 2100
    },
    {
      "epoch": 0.6752,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.15742196272176e-05,
      "loss": 0.178,
      "step": 2110
    },
    {
      "epoch": 0.6784,
      "grad_norm": 10.0,
      "learning_rate": 8.146193577363576e-05,
      "loss": 0.1867,
      "step": 2120
    },
    {
      "epoch": 0.6816,
      "grad_norm": 8.584357261657715,
      "learning_rate": 8.13496519200539e-05,
      "loss": 0.1832,
      "step": 2130
    },
    {
      "epoch": 0.6848,
      "grad_norm": 4.891357421875,
      "learning_rate": 8.123736806647204e-05,
      "loss": 0.1771,
      "step": 2140
    },
    {
      "epoch": 0.688,
      "grad_norm": 5.522593021392822,
      "learning_rate": 8.11250842128902e-05,
      "loss": 0.1527,
      "step": 2150
    },
    {
      "epoch": 0.6912,
      "grad_norm": 9.386947631835938,
      "learning_rate": 8.101280035930835e-05,
      "loss": 0.1769,
      "step": 2160
    },
    {
      "epoch": 0.6944,
      "grad_norm": 10.0,
      "learning_rate": 8.090051650572648e-05,
      "loss": 0.1889,
      "step": 2170
    },
    {
      "epoch": 0.6976,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.078823265214462e-05,
      "loss": 0.1827,
      "step": 2180
    },
    {
      "epoch": 0.7008,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.067594879856277e-05,
      "loss": 0.2055,
      "step": 2190
    },
    {
      "epoch": 0.704,
      "grad_norm": 9.999998092651367,
      "learning_rate": 8.056366494498092e-05,
      "loss": 0.1802,
      "step": 2200
    },
    {
      "epoch": 0.7072,
      "grad_norm": 9.999999046325684,
      "learning_rate": 8.045138109139906e-05,
      "loss": 0.1706,
      "step": 2210
    },
    {
      "epoch": 0.7104,
      "grad_norm": 3.970720052719116,
      "learning_rate": 8.033909723781721e-05,
      "loss": 0.1604,
      "step": 2220
    },
    {
      "epoch": 0.7136,
      "grad_norm": 3.6069769859313965,
      "learning_rate": 8.022681338423536e-05,
      "loss": 0.1453,
      "step": 2230
    },
    {
      "epoch": 0.7168,
      "grad_norm": 3.9357783794403076,
      "learning_rate": 8.01145295306535e-05,
      "loss": 0.1516,
      "step": 2240
    },
    {
      "epoch": 0.72,
      "grad_norm": 5.958951950073242,
      "learning_rate": 8.000224567707165e-05,
      "loss": 0.1512,
      "step": 2250
    },
    {
      "epoch": 0.7232,
      "grad_norm": 9.320231437683105,
      "learning_rate": 7.988996182348978e-05,
      "loss": 0.1642,
      "step": 2260
    },
    {
      "epoch": 0.7264,
      "grad_norm": 4.681884765625,
      "learning_rate": 7.977767796990792e-05,
      "loss": 0.1613,
      "step": 2270
    },
    {
      "epoch": 0.7296,
      "grad_norm": 7.769372940063477,
      "learning_rate": 7.966539411632607e-05,
      "loss": 0.1544,
      "step": 2280
    },
    {
      "epoch": 0.7328,
      "grad_norm": 4.547751426696777,
      "learning_rate": 7.955311026274422e-05,
      "loss": 0.1636,
      "step": 2290
    },
    {
      "epoch": 0.736,
      "grad_norm": 8.214717864990234,
      "learning_rate": 7.944082640916236e-05,
      "loss": 0.1372,
      "step": 2300
    },
    {
      "epoch": 0.7392,
      "grad_norm": 7.887718677520752,
      "learning_rate": 7.932854255558051e-05,
      "loss": 0.158,
      "step": 2310
    },
    {
      "epoch": 0.7424,
      "grad_norm": 9.999999046325684,
      "learning_rate": 7.921625870199866e-05,
      "loss": 0.1611,
      "step": 2320
    },
    {
      "epoch": 0.7456,
      "grad_norm": 3.0139806270599365,
      "learning_rate": 7.910397484841681e-05,
      "loss": 0.1584,
      "step": 2330
    },
    {
      "epoch": 0.7488,
      "grad_norm": 5.308823585510254,
      "learning_rate": 7.899169099483495e-05,
      "loss": 0.1489,
      "step": 2340
    },
    {
      "epoch": 0.752,
      "grad_norm": 1.894464373588562,
      "learning_rate": 7.887940714125309e-05,
      "loss": 0.1335,
      "step": 2350
    },
    {
      "epoch": 0.7552,
      "grad_norm": 8.55656909942627,
      "learning_rate": 7.876712328767124e-05,
      "loss": 0.1363,
      "step": 2360
    },
    {
      "epoch": 0.7584,
      "grad_norm": 7.630896091461182,
      "learning_rate": 7.865483943408937e-05,
      "loss": 0.1398,
      "step": 2370
    },
    {
      "epoch": 0.7616,
      "grad_norm": 9.361071586608887,
      "learning_rate": 7.854255558050752e-05,
      "loss": 0.1307,
      "step": 2380
    },
    {
      "epoch": 0.7648,
      "grad_norm": 3.613555431365967,
      "learning_rate": 7.843027172692568e-05,
      "loss": 0.1461,
      "step": 2390
    },
    {
      "epoch": 0.768,
      "grad_norm": 4.020608901977539,
      "learning_rate": 7.831798787334381e-05,
      "loss": 0.1432,
      "step": 2400
    },
    {
      "epoch": 0.7712,
      "grad_norm": 6.401773452758789,
      "learning_rate": 7.820570401976196e-05,
      "loss": 0.1396,
      "step": 2410
    },
    {
      "epoch": 0.7744,
      "grad_norm": 6.332232475280762,
      "learning_rate": 7.809342016618011e-05,
      "loss": 0.1355,
      "step": 2420
    },
    {
      "epoch": 0.7776,
      "grad_norm": 2.399341344833374,
      "learning_rate": 7.798113631259825e-05,
      "loss": 0.1416,
      "step": 2430
    },
    {
      "epoch": 0.7808,
      "grad_norm": 5.8365654945373535,
      "learning_rate": 7.78688524590164e-05,
      "loss": 0.1265,
      "step": 2440
    },
    {
      "epoch": 0.784,
      "grad_norm": 10.0,
      "learning_rate": 7.775656860543454e-05,
      "loss": 0.6647,
      "step": 2450
    },
    {
      "epoch": 0.7872,
      "grad_norm": 5.435879230499268,
      "learning_rate": 7.764428475185269e-05,
      "loss": 0.1334,
      "step": 2460
    },
    {
      "epoch": 0.7904,
      "grad_norm": 10.0,
      "learning_rate": 7.753200089827083e-05,
      "loss": 0.1284,
      "step": 2470
    },
    {
      "epoch": 0.7936,
      "grad_norm": 7.202799320220947,
      "learning_rate": 7.741971704468898e-05,
      "loss": 0.1369,
      "step": 2480
    },
    {
      "epoch": 0.7968,
      "grad_norm": 2.0989317893981934,
      "learning_rate": 7.730743319110713e-05,
      "loss": 0.1105,
      "step": 2490
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.924466609954834,
      "learning_rate": 7.719514933752526e-05,
      "loss": 0.1226,
      "step": 2500
    },
    {
      "epoch": 0.8032,
      "grad_norm": 7.978616714477539,
      "learning_rate": 7.708286548394342e-05,
      "loss": 0.1089,
      "step": 2510
    },
    {
      "epoch": 0.8064,
      "grad_norm": 4.150684356689453,
      "learning_rate": 7.697058163036157e-05,
      "loss": 0.1234,
      "step": 2520
    },
    {
      "epoch": 0.8096,
      "grad_norm": 4.818097114562988,
      "learning_rate": 7.68582977767797e-05,
      "loss": 0.1188,
      "step": 2530
    },
    {
      "epoch": 0.8128,
      "grad_norm": 2.5419697761535645,
      "learning_rate": 7.674601392319784e-05,
      "loss": 0.113,
      "step": 2540
    },
    {
      "epoch": 0.816,
      "grad_norm": 5.721562385559082,
      "learning_rate": 7.663373006961599e-05,
      "loss": 0.109,
      "step": 2550
    },
    {
      "epoch": 0.8192,
      "grad_norm": 2.7478086948394775,
      "learning_rate": 7.652144621603414e-05,
      "loss": 0.101,
      "step": 2560
    },
    {
      "epoch": 0.8224,
      "grad_norm": 9.692163467407227,
      "learning_rate": 7.640916236245228e-05,
      "loss": 0.1156,
      "step": 2570
    },
    {
      "epoch": 0.8256,
      "grad_norm": 6.791487693786621,
      "learning_rate": 7.629687850887043e-05,
      "loss": 0.12,
      "step": 2580
    },
    {
      "epoch": 0.8288,
      "grad_norm": 4.655740261077881,
      "learning_rate": 7.618459465528858e-05,
      "loss": 0.114,
      "step": 2590
    },
    {
      "epoch": 0.832,
      "grad_norm": 2.558154344558716,
      "learning_rate": 7.607231080170672e-05,
      "loss": 0.102,
      "step": 2600
    },
    {
      "epoch": 0.8352,
      "grad_norm": 5.348006725311279,
      "learning_rate": 7.596002694812487e-05,
      "loss": 0.156,
      "step": 2610
    },
    {
      "epoch": 0.8384,
      "grad_norm": 4.152245044708252,
      "learning_rate": 7.5847743094543e-05,
      "loss": 0.1256,
      "step": 2620
    },
    {
      "epoch": 0.8416,
      "grad_norm": 6.711794853210449,
      "learning_rate": 7.573545924096114e-05,
      "loss": 0.1184,
      "step": 2630
    },
    {
      "epoch": 0.8448,
      "grad_norm": 6.55480432510376,
      "learning_rate": 7.562317538737929e-05,
      "loss": 0.1253,
      "step": 2640
    },
    {
      "epoch": 0.848,
      "grad_norm": 6.035834312438965,
      "learning_rate": 7.551089153379744e-05,
      "loss": 0.125,
      "step": 2650
    },
    {
      "epoch": 0.8512,
      "grad_norm": 7.503954887390137,
      "learning_rate": 7.53986076802156e-05,
      "loss": 0.1068,
      "step": 2660
    },
    {
      "epoch": 0.8544,
      "grad_norm": 4.4410271644592285,
      "learning_rate": 7.528632382663373e-05,
      "loss": 0.1137,
      "step": 2670
    },
    {
      "epoch": 0.8576,
      "grad_norm": 4.127198696136475,
      "learning_rate": 7.517403997305188e-05,
      "loss": 0.1127,
      "step": 2680
    },
    {
      "epoch": 0.8608,
      "grad_norm": 3.0780539512634277,
      "learning_rate": 7.506175611947003e-05,
      "loss": 0.1009,
      "step": 2690
    },
    {
      "epoch": 0.864,
      "grad_norm": 8.409754753112793,
      "learning_rate": 7.494947226588817e-05,
      "loss": 0.1017,
      "step": 2700
    },
    {
      "epoch": 0.8672,
      "grad_norm": 4.118874549865723,
      "learning_rate": 7.483718841230631e-05,
      "loss": 0.1,
      "step": 2710
    },
    {
      "epoch": 0.8704,
      "grad_norm": 2.367293357849121,
      "learning_rate": 7.472490455872446e-05,
      "loss": 0.1019,
      "step": 2720
    },
    {
      "epoch": 0.8736,
      "grad_norm": 5.165258884429932,
      "learning_rate": 7.46126207051426e-05,
      "loss": 0.0891,
      "step": 2730
    },
    {
      "epoch": 0.8768,
      "grad_norm": 1.9673935174942017,
      "learning_rate": 7.450033685156075e-05,
      "loss": 0.0869,
      "step": 2740
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.972908020019531,
      "learning_rate": 7.43880529979789e-05,
      "loss": 0.0894,
      "step": 2750
    },
    {
      "epoch": 0.8832,
      "grad_norm": 4.128866195678711,
      "learning_rate": 7.427576914439703e-05,
      "loss": 0.0888,
      "step": 2760
    },
    {
      "epoch": 0.8864,
      "grad_norm": 1.7406138181686401,
      "learning_rate": 7.416348529081518e-05,
      "loss": 0.0876,
      "step": 2770
    },
    {
      "epoch": 0.8896,
      "grad_norm": 1.7218992710113525,
      "learning_rate": 7.405120143723333e-05,
      "loss": 0.0925,
      "step": 2780
    },
    {
      "epoch": 0.8928,
      "grad_norm": 2.668508768081665,
      "learning_rate": 7.393891758365149e-05,
      "loss": 0.0872,
      "step": 2790
    },
    {
      "epoch": 0.896,
      "grad_norm": 5.266975402832031,
      "learning_rate": 7.382663373006962e-05,
      "loss": 0.083,
      "step": 2800
    },
    {
      "epoch": 0.8992,
      "grad_norm": 2.1134185791015625,
      "learning_rate": 7.371434987648776e-05,
      "loss": 0.0871,
      "step": 2810
    },
    {
      "epoch": 0.9024,
      "grad_norm": 4.195724010467529,
      "learning_rate": 7.360206602290591e-05,
      "loss": 0.0941,
      "step": 2820
    },
    {
      "epoch": 0.9056,
      "grad_norm": 2.4259421825408936,
      "learning_rate": 7.348978216932405e-05,
      "loss": 0.0937,
      "step": 2830
    },
    {
      "epoch": 0.9088,
      "grad_norm": 2.7671356201171875,
      "learning_rate": 7.33774983157422e-05,
      "loss": 0.095,
      "step": 2840
    },
    {
      "epoch": 0.912,
      "grad_norm": 6.370889663696289,
      "learning_rate": 7.326521446216035e-05,
      "loss": 0.0826,
      "step": 2850
    },
    {
      "epoch": 0.9152,
      "grad_norm": 6.082813739776611,
      "learning_rate": 7.315293060857849e-05,
      "loss": 0.0891,
      "step": 2860
    },
    {
      "epoch": 0.9184,
      "grad_norm": 4.761292934417725,
      "learning_rate": 7.304064675499664e-05,
      "loss": 0.0905,
      "step": 2870
    },
    {
      "epoch": 0.9216,
      "grad_norm": 3.1539108753204346,
      "learning_rate": 7.292836290141479e-05,
      "loss": 0.0836,
      "step": 2880
    },
    {
      "epoch": 0.9248,
      "grad_norm": 3.095581531524658,
      "learning_rate": 7.281607904783292e-05,
      "loss": 0.0782,
      "step": 2890
    },
    {
      "epoch": 0.928,
      "grad_norm": 2.6302435398101807,
      "learning_rate": 7.270379519425106e-05,
      "loss": 0.0844,
      "step": 2900
    },
    {
      "epoch": 0.9312,
      "grad_norm": 4.609825134277344,
      "learning_rate": 7.259151134066921e-05,
      "loss": 0.0773,
      "step": 2910
    },
    {
      "epoch": 0.9344,
      "grad_norm": 6.823300361633301,
      "learning_rate": 7.247922748708736e-05,
      "loss": 0.0811,
      "step": 2920
    },
    {
      "epoch": 0.9376,
      "grad_norm": 2.5662624835968018,
      "learning_rate": 7.23669436335055e-05,
      "loss": 0.0751,
      "step": 2930
    },
    {
      "epoch": 0.9408,
      "grad_norm": 1.9695119857788086,
      "learning_rate": 7.225465977992365e-05,
      "loss": 0.087,
      "step": 2940
    },
    {
      "epoch": 0.944,
      "grad_norm": 3.3225550651550293,
      "learning_rate": 7.21423759263418e-05,
      "loss": 0.0825,
      "step": 2950
    },
    {
      "epoch": 0.9472,
      "grad_norm": 3.849437713623047,
      "learning_rate": 7.203009207275994e-05,
      "loss": 0.0767,
      "step": 2960
    },
    {
      "epoch": 0.9504,
      "grad_norm": 1.750457525253296,
      "learning_rate": 7.191780821917809e-05,
      "loss": 0.0882,
      "step": 2970
    },
    {
      "epoch": 0.9536,
      "grad_norm": 6.477813243865967,
      "learning_rate": 7.180552436559623e-05,
      "loss": 0.0919,
      "step": 2980
    },
    {
      "epoch": 0.9568,
      "grad_norm": 1.4271601438522339,
      "learning_rate": 7.169324051201438e-05,
      "loss": 0.0804,
      "step": 2990
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.061021327972412,
      "learning_rate": 7.158095665843251e-05,
      "loss": 0.0832,
      "step": 3000
    },
    {
      "epoch": 0.9632,
      "grad_norm": 2.1753170490264893,
      "learning_rate": 7.146867280485066e-05,
      "loss": 0.0741,
      "step": 3010
    },
    {
      "epoch": 0.9664,
      "grad_norm": 7.894692897796631,
      "learning_rate": 7.135638895126882e-05,
      "loss": 0.0723,
      "step": 3020
    },
    {
      "epoch": 0.9696,
      "grad_norm": 2.4842376708984375,
      "learning_rate": 7.124410509768695e-05,
      "loss": 0.0746,
      "step": 3030
    },
    {
      "epoch": 0.9728,
      "grad_norm": 4.693914413452148,
      "learning_rate": 7.11318212441051e-05,
      "loss": 0.0818,
      "step": 3040
    },
    {
      "epoch": 0.976,
      "grad_norm": 3.4993011951446533,
      "learning_rate": 7.101953739052325e-05,
      "loss": 0.0743,
      "step": 3050
    },
    {
      "epoch": 0.9792,
      "grad_norm": 2.4109108448028564,
      "learning_rate": 7.090725353694139e-05,
      "loss": 0.0698,
      "step": 3060
    },
    {
      "epoch": 0.9824,
      "grad_norm": 3.363265037536621,
      "learning_rate": 7.079496968335954e-05,
      "loss": 0.076,
      "step": 3070
    },
    {
      "epoch": 0.9856,
      "grad_norm": 4.7013959884643555,
      "learning_rate": 7.068268582977768e-05,
      "loss": 0.0801,
      "step": 3080
    },
    {
      "epoch": 0.9888,
      "grad_norm": 1.858520269393921,
      "learning_rate": 7.057040197619582e-05,
      "loss": 0.0691,
      "step": 3090
    },
    {
      "epoch": 0.992,
      "grad_norm": 2.71395206451416,
      "learning_rate": 7.045811812261397e-05,
      "loss": 0.0811,
      "step": 3100
    },
    {
      "epoch": 0.9952,
      "grad_norm": 3.254763603210449,
      "learning_rate": 7.034583426903212e-05,
      "loss": 0.0772,
      "step": 3110
    },
    {
      "epoch": 0.9984,
      "grad_norm": 6.519776821136475,
      "learning_rate": 7.023355041545027e-05,
      "loss": 0.0718,
      "step": 3120
    },
    {
      "epoch": 1.0016,
      "grad_norm": 1.91741144657135,
      "learning_rate": 7.01212665618684e-05,
      "loss": 0.0746,
      "step": 3130
    },
    {
      "epoch": 1.0048,
      "grad_norm": 1.5471233129501343,
      "learning_rate": 7.000898270828656e-05,
      "loss": 0.071,
      "step": 3140
    },
    {
      "epoch": 1.008,
      "grad_norm": 3.8411548137664795,
      "learning_rate": 6.98966988547047e-05,
      "loss": 0.0646,
      "step": 3150
    },
    {
      "epoch": 1.0112,
      "grad_norm": 4.6282267570495605,
      "learning_rate": 6.978441500112284e-05,
      "loss": 0.068,
      "step": 3160
    },
    {
      "epoch": 1.0144,
      "grad_norm": 3.1158607006073,
      "learning_rate": 6.967213114754098e-05,
      "loss": 0.0706,
      "step": 3170
    },
    {
      "epoch": 1.0176,
      "grad_norm": 4.9777913093566895,
      "learning_rate": 6.955984729395913e-05,
      "loss": 0.0711,
      "step": 3180
    },
    {
      "epoch": 1.0208,
      "grad_norm": 2.6763927936553955,
      "learning_rate": 6.944756344037727e-05,
      "loss": 0.0649,
      "step": 3190
    },
    {
      "epoch": 1.024,
      "grad_norm": 4.165836334228516,
      "learning_rate": 6.933527958679542e-05,
      "loss": 0.066,
      "step": 3200
    },
    {
      "epoch": 1.0272,
      "grad_norm": 9.641294479370117,
      "learning_rate": 6.922299573321357e-05,
      "loss": 0.068,
      "step": 3210
    },
    {
      "epoch": 1.0304,
      "grad_norm": 2.3524587154388428,
      "learning_rate": 6.911071187963172e-05,
      "loss": 0.0695,
      "step": 3220
    },
    {
      "epoch": 1.0336,
      "grad_norm": 3.930358648300171,
      "learning_rate": 6.899842802604986e-05,
      "loss": 0.0869,
      "step": 3230
    },
    {
      "epoch": 1.0368,
      "grad_norm": 3.403099298477173,
      "learning_rate": 6.888614417246801e-05,
      "loss": 0.0734,
      "step": 3240
    },
    {
      "epoch": 1.04,
      "grad_norm": 4.471584796905518,
      "learning_rate": 6.877386031888615e-05,
      "loss": 0.0729,
      "step": 3250
    },
    {
      "epoch": 1.0432,
      "grad_norm": 2.041577100753784,
      "learning_rate": 6.866157646530428e-05,
      "loss": 0.0649,
      "step": 3260
    },
    {
      "epoch": 1.0464,
      "grad_norm": 4.053502559661865,
      "learning_rate": 6.854929261172243e-05,
      "loss": 0.068,
      "step": 3270
    },
    {
      "epoch": 1.0496,
      "grad_norm": 1.712865948677063,
      "learning_rate": 6.843700875814058e-05,
      "loss": 0.0693,
      "step": 3280
    },
    {
      "epoch": 1.0528,
      "grad_norm": 8.817410469055176,
      "learning_rate": 6.832472490455872e-05,
      "loss": 0.073,
      "step": 3290
    },
    {
      "epoch": 1.056,
      "grad_norm": 1.9689174890518188,
      "learning_rate": 6.821244105097687e-05,
      "loss": 0.0665,
      "step": 3300
    },
    {
      "epoch": 1.0592,
      "grad_norm": 4.147378921508789,
      "learning_rate": 6.810015719739502e-05,
      "loss": 0.0683,
      "step": 3310
    },
    {
      "epoch": 1.0624,
      "grad_norm": 3.4082727432250977,
      "learning_rate": 6.798787334381316e-05,
      "loss": 0.0635,
      "step": 3320
    },
    {
      "epoch": 1.0656,
      "grad_norm": 1.8768893480300903,
      "learning_rate": 6.787558949023131e-05,
      "loss": 0.0587,
      "step": 3330
    },
    {
      "epoch": 1.0688,
      "grad_norm": 1.7891249656677246,
      "learning_rate": 6.776330563664946e-05,
      "loss": 0.0628,
      "step": 3340
    },
    {
      "epoch": 1.072,
      "grad_norm": 1.5056793689727783,
      "learning_rate": 6.76510217830676e-05,
      "loss": 0.059,
      "step": 3350
    },
    {
      "epoch": 1.0752,
      "grad_norm": 2.3811066150665283,
      "learning_rate": 6.753873792948574e-05,
      "loss": 0.0642,
      "step": 3360
    },
    {
      "epoch": 1.0784,
      "grad_norm": 4.5819902420043945,
      "learning_rate": 6.742645407590389e-05,
      "loss": 0.0573,
      "step": 3370
    },
    {
      "epoch": 1.0816,
      "grad_norm": 3.9442105293273926,
      "learning_rate": 6.731417022232204e-05,
      "loss": 0.0926,
      "step": 3380
    },
    {
      "epoch": 1.0848,
      "grad_norm": 4.184739112854004,
      "learning_rate": 6.720188636874017e-05,
      "loss": 0.0765,
      "step": 3390
    },
    {
      "epoch": 1.088,
      "grad_norm": 2.208756446838379,
      "learning_rate": 6.708960251515832e-05,
      "loss": 0.0657,
      "step": 3400
    },
    {
      "epoch": 1.0912,
      "grad_norm": 1.9726155996322632,
      "learning_rate": 6.697731866157648e-05,
      "loss": 0.0584,
      "step": 3410
    },
    {
      "epoch": 1.0944,
      "grad_norm": 2.3560941219329834,
      "learning_rate": 6.686503480799461e-05,
      "loss": 0.0663,
      "step": 3420
    },
    {
      "epoch": 1.0976,
      "grad_norm": 4.31378173828125,
      "learning_rate": 6.675275095441276e-05,
      "loss": 0.0652,
      "step": 3430
    },
    {
      "epoch": 1.1008,
      "grad_norm": 5.586067199707031,
      "learning_rate": 6.66404671008309e-05,
      "loss": 0.0619,
      "step": 3440
    },
    {
      "epoch": 1.104,
      "grad_norm": 4.057238578796387,
      "learning_rate": 6.652818324724905e-05,
      "loss": 0.0653,
      "step": 3450
    },
    {
      "epoch": 1.1072,
      "grad_norm": 2.5588834285736084,
      "learning_rate": 6.641589939366719e-05,
      "loss": 0.0647,
      "step": 3460
    },
    {
      "epoch": 1.1104,
      "grad_norm": 3.098489761352539,
      "learning_rate": 6.630361554008534e-05,
      "loss": 0.0604,
      "step": 3470
    },
    {
      "epoch": 1.1136,
      "grad_norm": 3.6659464836120605,
      "learning_rate": 6.619133168650349e-05,
      "loss": 0.0665,
      "step": 3480
    },
    {
      "epoch": 1.1168,
      "grad_norm": 2.530979633331299,
      "learning_rate": 6.607904783292163e-05,
      "loss": 0.059,
      "step": 3490
    },
    {
      "epoch": 1.12,
      "grad_norm": 4.6189374923706055,
      "learning_rate": 6.596676397933978e-05,
      "loss": 0.062,
      "step": 3500
    },
    {
      "epoch": 1.1232,
      "grad_norm": 2.125894784927368,
      "learning_rate": 6.585448012575793e-05,
      "loss": 0.0573,
      "step": 3510
    },
    {
      "epoch": 1.1264,
      "grad_norm": 3.884368896484375,
      "learning_rate": 6.574219627217606e-05,
      "loss": 0.0588,
      "step": 3520
    },
    {
      "epoch": 1.1296,
      "grad_norm": 4.213693141937256,
      "learning_rate": 6.56299124185942e-05,
      "loss": 0.0648,
      "step": 3530
    },
    {
      "epoch": 1.1328,
      "grad_norm": 4.863856315612793,
      "learning_rate": 6.551762856501235e-05,
      "loss": 0.0585,
      "step": 3540
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 2.9554522037506104,
      "learning_rate": 6.540534471143049e-05,
      "loss": 0.0584,
      "step": 3550
    },
    {
      "epoch": 1.1392,
      "grad_norm": 1.8812214136123657,
      "learning_rate": 6.529306085784864e-05,
      "loss": 0.0611,
      "step": 3560
    },
    {
      "epoch": 1.1424,
      "grad_norm": 2.52107572555542,
      "learning_rate": 6.518077700426679e-05,
      "loss": 0.0591,
      "step": 3570
    },
    {
      "epoch": 1.1456,
      "grad_norm": 3.270277500152588,
      "learning_rate": 6.506849315068494e-05,
      "loss": 0.0622,
      "step": 3580
    },
    {
      "epoch": 1.1488,
      "grad_norm": 2.0023467540740967,
      "learning_rate": 6.495620929710308e-05,
      "loss": 0.0586,
      "step": 3590
    },
    {
      "epoch": 1.152,
      "grad_norm": 2.0342307090759277,
      "learning_rate": 6.484392544352123e-05,
      "loss": 0.0517,
      "step": 3600
    },
    {
      "epoch": 1.1552,
      "grad_norm": 3.3358206748962402,
      "learning_rate": 6.473164158993938e-05,
      "loss": 0.0568,
      "step": 3610
    },
    {
      "epoch": 1.1584,
      "grad_norm": 1.158366322517395,
      "learning_rate": 6.461935773635752e-05,
      "loss": 0.0509,
      "step": 3620
    },
    {
      "epoch": 1.1616,
      "grad_norm": 1.7512037754058838,
      "learning_rate": 6.450707388277565e-05,
      "loss": 0.0642,
      "step": 3630
    },
    {
      "epoch": 1.1648,
      "grad_norm": 1.3442176580429077,
      "learning_rate": 6.43947900291938e-05,
      "loss": 0.0559,
      "step": 3640
    },
    {
      "epoch": 1.168,
      "grad_norm": 4.689185619354248,
      "learning_rate": 6.428250617561194e-05,
      "loss": 0.0565,
      "step": 3650
    },
    {
      "epoch": 1.1712,
      "grad_norm": 3.3459503650665283,
      "learning_rate": 6.417022232203009e-05,
      "loss": 0.0575,
      "step": 3660
    },
    {
      "epoch": 1.1743999999999999,
      "grad_norm": 2.5210814476013184,
      "learning_rate": 6.405793846844824e-05,
      "loss": 0.0534,
      "step": 3670
    },
    {
      "epoch": 1.1776,
      "grad_norm": 1.4273737668991089,
      "learning_rate": 6.39456546148664e-05,
      "loss": 0.0562,
      "step": 3680
    },
    {
      "epoch": 1.1808,
      "grad_norm": 3.007507562637329,
      "learning_rate": 6.383337076128453e-05,
      "loss": 0.0531,
      "step": 3690
    },
    {
      "epoch": 1.184,
      "grad_norm": 2.328012228012085,
      "learning_rate": 6.372108690770268e-05,
      "loss": 0.0521,
      "step": 3700
    },
    {
      "epoch": 1.1872,
      "grad_norm": 3.815755844116211,
      "learning_rate": 6.360880305412082e-05,
      "loss": 0.0586,
      "step": 3710
    },
    {
      "epoch": 1.1904,
      "grad_norm": 2.570431709289551,
      "learning_rate": 6.349651920053896e-05,
      "loss": 0.0559,
      "step": 3720
    },
    {
      "epoch": 1.1936,
      "grad_norm": 2.9417104721069336,
      "learning_rate": 6.338423534695711e-05,
      "loss": 0.0555,
      "step": 3730
    },
    {
      "epoch": 1.1968,
      "grad_norm": 1.5327764749526978,
      "learning_rate": 6.327195149337526e-05,
      "loss": 0.0515,
      "step": 3740
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.548718214035034,
      "learning_rate": 6.31596676397934e-05,
      "loss": 0.054,
      "step": 3750
    },
    {
      "epoch": 1.2032,
      "grad_norm": 1.7067848443984985,
      "learning_rate": 6.304738378621155e-05,
      "loss": 0.0552,
      "step": 3760
    },
    {
      "epoch": 1.2064,
      "grad_norm": 1.4624521732330322,
      "learning_rate": 6.29350999326297e-05,
      "loss": 0.0459,
      "step": 3770
    },
    {
      "epoch": 1.2096,
      "grad_norm": 4.673206329345703,
      "learning_rate": 6.282281607904783e-05,
      "loss": 0.0459,
      "step": 3780
    },
    {
      "epoch": 1.2128,
      "grad_norm": 2.1773905754089355,
      "learning_rate": 6.271053222546598e-05,
      "loss": 0.0515,
      "step": 3790
    },
    {
      "epoch": 1.216,
      "grad_norm": 4.247639179229736,
      "learning_rate": 6.259824837188412e-05,
      "loss": 0.0623,
      "step": 3800
    },
    {
      "epoch": 1.2192,
      "grad_norm": 2.148364543914795,
      "learning_rate": 6.248596451830227e-05,
      "loss": 17.18,
      "step": 3810
    },
    {
      "epoch": 1.2224,
      "grad_norm": 3.752838134765625,
      "learning_rate": 6.237368066472041e-05,
      "loss": 0.0535,
      "step": 3820
    },
    {
      "epoch": 1.2256,
      "grad_norm": 3.2757108211517334,
      "learning_rate": 6.226139681113856e-05,
      "loss": 0.0552,
      "step": 3830
    },
    {
      "epoch": 1.2288000000000001,
      "grad_norm": 2.085975408554077,
      "learning_rate": 6.214911295755671e-05,
      "loss": 0.0495,
      "step": 3840
    },
    {
      "epoch": 1.232,
      "grad_norm": 1.4556792974472046,
      "learning_rate": 6.203682910397485e-05,
      "loss": 0.0468,
      "step": 3850
    },
    {
      "epoch": 1.2352,
      "grad_norm": 1.6175802946090698,
      "learning_rate": 6.1924545250393e-05,
      "loss": 0.0583,
      "step": 3860
    },
    {
      "epoch": 1.2384,
      "grad_norm": 1.6184957027435303,
      "learning_rate": 6.181226139681115e-05,
      "loss": 0.0486,
      "step": 3870
    },
    {
      "epoch": 1.2416,
      "grad_norm": 9.999999046325684,
      "learning_rate": 6.169997754322929e-05,
      "loss": 0.0778,
      "step": 3880
    },
    {
      "epoch": 1.2448,
      "grad_norm": 7.507689952850342,
      "learning_rate": 6.158769368964744e-05,
      "loss": 0.0771,
      "step": 3890
    },
    {
      "epoch": 1.248,
      "grad_norm": 4.089766502380371,
      "learning_rate": 6.147540983606557e-05,
      "loss": 0.1067,
      "step": 3900
    },
    {
      "epoch": 1.2511999999999999,
      "grad_norm": 2.4886679649353027,
      "learning_rate": 6.136312598248372e-05,
      "loss": 0.069,
      "step": 3910
    },
    {
      "epoch": 1.2544,
      "grad_norm": 3.568296432495117,
      "learning_rate": 6.125084212890186e-05,
      "loss": 0.0643,
      "step": 3920
    },
    {
      "epoch": 1.2576,
      "grad_norm": 2.1102867126464844,
      "learning_rate": 6.113855827532001e-05,
      "loss": 0.0568,
      "step": 3930
    },
    {
      "epoch": 1.2608,
      "grad_norm": 1.3482815027236938,
      "learning_rate": 6.102627442173816e-05,
      "loss": 0.0591,
      "step": 3940
    },
    {
      "epoch": 1.264,
      "grad_norm": 2.092593193054199,
      "learning_rate": 6.09139905681563e-05,
      "loss": 0.0576,
      "step": 3950
    },
    {
      "epoch": 1.2671999999999999,
      "grad_norm": 2.106621503829956,
      "learning_rate": 6.0801706714574444e-05,
      "loss": 0.0484,
      "step": 3960
    },
    {
      "epoch": 1.2704,
      "grad_norm": 2.036658525466919,
      "learning_rate": 6.0689422860992595e-05,
      "loss": 0.0433,
      "step": 3970
    },
    {
      "epoch": 1.2736,
      "grad_norm": 1.402249813079834,
      "learning_rate": 6.057713900741073e-05,
      "loss": 0.0449,
      "step": 3980
    },
    {
      "epoch": 1.2768,
      "grad_norm": 2.1640737056732178,
      "learning_rate": 6.046485515382888e-05,
      "loss": 0.0482,
      "step": 3990
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.2044899463653564,
      "learning_rate": 6.0352571300247026e-05,
      "loss": 0.0463,
      "step": 4000
    },
    {
      "epoch": 1.2832,
      "grad_norm": 7.269384384155273,
      "learning_rate": 6.024028744666518e-05,
      "loss": 0.0549,
      "step": 4010
    },
    {
      "epoch": 1.2864,
      "grad_norm": 3.0673646926879883,
      "learning_rate": 6.0128003593083314e-05,
      "loss": 0.0522,
      "step": 4020
    },
    {
      "epoch": 1.2896,
      "grad_norm": 5.095019340515137,
      "learning_rate": 6.0015719739501465e-05,
      "loss": 0.0471,
      "step": 4030
    },
    {
      "epoch": 1.2928,
      "grad_norm": 3.6901588439941406,
      "learning_rate": 5.9903435885919615e-05,
      "loss": 0.0483,
      "step": 4040
    },
    {
      "epoch": 1.296,
      "grad_norm": 1.2914890050888062,
      "learning_rate": 5.979115203233775e-05,
      "loss": 0.0456,
      "step": 4050
    },
    {
      "epoch": 1.2992,
      "grad_norm": 2.4384307861328125,
      "learning_rate": 5.9678868178755896e-05,
      "loss": 0.0475,
      "step": 4060
    },
    {
      "epoch": 1.3024,
      "grad_norm": 1.596550703048706,
      "learning_rate": 5.956658432517405e-05,
      "loss": 0.0456,
      "step": 4070
    },
    {
      "epoch": 1.3056,
      "grad_norm": 1.6937170028686523,
      "learning_rate": 5.9454300471592184e-05,
      "loss": 0.0517,
      "step": 4080
    },
    {
      "epoch": 1.3088,
      "grad_norm": 1.587768316268921,
      "learning_rate": 5.9342016618010335e-05,
      "loss": 0.0437,
      "step": 4090
    },
    {
      "epoch": 1.312,
      "grad_norm": 4.193778991699219,
      "learning_rate": 5.922973276442848e-05,
      "loss": 0.0457,
      "step": 4100
    },
    {
      "epoch": 1.3152,
      "grad_norm": 2.494598865509033,
      "learning_rate": 5.9117448910846616e-05,
      "loss": 0.0479,
      "step": 4110
    },
    {
      "epoch": 1.3184,
      "grad_norm": 2.869279623031616,
      "learning_rate": 5.900516505726477e-05,
      "loss": 0.0433,
      "step": 4120
    },
    {
      "epoch": 1.3216,
      "grad_norm": 4.543278217315674,
      "learning_rate": 5.889288120368292e-05,
      "loss": 0.0519,
      "step": 4130
    },
    {
      "epoch": 1.3248,
      "grad_norm": 1.5083669424057007,
      "learning_rate": 5.878059735010106e-05,
      "loss": 0.0492,
      "step": 4140
    },
    {
      "epoch": 1.328,
      "grad_norm": 2.1934690475463867,
      "learning_rate": 5.86683134965192e-05,
      "loss": 0.0426,
      "step": 4150
    },
    {
      "epoch": 1.3312,
      "grad_norm": 2.10366153717041,
      "learning_rate": 5.855602964293735e-05,
      "loss": 0.0441,
      "step": 4160
    },
    {
      "epoch": 1.3344,
      "grad_norm": 1.6721271276474,
      "learning_rate": 5.84437457893555e-05,
      "loss": 0.0437,
      "step": 4170
    },
    {
      "epoch": 1.3376000000000001,
      "grad_norm": 4.587328910827637,
      "learning_rate": 5.833146193577364e-05,
      "loss": 0.0432,
      "step": 4180
    },
    {
      "epoch": 1.3408,
      "grad_norm": 2.2152934074401855,
      "learning_rate": 5.821917808219178e-05,
      "loss": 0.053,
      "step": 4190
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 3.132293224334717,
      "learning_rate": 5.810689422860993e-05,
      "loss": 0.05,
      "step": 4200
    },
    {
      "epoch": 1.3472,
      "grad_norm": 3.02851939201355,
      "learning_rate": 5.799461037502807e-05,
      "loss": 0.0408,
      "step": 4210
    },
    {
      "epoch": 1.3504,
      "grad_norm": 2.1754748821258545,
      "learning_rate": 5.788232652144622e-05,
      "loss": 0.046,
      "step": 4220
    },
    {
      "epoch": 1.3536000000000001,
      "grad_norm": 2.0088369846343994,
      "learning_rate": 5.777004266786436e-05,
      "loss": 0.0428,
      "step": 4230
    },
    {
      "epoch": 1.3568,
      "grad_norm": 2.7489728927612305,
      "learning_rate": 5.7657758814282514e-05,
      "loss": 0.0424,
      "step": 4240
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.6788060665130615,
      "learning_rate": 5.754547496070065e-05,
      "loss": 0.0448,
      "step": 4250
    },
    {
      "epoch": 1.3632,
      "grad_norm": 2.4949731826782227,
      "learning_rate": 5.74331911071188e-05,
      "loss": 0.041,
      "step": 4260
    },
    {
      "epoch": 1.3664,
      "grad_norm": 1.9527579545974731,
      "learning_rate": 5.7320907253536945e-05,
      "loss": 0.0441,
      "step": 4270
    },
    {
      "epoch": 1.3696,
      "grad_norm": 2.471604108810425,
      "learning_rate": 5.720862339995508e-05,
      "loss": 0.043,
      "step": 4280
    },
    {
      "epoch": 1.3728,
      "grad_norm": 4.944948196411133,
      "learning_rate": 5.709633954637323e-05,
      "loss": 0.0562,
      "step": 4290
    },
    {
      "epoch": 1.376,
      "grad_norm": 2.4510498046875,
      "learning_rate": 5.6984055692791384e-05,
      "loss": 0.0469,
      "step": 4300
    },
    {
      "epoch": 1.3792,
      "grad_norm": 1.1143766641616821,
      "learning_rate": 5.687177183920952e-05,
      "loss": 0.0428,
      "step": 4310
    },
    {
      "epoch": 1.3824,
      "grad_norm": 1.719165325164795,
      "learning_rate": 5.675948798562767e-05,
      "loss": 0.0448,
      "step": 4320
    },
    {
      "epoch": 1.3856,
      "grad_norm": 2.277461528778076,
      "learning_rate": 5.6647204132045816e-05,
      "loss": 0.0417,
      "step": 4330
    },
    {
      "epoch": 1.3888,
      "grad_norm": 3.449477195739746,
      "learning_rate": 5.653492027846395e-05,
      "loss": 0.038,
      "step": 4340
    },
    {
      "epoch": 1.392,
      "grad_norm": 2.189485549926758,
      "learning_rate": 5.6422636424882103e-05,
      "loss": 0.0396,
      "step": 4350
    },
    {
      "epoch": 1.3952,
      "grad_norm": 1.732558012008667,
      "learning_rate": 5.6310352571300254e-05,
      "loss": 0.0398,
      "step": 4360
    },
    {
      "epoch": 1.3984,
      "grad_norm": 2.732851266860962,
      "learning_rate": 5.61980687177184e-05,
      "loss": 0.0433,
      "step": 4370
    },
    {
      "epoch": 1.4016,
      "grad_norm": 1.4708316326141357,
      "learning_rate": 5.6085784864136535e-05,
      "loss": 0.0361,
      "step": 4380
    },
    {
      "epoch": 1.4048,
      "grad_norm": 2.114934206008911,
      "learning_rate": 5.5973501010554686e-05,
      "loss": 0.0438,
      "step": 4390
    },
    {
      "epoch": 1.408,
      "grad_norm": 4.473976135253906,
      "learning_rate": 5.5861217156972837e-05,
      "loss": 0.0421,
      "step": 4400
    },
    {
      "epoch": 1.4112,
      "grad_norm": 1.1676849126815796,
      "learning_rate": 5.5748933303390974e-05,
      "loss": 0.0437,
      "step": 4410
    },
    {
      "epoch": 1.4144,
      "grad_norm": 2.1100847721099854,
      "learning_rate": 5.563664944980912e-05,
      "loss": 0.0351,
      "step": 4420
    },
    {
      "epoch": 1.4176,
      "grad_norm": 2.426988124847412,
      "learning_rate": 5.552436559622727e-05,
      "loss": 0.0456,
      "step": 4430
    },
    {
      "epoch": 1.4208,
      "grad_norm": 3.200514078140259,
      "learning_rate": 5.5412081742645405e-05,
      "loss": 0.0381,
      "step": 4440
    },
    {
      "epoch": 1.424,
      "grad_norm": 1.525909423828125,
      "learning_rate": 5.5299797889063556e-05,
      "loss": 0.0414,
      "step": 4450
    },
    {
      "epoch": 1.4272,
      "grad_norm": 1.2169736623764038,
      "learning_rate": 5.51875140354817e-05,
      "loss": 0.0407,
      "step": 4460
    },
    {
      "epoch": 1.4304000000000001,
      "grad_norm": 4.590202808380127,
      "learning_rate": 5.507523018189985e-05,
      "loss": 0.0476,
      "step": 4470
    },
    {
      "epoch": 1.4336,
      "grad_norm": 1.4722408056259155,
      "learning_rate": 5.496294632831799e-05,
      "loss": 0.052,
      "step": 4480
    },
    {
      "epoch": 1.4368,
      "grad_norm": 1.351094126701355,
      "learning_rate": 5.485066247473614e-05,
      "loss": 0.0459,
      "step": 4490
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.2844514846801758,
      "learning_rate": 5.473837862115428e-05,
      "loss": 0.0446,
      "step": 4500
    },
    {
      "epoch": 1.4432,
      "grad_norm": 0.783967912197113,
      "learning_rate": 5.462609476757242e-05,
      "loss": 0.0392,
      "step": 4510
    },
    {
      "epoch": 1.4464000000000001,
      "grad_norm": 2.0353965759277344,
      "learning_rate": 5.451381091399057e-05,
      "loss": 0.0407,
      "step": 4520
    },
    {
      "epoch": 1.4496,
      "grad_norm": 1.3156319856643677,
      "learning_rate": 5.440152706040872e-05,
      "loss": 0.0381,
      "step": 4530
    },
    {
      "epoch": 1.4527999999999999,
      "grad_norm": 1.4378070831298828,
      "learning_rate": 5.428924320682686e-05,
      "loss": 0.0353,
      "step": 4540
    },
    {
      "epoch": 1.456,
      "grad_norm": 3.0744736194610596,
      "learning_rate": 5.4176959353245e-05,
      "loss": 0.0348,
      "step": 4550
    },
    {
      "epoch": 1.4592,
      "grad_norm": 1.6298600435256958,
      "learning_rate": 5.406467549966315e-05,
      "loss": 0.0402,
      "step": 4560
    },
    {
      "epoch": 1.4624,
      "grad_norm": 2.6494648456573486,
      "learning_rate": 5.395239164608129e-05,
      "loss": 0.0365,
      "step": 4570
    },
    {
      "epoch": 1.4656,
      "grad_norm": 1.653573751449585,
      "learning_rate": 5.384010779249944e-05,
      "loss": 0.0363,
      "step": 4580
    },
    {
      "epoch": 1.4687999999999999,
      "grad_norm": 1.7645295858383179,
      "learning_rate": 5.3727823938917584e-05,
      "loss": 0.0393,
      "step": 4590
    },
    {
      "epoch": 1.472,
      "grad_norm": 4.306888580322266,
      "learning_rate": 5.3615540085335735e-05,
      "loss": 0.0406,
      "step": 4600
    },
    {
      "epoch": 1.4752,
      "grad_norm": 3.1965126991271973,
      "learning_rate": 5.350325623175387e-05,
      "loss": 0.0358,
      "step": 4610
    },
    {
      "epoch": 1.4784,
      "grad_norm": 1.2502505779266357,
      "learning_rate": 5.339097237817202e-05,
      "loss": 0.0396,
      "step": 4620
    },
    {
      "epoch": 1.4816,
      "grad_norm": 2.091470718383789,
      "learning_rate": 5.327868852459017e-05,
      "loss": 0.035,
      "step": 4630
    },
    {
      "epoch": 1.4848,
      "grad_norm": 1.1398119926452637,
      "learning_rate": 5.316640467100831e-05,
      "loss": 0.0428,
      "step": 4640
    },
    {
      "epoch": 1.488,
      "grad_norm": 2.7160258293151855,
      "learning_rate": 5.3054120817426454e-05,
      "loss": 0.0353,
      "step": 4650
    },
    {
      "epoch": 1.4912,
      "grad_norm": 0.9645196199417114,
      "learning_rate": 5.2941836963844605e-05,
      "loss": 0.0415,
      "step": 4660
    },
    {
      "epoch": 1.4944,
      "grad_norm": 4.158140182495117,
      "learning_rate": 5.282955311026274e-05,
      "loss": 0.036,
      "step": 4670
    },
    {
      "epoch": 1.4976,
      "grad_norm": 1.1706950664520264,
      "learning_rate": 5.271726925668089e-05,
      "loss": 0.0376,
      "step": 4680
    },
    {
      "epoch": 1.5008,
      "grad_norm": 1.1529676914215088,
      "learning_rate": 5.260498540309904e-05,
      "loss": 0.0374,
      "step": 4690
    },
    {
      "epoch": 1.504,
      "grad_norm": 1.944616675376892,
      "learning_rate": 5.249270154951719e-05,
      "loss": 0.037,
      "step": 4700
    },
    {
      "epoch": 1.5072,
      "grad_norm": 1.7939577102661133,
      "learning_rate": 5.2380417695935325e-05,
      "loss": 0.0376,
      "step": 4710
    },
    {
      "epoch": 1.5104,
      "grad_norm": 2.588820695877075,
      "learning_rate": 5.2268133842353475e-05,
      "loss": 0.0345,
      "step": 4720
    },
    {
      "epoch": 1.5135999999999998,
      "grad_norm": 1.099802017211914,
      "learning_rate": 5.215584998877162e-05,
      "loss": 0.0355,
      "step": 4730
    },
    {
      "epoch": 1.5168,
      "grad_norm": 1.9600342512130737,
      "learning_rate": 5.2043566135189756e-05,
      "loss": 0.036,
      "step": 4740
    },
    {
      "epoch": 1.52,
      "grad_norm": 3.2066643238067627,
      "learning_rate": 5.193128228160791e-05,
      "loss": 0.0413,
      "step": 4750
    },
    {
      "epoch": 1.5232,
      "grad_norm": 4.0401811599731445,
      "learning_rate": 5.181899842802606e-05,
      "loss": 0.036,
      "step": 4760
    },
    {
      "epoch": 1.5264,
      "grad_norm": 1.673994541168213,
      "learning_rate": 5.1706714574444195e-05,
      "loss": 0.0366,
      "step": 4770
    },
    {
      "epoch": 1.5295999999999998,
      "grad_norm": 4.127200126647949,
      "learning_rate": 5.159443072086234e-05,
      "loss": 0.0375,
      "step": 4780
    },
    {
      "epoch": 1.5328,
      "grad_norm": 2.1488308906555176,
      "learning_rate": 5.148214686728049e-05,
      "loss": 0.0364,
      "step": 4790
    },
    {
      "epoch": 1.536,
      "grad_norm": 3.2764744758605957,
      "learning_rate": 5.136986301369864e-05,
      "loss": 0.0366,
      "step": 4800
    },
    {
      "epoch": 1.5392000000000001,
      "grad_norm": 4.183980941772461,
      "learning_rate": 5.125757916011678e-05,
      "loss": 0.0387,
      "step": 4810
    },
    {
      "epoch": 1.5424,
      "grad_norm": 2.350937604904175,
      "learning_rate": 5.114529530653492e-05,
      "loss": 0.0376,
      "step": 4820
    },
    {
      "epoch": 1.5455999999999999,
      "grad_norm": 1.4431155920028687,
      "learning_rate": 5.103301145295307e-05,
      "loss": 0.0378,
      "step": 4830
    },
    {
      "epoch": 1.5488,
      "grad_norm": 2.455113172531128,
      "learning_rate": 5.092072759937121e-05,
      "loss": 0.0352,
      "step": 4840
    },
    {
      "epoch": 1.552,
      "grad_norm": 2.4375059604644775,
      "learning_rate": 5.080844374578936e-05,
      "loss": 0.0388,
      "step": 4850
    },
    {
      "epoch": 1.5552000000000001,
      "grad_norm": 1.8249945640563965,
      "learning_rate": 5.0696159892207503e-05,
      "loss": 0.0352,
      "step": 4860
    },
    {
      "epoch": 1.5584,
      "grad_norm": 2.562242031097412,
      "learning_rate": 5.058387603862564e-05,
      "loss": 0.0366,
      "step": 4870
    },
    {
      "epoch": 1.5615999999999999,
      "grad_norm": 1.7993731498718262,
      "learning_rate": 5.047159218504379e-05,
      "loss": 0.0381,
      "step": 4880
    },
    {
      "epoch": 1.5648,
      "grad_norm": 1.6024712324142456,
      "learning_rate": 5.035930833146194e-05,
      "loss": 0.0342,
      "step": 4890
    },
    {
      "epoch": 1.568,
      "grad_norm": 1.0818573236465454,
      "learning_rate": 5.024702447788008e-05,
      "loss": 0.0355,
      "step": 4900
    },
    {
      "epoch": 1.5712000000000002,
      "grad_norm": 0.9753634929656982,
      "learning_rate": 5.013474062429823e-05,
      "loss": 0.0381,
      "step": 4910
    },
    {
      "epoch": 1.5744,
      "grad_norm": 1.9120144844055176,
      "learning_rate": 5.0022456770716374e-05,
      "loss": 0.0341,
      "step": 4920
    },
    {
      "epoch": 1.5776,
      "grad_norm": 2.293750762939453,
      "learning_rate": 4.991017291713452e-05,
      "loss": 0.0377,
      "step": 4930
    },
    {
      "epoch": 1.5808,
      "grad_norm": 3.1085097789764404,
      "learning_rate": 4.979788906355267e-05,
      "loss": 0.0343,
      "step": 4940
    },
    {
      "epoch": 1.584,
      "grad_norm": 1.3106160163879395,
      "learning_rate": 4.968560520997081e-05,
      "loss": 0.036,
      "step": 4950
    },
    {
      "epoch": 1.5872000000000002,
      "grad_norm": 2.5809476375579834,
      "learning_rate": 4.957332135638895e-05,
      "loss": 0.0341,
      "step": 4960
    },
    {
      "epoch": 1.5904,
      "grad_norm": 1.423450231552124,
      "learning_rate": 4.94610375028071e-05,
      "loss": 0.0306,
      "step": 4970
    },
    {
      "epoch": 1.5936,
      "grad_norm": 3.155231475830078,
      "learning_rate": 4.9348753649225244e-05,
      "loss": 0.0339,
      "step": 4980
    },
    {
      "epoch": 1.5968,
      "grad_norm": 1.6214268207550049,
      "learning_rate": 4.923646979564339e-05,
      "loss": 0.0369,
      "step": 4990
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.8274025917053223,
      "learning_rate": 4.912418594206153e-05,
      "loss": 0.0398,
      "step": 5000
    },
    {
      "epoch": 1.6032,
      "grad_norm": 3.3754544258117676,
      "learning_rate": 4.9011902088479676e-05,
      "loss": 0.0347,
      "step": 5010
    },
    {
      "epoch": 1.6064,
      "grad_norm": 2.3379604816436768,
      "learning_rate": 4.8899618234897826e-05,
      "loss": 0.0335,
      "step": 5020
    },
    {
      "epoch": 1.6096,
      "grad_norm": 1.3889174461364746,
      "learning_rate": 4.878733438131597e-05,
      "loss": 0.0327,
      "step": 5030
    },
    {
      "epoch": 1.6128,
      "grad_norm": 2.985076427459717,
      "learning_rate": 4.8675050527734114e-05,
      "loss": 0.0362,
      "step": 5040
    },
    {
      "epoch": 1.616,
      "grad_norm": 1.5555957555770874,
      "learning_rate": 4.856276667415226e-05,
      "loss": 0.0365,
      "step": 5050
    },
    {
      "epoch": 1.6192,
      "grad_norm": 2.723813533782959,
      "learning_rate": 4.84504828205704e-05,
      "loss": 0.0384,
      "step": 5060
    },
    {
      "epoch": 1.6223999999999998,
      "grad_norm": 1.3659981489181519,
      "learning_rate": 4.833819896698855e-05,
      "loss": 0.0336,
      "step": 5070
    },
    {
      "epoch": 1.6256,
      "grad_norm": 3.0281941890716553,
      "learning_rate": 4.8225915113406696e-05,
      "loss": 0.0307,
      "step": 5080
    },
    {
      "epoch": 1.6288,
      "grad_norm": 1.122520089149475,
      "learning_rate": 4.811363125982484e-05,
      "loss": 0.0326,
      "step": 5090
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 2.31559681892395,
      "learning_rate": 4.8001347406242984e-05,
      "loss": 0.0331,
      "step": 5100
    },
    {
      "epoch": 1.6352,
      "grad_norm": 1.262046217918396,
      "learning_rate": 4.788906355266113e-05,
      "loss": 0.0375,
      "step": 5110
    },
    {
      "epoch": 1.6383999999999999,
      "grad_norm": 2.673083782196045,
      "learning_rate": 4.777677969907928e-05,
      "loss": 0.0344,
      "step": 5120
    },
    {
      "epoch": 1.6416,
      "grad_norm": 5.857226371765137,
      "learning_rate": 4.766449584549742e-05,
      "loss": 0.0434,
      "step": 5130
    },
    {
      "epoch": 1.6448,
      "grad_norm": 2.3795230388641357,
      "learning_rate": 4.755221199191556e-05,
      "loss": 0.0477,
      "step": 5140
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 2.1502673625946045,
      "learning_rate": 4.743992813833371e-05,
      "loss": 0.0524,
      "step": 5150
    },
    {
      "epoch": 1.6512,
      "grad_norm": 1.4233574867248535,
      "learning_rate": 4.7327644284751854e-05,
      "loss": 0.0429,
      "step": 5160
    },
    {
      "epoch": 1.6543999999999999,
      "grad_norm": 2.0955042839050293,
      "learning_rate": 4.7215360431170005e-05,
      "loss": 0.0345,
      "step": 5170
    },
    {
      "epoch": 1.6576,
      "grad_norm": 2.341566562652588,
      "learning_rate": 4.710307657758814e-05,
      "loss": 0.0351,
      "step": 5180
    },
    {
      "epoch": 1.6608,
      "grad_norm": 3.160850763320923,
      "learning_rate": 4.6990792724006286e-05,
      "loss": 0.0344,
      "step": 5190
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 2.272794485092163,
      "learning_rate": 4.687850887042444e-05,
      "loss": 0.0331,
      "step": 5200
    },
    {
      "epoch": 1.6672,
      "grad_norm": 1.2717911005020142,
      "learning_rate": 4.676622501684258e-05,
      "loss": 0.0335,
      "step": 5210
    },
    {
      "epoch": 1.6703999999999999,
      "grad_norm": 2.4570579528808594,
      "learning_rate": 4.6653941163260725e-05,
      "loss": 0.0319,
      "step": 5220
    },
    {
      "epoch": 1.6736,
      "grad_norm": 1.8033403158187866,
      "learning_rate": 4.654165730967887e-05,
      "loss": 0.0343,
      "step": 5230
    },
    {
      "epoch": 1.6768,
      "grad_norm": 1.5098129510879517,
      "learning_rate": 4.642937345609701e-05,
      "loss": 0.032,
      "step": 5240
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.48603355884552,
      "learning_rate": 4.631708960251516e-05,
      "loss": 0.0327,
      "step": 5250
    },
    {
      "epoch": 1.6832,
      "grad_norm": 1.4422051906585693,
      "learning_rate": 4.620480574893331e-05,
      "loss": 0.0353,
      "step": 5260
    },
    {
      "epoch": 1.6864,
      "grad_norm": 1.18756103515625,
      "learning_rate": 4.609252189535145e-05,
      "loss": 0.0321,
      "step": 5270
    },
    {
      "epoch": 1.6896,
      "grad_norm": 1.1758790016174316,
      "learning_rate": 4.5980238041769595e-05,
      "loss": 0.0352,
      "step": 5280
    },
    {
      "epoch": 1.6928,
      "grad_norm": 1.2466790676116943,
      "learning_rate": 4.586795418818774e-05,
      "loss": 0.03,
      "step": 5290
    },
    {
      "epoch": 1.696,
      "grad_norm": 1.9264726638793945,
      "learning_rate": 4.575567033460589e-05,
      "loss": 0.0314,
      "step": 5300
    },
    {
      "epoch": 1.6992,
      "grad_norm": 1.9639238119125366,
      "learning_rate": 4.564338648102403e-05,
      "loss": 0.0328,
      "step": 5310
    },
    {
      "epoch": 1.7024,
      "grad_norm": 2.070943832397461,
      "learning_rate": 4.553110262744217e-05,
      "loss": 0.0347,
      "step": 5320
    },
    {
      "epoch": 1.7056,
      "grad_norm": 2.0837361812591553,
      "learning_rate": 4.541881877386032e-05,
      "loss": 0.0333,
      "step": 5330
    },
    {
      "epoch": 1.7088,
      "grad_norm": 1.9007681608200073,
      "learning_rate": 4.5306534920278465e-05,
      "loss": 0.0323,
      "step": 5340
    },
    {
      "epoch": 1.712,
      "grad_norm": 4.6805830001831055,
      "learning_rate": 4.5194251066696616e-05,
      "loss": 0.0341,
      "step": 5350
    },
    {
      "epoch": 1.7151999999999998,
      "grad_norm": 1.4064592123031616,
      "learning_rate": 4.508196721311476e-05,
      "loss": 0.0288,
      "step": 5360
    },
    {
      "epoch": 1.7184,
      "grad_norm": 3.4108219146728516,
      "learning_rate": 4.4969683359532897e-05,
      "loss": 0.0303,
      "step": 5370
    },
    {
      "epoch": 1.7216,
      "grad_norm": 0.9329103827476501,
      "learning_rate": 4.485739950595105e-05,
      "loss": 0.0314,
      "step": 5380
    },
    {
      "epoch": 1.7248,
      "grad_norm": 1.681719183921814,
      "learning_rate": 4.474511565236919e-05,
      "loss": 0.0284,
      "step": 5390
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.932102382183075,
      "learning_rate": 4.463283179878734e-05,
      "loss": 0.0299,
      "step": 5400
    },
    {
      "epoch": 1.7311999999999999,
      "grad_norm": 2.7038533687591553,
      "learning_rate": 4.452054794520548e-05,
      "loss": 0.0329,
      "step": 5410
    },
    {
      "epoch": 1.7344,
      "grad_norm": 1.4268467426300049,
      "learning_rate": 4.440826409162362e-05,
      "loss": 0.0303,
      "step": 5420
    },
    {
      "epoch": 1.7376,
      "grad_norm": 1.9577819108963013,
      "learning_rate": 4.4295980238041774e-05,
      "loss": 0.0326,
      "step": 5430
    },
    {
      "epoch": 1.7408000000000001,
      "grad_norm": 2.5221760272979736,
      "learning_rate": 4.418369638445992e-05,
      "loss": 0.0325,
      "step": 5440
    },
    {
      "epoch": 1.744,
      "grad_norm": 3.2790379524230957,
      "learning_rate": 4.407141253087806e-05,
      "loss": 0.0295,
      "step": 5450
    },
    {
      "epoch": 1.7471999999999999,
      "grad_norm": 0.8850557208061218,
      "learning_rate": 4.3959128677296205e-05,
      "loss": 0.0307,
      "step": 5460
    },
    {
      "epoch": 1.7504,
      "grad_norm": 1.8326717615127563,
      "learning_rate": 4.384684482371435e-05,
      "loss": 0.0289,
      "step": 5470
    },
    {
      "epoch": 1.7536,
      "grad_norm": 1.3088713884353638,
      "learning_rate": 4.37345609701325e-05,
      "loss": 0.0292,
      "step": 5480
    },
    {
      "epoch": 1.7568000000000001,
      "grad_norm": 1.0117987394332886,
      "learning_rate": 4.3622277116550644e-05,
      "loss": 0.0311,
      "step": 5490
    },
    {
      "epoch": 1.76,
      "grad_norm": 2.7869484424591064,
      "learning_rate": 4.350999326296879e-05,
      "loss": 0.0278,
      "step": 5500
    },
    {
      "epoch": 1.7631999999999999,
      "grad_norm": 1.3128660917282104,
      "learning_rate": 4.339770940938693e-05,
      "loss": 0.0278,
      "step": 5510
    },
    {
      "epoch": 1.7664,
      "grad_norm": 1.1051273345947266,
      "learning_rate": 4.3285425555805075e-05,
      "loss": 0.03,
      "step": 5520
    },
    {
      "epoch": 1.7696,
      "grad_norm": 1.3793776035308838,
      "learning_rate": 4.3173141702223226e-05,
      "loss": 0.0306,
      "step": 5530
    },
    {
      "epoch": 1.7728000000000002,
      "grad_norm": 2.992269515991211,
      "learning_rate": 4.306085784864137e-05,
      "loss": 0.0299,
      "step": 5540
    },
    {
      "epoch": 1.776,
      "grad_norm": 1.6625593900680542,
      "learning_rate": 4.294857399505951e-05,
      "loss": 0.0356,
      "step": 5550
    },
    {
      "epoch": 1.7792,
      "grad_norm": 1.0821179151535034,
      "learning_rate": 4.283629014147766e-05,
      "loss": 0.0349,
      "step": 5560
    },
    {
      "epoch": 1.7824,
      "grad_norm": 1.0884099006652832,
      "learning_rate": 4.27240062878958e-05,
      "loss": 0.0313,
      "step": 5570
    },
    {
      "epoch": 1.7856,
      "grad_norm": 1.5417124032974243,
      "learning_rate": 4.261172243431395e-05,
      "loss": 0.0306,
      "step": 5580
    },
    {
      "epoch": 1.7888,
      "grad_norm": 2.5081472396850586,
      "learning_rate": 4.249943858073209e-05,
      "loss": 0.0329,
      "step": 5590
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.9784805178642273,
      "learning_rate": 4.2387154727150233e-05,
      "loss": 0.0331,
      "step": 5600
    },
    {
      "epoch": 1.7952,
      "grad_norm": 2.7062466144561768,
      "learning_rate": 4.2274870873568384e-05,
      "loss": 0.0295,
      "step": 5610
    },
    {
      "epoch": 1.7984,
      "grad_norm": 2.028097629547119,
      "learning_rate": 4.216258701998653e-05,
      "loss": 0.0294,
      "step": 5620
    },
    {
      "epoch": 1.8016,
      "grad_norm": 0.9252501130104065,
      "learning_rate": 4.205030316640468e-05,
      "loss": 0.0282,
      "step": 5630
    },
    {
      "epoch": 1.8048,
      "grad_norm": 1.6614617109298706,
      "learning_rate": 4.1938019312822816e-05,
      "loss": 0.029,
      "step": 5640
    },
    {
      "epoch": 1.808,
      "grad_norm": 1.5624871253967285,
      "learning_rate": 4.182573545924096e-05,
      "loss": 0.0286,
      "step": 5650
    },
    {
      "epoch": 1.8112,
      "grad_norm": 1.7454490661621094,
      "learning_rate": 4.171345160565911e-05,
      "loss": 0.0299,
      "step": 5660
    },
    {
      "epoch": 1.8144,
      "grad_norm": 1.7463639974594116,
      "learning_rate": 4.1601167752077254e-05,
      "loss": 0.0296,
      "step": 5670
    },
    {
      "epoch": 1.8176,
      "grad_norm": 1.4736864566802979,
      "learning_rate": 4.14888838984954e-05,
      "loss": 0.0317,
      "step": 5680
    },
    {
      "epoch": 1.8208,
      "grad_norm": 1.21503484249115,
      "learning_rate": 4.137660004491354e-05,
      "loss": 0.0293,
      "step": 5690
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 3.489445209503174,
      "learning_rate": 4.1264316191331686e-05,
      "loss": 0.0305,
      "step": 5700
    },
    {
      "epoch": 1.8272,
      "grad_norm": 1.21157705783844,
      "learning_rate": 4.115203233774984e-05,
      "loss": 0.03,
      "step": 5710
    },
    {
      "epoch": 1.8304,
      "grad_norm": 2.4874978065490723,
      "learning_rate": 4.103974848416798e-05,
      "loss": 0.0288,
      "step": 5720
    },
    {
      "epoch": 1.8336000000000001,
      "grad_norm": 1.4586814641952515,
      "learning_rate": 4.092746463058612e-05,
      "loss": 0.0354,
      "step": 5730
    },
    {
      "epoch": 1.8368,
      "grad_norm": 1.2466408014297485,
      "learning_rate": 4.081518077700427e-05,
      "loss": 0.0345,
      "step": 5740
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 1.0634334087371826,
      "learning_rate": 4.070289692342241e-05,
      "loss": 0.0281,
      "step": 5750
    },
    {
      "epoch": 1.8432,
      "grad_norm": 1.6378570795059204,
      "learning_rate": 4.059061306984056e-05,
      "loss": 0.0311,
      "step": 5760
    },
    {
      "epoch": 1.8464,
      "grad_norm": 1.5089457035064697,
      "learning_rate": 4.047832921625871e-05,
      "loss": 0.0298,
      "step": 5770
    },
    {
      "epoch": 1.8496000000000001,
      "grad_norm": 2.608259677886963,
      "learning_rate": 4.0366045362676844e-05,
      "loss": 0.029,
      "step": 5780
    },
    {
      "epoch": 1.8528,
      "grad_norm": 1.7564635276794434,
      "learning_rate": 4.0253761509094995e-05,
      "loss": 0.0268,
      "step": 5790
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 1.1659057140350342,
      "learning_rate": 4.014147765551314e-05,
      "loss": 0.0274,
      "step": 5800
    },
    {
      "epoch": 1.8592,
      "grad_norm": 2.8701725006103516,
      "learning_rate": 4.002919380193129e-05,
      "loss": 0.0272,
      "step": 5810
    },
    {
      "epoch": 1.8624,
      "grad_norm": 1.034717321395874,
      "learning_rate": 3.9916909948349426e-05,
      "loss": 0.0279,
      "step": 5820
    },
    {
      "epoch": 1.8656000000000001,
      "grad_norm": 1.3043538331985474,
      "learning_rate": 3.980462609476757e-05,
      "loss": 0.0307,
      "step": 5830
    },
    {
      "epoch": 1.8688,
      "grad_norm": 2.0375423431396484,
      "learning_rate": 3.969234224118572e-05,
      "loss": 0.0258,
      "step": 5840
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 2.1126816272735596,
      "learning_rate": 3.9580058387603865e-05,
      "loss": 0.0308,
      "step": 5850
    },
    {
      "epoch": 1.8752,
      "grad_norm": 1.7014706134796143,
      "learning_rate": 3.946777453402201e-05,
      "loss": 0.0282,
      "step": 5860
    },
    {
      "epoch": 1.8784,
      "grad_norm": 2.7476634979248047,
      "learning_rate": 3.935549068044015e-05,
      "loss": 0.0284,
      "step": 5870
    },
    {
      "epoch": 1.8816000000000002,
      "grad_norm": 1.6362510919570923,
      "learning_rate": 3.9243206826858297e-05,
      "loss": 0.0242,
      "step": 5880
    },
    {
      "epoch": 1.8848,
      "grad_norm": 1.3239845037460327,
      "learning_rate": 3.913092297327645e-05,
      "loss": 0.0361,
      "step": 5890
    },
    {
      "epoch": 1.888,
      "grad_norm": 1.4442349672317505,
      "learning_rate": 3.901863911969459e-05,
      "loss": 0.0277,
      "step": 5900
    },
    {
      "epoch": 1.8912,
      "grad_norm": 1.9677876234054565,
      "learning_rate": 3.8906355266112735e-05,
      "loss": 0.0258,
      "step": 5910
    },
    {
      "epoch": 1.8944,
      "grad_norm": 2.842235803604126,
      "learning_rate": 3.879407141253088e-05,
      "loss": 0.0298,
      "step": 5920
    },
    {
      "epoch": 1.8976,
      "grad_norm": 1.5647774934768677,
      "learning_rate": 3.868178755894902e-05,
      "loss": 0.0292,
      "step": 5930
    },
    {
      "epoch": 1.9008,
      "grad_norm": 1.7668209075927734,
      "learning_rate": 3.8569503705367174e-05,
      "loss": 0.0357,
      "step": 5940
    },
    {
      "epoch": 1.904,
      "grad_norm": 2.651283025741577,
      "learning_rate": 3.845721985178532e-05,
      "loss": 0.0302,
      "step": 5950
    },
    {
      "epoch": 1.9072,
      "grad_norm": 5.3611040115356445,
      "learning_rate": 3.834493599820346e-05,
      "loss": 0.0304,
      "step": 5960
    },
    {
      "epoch": 1.9104,
      "grad_norm": 5.584418773651123,
      "learning_rate": 3.8232652144621605e-05,
      "loss": 0.0284,
      "step": 5970
    },
    {
      "epoch": 1.9136,
      "grad_norm": 3.7711610794067383,
      "learning_rate": 3.812036829103975e-05,
      "loss": 0.0297,
      "step": 5980
    },
    {
      "epoch": 1.9167999999999998,
      "grad_norm": 0.7803456783294678,
      "learning_rate": 3.80080844374579e-05,
      "loss": 0.0289,
      "step": 5990
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.1393859386444092,
      "learning_rate": 3.789580058387604e-05,
      "loss": 0.0247,
      "step": 6000
    },
    {
      "epoch": 1.9232,
      "grad_norm": 1.7076109647750854,
      "learning_rate": 3.778351673029418e-05,
      "loss": 0.0276,
      "step": 6010
    },
    {
      "epoch": 1.9264000000000001,
      "grad_norm": 1.2361043691635132,
      "learning_rate": 3.767123287671233e-05,
      "loss": 0.0277,
      "step": 6020
    },
    {
      "epoch": 1.9296,
      "grad_norm": 1.1116836071014404,
      "learning_rate": 3.7558949023130475e-05,
      "loss": 0.0279,
      "step": 6030
    },
    {
      "epoch": 1.9327999999999999,
      "grad_norm": 2.2229862213134766,
      "learning_rate": 3.744666516954862e-05,
      "loss": 0.0284,
      "step": 6040
    },
    {
      "epoch": 1.936,
      "grad_norm": 1.5508464574813843,
      "learning_rate": 3.733438131596676e-05,
      "loss": 0.0306,
      "step": 6050
    },
    {
      "epoch": 1.9392,
      "grad_norm": 1.7325248718261719,
      "learning_rate": 3.722209746238491e-05,
      "loss": 0.0308,
      "step": 6060
    },
    {
      "epoch": 1.9424000000000001,
      "grad_norm": 1.0399812459945679,
      "learning_rate": 3.710981360880306e-05,
      "loss": 0.0261,
      "step": 6070
    },
    {
      "epoch": 1.9456,
      "grad_norm": 2.994081974029541,
      "learning_rate": 3.69975297552212e-05,
      "loss": 0.0297,
      "step": 6080
    },
    {
      "epoch": 1.9487999999999999,
      "grad_norm": 2.2742340564727783,
      "learning_rate": 3.6885245901639346e-05,
      "loss": 0.0276,
      "step": 6090
    },
    {
      "epoch": 1.952,
      "grad_norm": 1.2096333503723145,
      "learning_rate": 3.677296204805749e-05,
      "loss": 0.0277,
      "step": 6100
    },
    {
      "epoch": 1.9552,
      "grad_norm": 1.3712992668151855,
      "learning_rate": 3.666067819447563e-05,
      "loss": 0.0289,
      "step": 6110
    },
    {
      "epoch": 1.9584000000000001,
      "grad_norm": 1.6062151193618774,
      "learning_rate": 3.6548394340893784e-05,
      "loss": 0.0273,
      "step": 6120
    },
    {
      "epoch": 1.9616,
      "grad_norm": 1.5088088512420654,
      "learning_rate": 3.643611048731193e-05,
      "loss": 0.0297,
      "step": 6130
    },
    {
      "epoch": 1.9647999999999999,
      "grad_norm": 0.9999478459358215,
      "learning_rate": 3.632382663373007e-05,
      "loss": 0.026,
      "step": 6140
    },
    {
      "epoch": 1.968,
      "grad_norm": 1.0416607856750488,
      "learning_rate": 3.6211542780148216e-05,
      "loss": 0.0285,
      "step": 6150
    },
    {
      "epoch": 1.9712,
      "grad_norm": 1.9191815853118896,
      "learning_rate": 3.609925892656636e-05,
      "loss": 0.0259,
      "step": 6160
    },
    {
      "epoch": 1.9744000000000002,
      "grad_norm": 1.457220196723938,
      "learning_rate": 3.598697507298451e-05,
      "loss": 0.0259,
      "step": 6170
    },
    {
      "epoch": 1.9776,
      "grad_norm": 1.0753467082977295,
      "learning_rate": 3.587469121940265e-05,
      "loss": 0.0264,
      "step": 6180
    },
    {
      "epoch": 1.9808,
      "grad_norm": 2.804377317428589,
      "learning_rate": 3.57624073658208e-05,
      "loss": 0.0258,
      "step": 6190
    },
    {
      "epoch": 1.984,
      "grad_norm": 1.9763532876968384,
      "learning_rate": 3.565012351223894e-05,
      "loss": 0.0282,
      "step": 6200
    },
    {
      "epoch": 1.9872,
      "grad_norm": 2.1442463397979736,
      "learning_rate": 3.5537839658657086e-05,
      "loss": 0.0244,
      "step": 6210
    },
    {
      "epoch": 1.9904,
      "grad_norm": 1.6756515502929688,
      "learning_rate": 3.542555580507524e-05,
      "loss": 0.0251,
      "step": 6220
    },
    {
      "epoch": 1.9936,
      "grad_norm": 2.3364181518554688,
      "learning_rate": 3.5313271951493374e-05,
      "loss": 0.0276,
      "step": 6230
    },
    {
      "epoch": 1.9968,
      "grad_norm": 3.023191452026367,
      "learning_rate": 3.5200988097911524e-05,
      "loss": 0.0266,
      "step": 6240
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.4868950843811035,
      "learning_rate": 3.508870424432967e-05,
      "loss": 0.0273,
      "step": 6250
    }
  ],
  "logging_steps": 10,
  "max_steps": 9375,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}