{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23553684210526316,
  "eval_steps": 500,
  "global_step": 2797,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008421052631578948,
      "grad_norm": 1.6452618837356567,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 0.8848,
      "step": 10
    },
    {
      "epoch": 0.0016842105263157896,
      "grad_norm": 1.2745853662490845,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 0.8978,
      "step": 20
    },
    {
      "epoch": 0.0025263157894736842,
      "grad_norm": 1.1237419843673706,
      "learning_rate": 3.342134831460675e-06,
      "loss": 0.8238,
      "step": 30
    },
    {
      "epoch": 0.003368421052631579,
      "grad_norm": 1.066956877708435,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 0.7917,
      "step": 40
    },
    {
      "epoch": 0.004210526315789474,
      "grad_norm": 0.8702846765518188,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.7807,
      "step": 50
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": 0.7245010733604431,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.7296,
      "step": 60
    },
    {
      "epoch": 0.005894736842105263,
      "grad_norm": 0.7846991419792175,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.735,
      "step": 70
    },
    {
      "epoch": 0.006736842105263158,
      "grad_norm": 0.8695846796035767,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7109,
      "step": 80
    },
    {
      "epoch": 0.007578947368421052,
      "grad_norm": 0.7376852035522461,
      "learning_rate": 1.005e-05,
      "loss": 0.7221,
      "step": 90
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 0.877524197101593,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7048,
      "step": 100
    },
    {
      "epoch": 0.009263157894736843,
      "grad_norm": 0.7281895875930786,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7126,
      "step": 110
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": 0.8136023283004761,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.6877,
      "step": 120
    },
    {
      "epoch": 0.010947368421052631,
      "grad_norm": 0.8643974661827087,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.7093,
      "step": 130
    },
    {
      "epoch": 0.011789473684210527,
      "grad_norm": 0.787255585193634,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.6981,
      "step": 140
    },
    {
      "epoch": 0.01263157894736842,
      "grad_norm": 0.8877604603767395,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.7027,
      "step": 150
    },
    {
      "epoch": 0.013473684210526317,
      "grad_norm": 0.8588012456893921,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.6974,
      "step": 160
    },
    {
      "epoch": 0.01431578947368421,
      "grad_norm": 0.737384557723999,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.7082,
      "step": 170
    },
    {
      "epoch": 0.015157894736842105,
      "grad_norm": 0.8280077576637268,
      "learning_rate": 2e-05,
      "loss": 0.7238,
      "step": 180
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.8020002841949463,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 190
    },
    {
      "epoch": 0.016842105263157894,
      "grad_norm": 0.7412464618682861,
      "learning_rate": 2e-05,
      "loss": 0.683,
      "step": 200
    },
    {
      "epoch": 0.01768421052631579,
      "grad_norm": 0.6804697513580322,
      "learning_rate": 2e-05,
      "loss": 0.6939,
      "step": 210
    },
    {
      "epoch": 0.018526315789473686,
      "grad_norm": 0.6289499402046204,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 220
    },
    {
      "epoch": 0.01936842105263158,
      "grad_norm": 0.7443152070045471,
      "learning_rate": 2e-05,
      "loss": 0.6954,
      "step": 230
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 0.5574337244033813,
      "learning_rate": 2e-05,
      "loss": 0.6995,
      "step": 240
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.5961909294128418,
      "learning_rate": 2e-05,
      "loss": 0.6741,
      "step": 250
    },
    {
      "epoch": 0.021894736842105262,
      "grad_norm": 0.623269259929657,
      "learning_rate": 2e-05,
      "loss": 0.6884,
      "step": 260
    },
    {
      "epoch": 0.02273684210526316,
      "grad_norm": 0.6100159287452698,
      "learning_rate": 2e-05,
      "loss": 0.6802,
      "step": 270
    },
    {
      "epoch": 0.023578947368421053,
      "grad_norm": 0.5976904034614563,
      "learning_rate": 2e-05,
      "loss": 0.6818,
      "step": 280
    },
    {
      "epoch": 0.024421052631578948,
      "grad_norm": 0.5483630895614624,
      "learning_rate": 2e-05,
      "loss": 0.6959,
      "step": 290
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 0.5604531764984131,
      "learning_rate": 2e-05,
      "loss": 0.6778,
      "step": 300
    },
    {
      "epoch": 0.026105263157894736,
      "grad_norm": 0.7242655158042908,
      "learning_rate": 2e-05,
      "loss": 0.6988,
      "step": 310
    },
    {
      "epoch": 0.026947368421052633,
      "grad_norm": 0.6082198619842529,
      "learning_rate": 2e-05,
      "loss": 0.7195,
      "step": 320
    },
    {
      "epoch": 0.027789473684210527,
      "grad_norm": 0.6409816145896912,
      "learning_rate": 2e-05,
      "loss": 0.7018,
      "step": 330
    },
    {
      "epoch": 0.02863157894736842,
      "grad_norm": 0.5886685848236084,
      "learning_rate": 2e-05,
      "loss": 0.6722,
      "step": 340
    },
    {
      "epoch": 0.029473684210526315,
      "grad_norm": 0.5524492859840393,
      "learning_rate": 2e-05,
      "loss": 0.6978,
      "step": 350
    },
    {
      "epoch": 0.03031578947368421,
      "grad_norm": 0.5257862210273743,
      "learning_rate": 2e-05,
      "loss": 0.6724,
      "step": 360
    },
    {
      "epoch": 0.031157894736842107,
      "grad_norm": 0.4827383756637573,
      "learning_rate": 2e-05,
      "loss": 0.6663,
      "step": 370
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.511551558971405,
      "learning_rate": 2e-05,
      "loss": 0.6967,
      "step": 380
    },
    {
      "epoch": 0.032842105263157895,
      "grad_norm": 0.495875746011734,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 390
    },
    {
      "epoch": 0.03368421052631579,
      "grad_norm": 0.5335220098495483,
      "learning_rate": 2e-05,
      "loss": 0.6871,
      "step": 400
    },
    {
      "epoch": 0.03452631578947368,
      "grad_norm": 0.49408501386642456,
      "learning_rate": 2e-05,
      "loss": 0.6896,
      "step": 410
    },
    {
      "epoch": 0.03536842105263158,
      "grad_norm": 0.5984386801719666,
      "learning_rate": 2e-05,
      "loss": 0.6874,
      "step": 420
    },
    {
      "epoch": 0.03621052631578947,
      "grad_norm": 0.5150274634361267,
      "learning_rate": 2e-05,
      "loss": 0.6681,
      "step": 430
    },
    {
      "epoch": 0.03705263157894737,
      "grad_norm": 0.5099483132362366,
      "learning_rate": 2e-05,
      "loss": 0.7014,
      "step": 440
    },
    {
      "epoch": 0.037894736842105266,
      "grad_norm": 0.5528599619865417,
      "learning_rate": 2e-05,
      "loss": 0.6855,
      "step": 450
    },
    {
      "epoch": 0.03873684210526316,
      "grad_norm": 0.5252863168716431,
      "learning_rate": 2e-05,
      "loss": 0.6827,
      "step": 460
    },
    {
      "epoch": 0.039578947368421054,
      "grad_norm": 0.5065030455589294,
      "learning_rate": 2e-05,
      "loss": 0.6915,
      "step": 470
    },
    {
      "epoch": 0.04042105263157895,
      "grad_norm": 0.5258328318595886,
      "learning_rate": 2e-05,
      "loss": 0.6889,
      "step": 480
    },
    {
      "epoch": 0.04126315789473684,
      "grad_norm": 0.5116169452667236,
      "learning_rate": 2e-05,
      "loss": 0.68,
      "step": 490
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.48490849137306213,
      "learning_rate": 2e-05,
      "loss": 0.6715,
      "step": 500
    },
    {
      "epoch": 0.04294736842105263,
      "grad_norm": 0.5084254145622253,
      "learning_rate": 2e-05,
      "loss": 0.6712,
      "step": 510
    },
    {
      "epoch": 0.043789473684210524,
      "grad_norm": 0.49414074420928955,
      "learning_rate": 2e-05,
      "loss": 0.6802,
      "step": 520
    },
    {
      "epoch": 0.04463157894736842,
      "grad_norm": 0.46595826745033264,
      "learning_rate": 2e-05,
      "loss": 0.6946,
      "step": 530
    },
    {
      "epoch": 0.04547368421052632,
      "grad_norm": 0.5120992064476013,
      "learning_rate": 2e-05,
      "loss": 0.6693,
      "step": 540
    },
    {
      "epoch": 0.04631578947368421,
      "grad_norm": 0.5484461784362793,
      "learning_rate": 2e-05,
      "loss": 0.6994,
      "step": 550
    },
    {
      "epoch": 0.04715789473684211,
      "grad_norm": 0.5065701603889465,
      "learning_rate": 2e-05,
      "loss": 0.6891,
      "step": 560
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.4997612237930298,
      "learning_rate": 2e-05,
      "loss": 0.6826,
      "step": 570
    },
    {
      "epoch": 0.048842105263157895,
      "grad_norm": 0.5135060548782349,
      "learning_rate": 2e-05,
      "loss": 0.6654,
      "step": 580
    },
    {
      "epoch": 0.04968421052631579,
      "grad_norm": 0.49073326587677,
      "learning_rate": 2e-05,
      "loss": 0.6721,
      "step": 590
    },
    {
      "epoch": 0.05052631578947368,
      "grad_norm": 0.4621580243110657,
      "learning_rate": 2e-05,
      "loss": 0.7012,
      "step": 600
    },
    {
      "epoch": 0.05136842105263158,
      "grad_norm": 0.5011141300201416,
      "learning_rate": 2e-05,
      "loss": 0.6714,
      "step": 610
    },
    {
      "epoch": 0.05221052631578947,
      "grad_norm": 0.46268361806869507,
      "learning_rate": 2e-05,
      "loss": 0.6728,
      "step": 620
    },
    {
      "epoch": 0.053052631578947365,
      "grad_norm": 0.4844551086425781,
      "learning_rate": 2e-05,
      "loss": 0.6558,
      "step": 630
    },
    {
      "epoch": 0.053894736842105266,
      "grad_norm": 0.4990077018737793,
      "learning_rate": 2e-05,
      "loss": 0.6796,
      "step": 640
    },
    {
      "epoch": 0.05473684210526316,
      "grad_norm": 0.49000492691993713,
      "learning_rate": 2e-05,
      "loss": 0.6845,
      "step": 650
    },
    {
      "epoch": 0.055578947368421054,
      "grad_norm": 0.4686015248298645,
      "learning_rate": 2e-05,
      "loss": 0.6876,
      "step": 660
    },
    {
      "epoch": 0.05642105263157895,
      "grad_norm": 0.5337815284729004,
      "learning_rate": 2e-05,
      "loss": 0.6824,
      "step": 670
    },
    {
      "epoch": 0.05726315789473684,
      "grad_norm": 0.49088242650032043,
      "learning_rate": 2e-05,
      "loss": 0.6586,
      "step": 680
    },
    {
      "epoch": 0.058105263157894736,
      "grad_norm": 0.46112194657325745,
      "learning_rate": 2e-05,
      "loss": 0.6704,
      "step": 690
    },
    {
      "epoch": 0.05894736842105263,
      "grad_norm": 0.5169646739959717,
      "learning_rate": 2e-05,
      "loss": 0.6587,
      "step": 700
    },
    {
      "epoch": 0.059789473684210524,
      "grad_norm": 0.4750337600708008,
      "learning_rate": 2e-05,
      "loss": 0.6933,
      "step": 710
    },
    {
      "epoch": 0.06063157894736842,
      "grad_norm": 0.47679170966148376,
      "learning_rate": 2e-05,
      "loss": 0.6688,
      "step": 720
    },
    {
      "epoch": 0.06147368421052631,
      "grad_norm": 0.4437170922756195,
      "learning_rate": 2e-05,
      "loss": 0.6641,
      "step": 730
    },
    {
      "epoch": 0.06231578947368421,
      "grad_norm": 0.48904526233673096,
      "learning_rate": 2e-05,
      "loss": 0.6901,
      "step": 740
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.47720208764076233,
      "learning_rate": 2e-05,
      "loss": 0.6612,
      "step": 750
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.45092350244522095,
      "learning_rate": 2e-05,
      "loss": 0.6585,
      "step": 760
    },
    {
      "epoch": 0.0648421052631579,
      "grad_norm": 0.5482639670372009,
      "learning_rate": 2e-05,
      "loss": 0.6644,
      "step": 770
    },
    {
      "epoch": 0.06568421052631579,
      "grad_norm": 0.47330716252326965,
      "learning_rate": 2e-05,
      "loss": 0.6659,
      "step": 780
    },
    {
      "epoch": 0.06652631578947368,
      "grad_norm": 0.4877111613750458,
      "learning_rate": 2e-05,
      "loss": 0.682,
      "step": 790
    },
    {
      "epoch": 0.06736842105263158,
      "grad_norm": 0.4415607154369354,
      "learning_rate": 2e-05,
      "loss": 0.6642,
      "step": 800
    },
    {
      "epoch": 0.06821052631578947,
      "grad_norm": 0.5016757249832153,
      "learning_rate": 2e-05,
      "loss": 0.6929,
      "step": 810
    },
    {
      "epoch": 0.06905263157894737,
      "grad_norm": 0.44279953837394714,
      "learning_rate": 2e-05,
      "loss": 0.665,
      "step": 820
    },
    {
      "epoch": 0.06989473684210526,
      "grad_norm": 0.46184229850769043,
      "learning_rate": 2e-05,
      "loss": 0.6689,
      "step": 830
    },
    {
      "epoch": 0.07073684210526315,
      "grad_norm": 0.4588353633880615,
      "learning_rate": 2e-05,
      "loss": 0.6529,
      "step": 840
    },
    {
      "epoch": 0.07157894736842105,
      "grad_norm": 0.46397942304611206,
      "learning_rate": 2e-05,
      "loss": 0.6678,
      "step": 850
    },
    {
      "epoch": 0.07242105263157894,
      "grad_norm": 0.4994259178638458,
      "learning_rate": 2e-05,
      "loss": 0.6788,
      "step": 860
    },
    {
      "epoch": 0.07326315789473684,
      "grad_norm": 0.43922510743141174,
      "learning_rate": 2e-05,
      "loss": 0.6468,
      "step": 870
    },
    {
      "epoch": 0.07410526315789474,
      "grad_norm": 0.4572885036468506,
      "learning_rate": 2e-05,
      "loss": 0.6584,
      "step": 880
    },
    {
      "epoch": 0.07494736842105264,
      "grad_norm": 0.5367586612701416,
      "learning_rate": 2e-05,
      "loss": 0.6739,
      "step": 890
    },
    {
      "epoch": 0.07578947368421053,
      "grad_norm": 0.4777562916278839,
      "learning_rate": 2e-05,
      "loss": 0.6713,
      "step": 900
    },
    {
      "epoch": 0.07663157894736843,
      "grad_norm": 0.47622188925743103,
      "learning_rate": 2e-05,
      "loss": 0.6596,
      "step": 910
    },
    {
      "epoch": 0.07747368421052632,
      "grad_norm": 0.46543118357658386,
      "learning_rate": 2e-05,
      "loss": 0.6734,
      "step": 920
    },
    {
      "epoch": 0.07831578947368421,
      "grad_norm": 0.460198312997818,
      "learning_rate": 2e-05,
      "loss": 0.6605,
      "step": 930
    },
    {
      "epoch": 0.07915789473684211,
      "grad_norm": 0.5260334014892578,
      "learning_rate": 2e-05,
      "loss": 0.6579,
      "step": 940
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5725151896476746,
      "learning_rate": 2e-05,
      "loss": 0.6633,
      "step": 950
    },
    {
      "epoch": 0.0808421052631579,
      "grad_norm": 0.4703020751476288,
      "learning_rate": 2e-05,
      "loss": 0.6642,
      "step": 960
    },
    {
      "epoch": 0.08168421052631579,
      "grad_norm": 0.46530941128730774,
      "learning_rate": 2e-05,
      "loss": 0.6729,
      "step": 970
    },
    {
      "epoch": 0.08252631578947368,
      "grad_norm": 0.486493855714798,
      "learning_rate": 2e-05,
      "loss": 0.6488,
      "step": 980
    },
    {
      "epoch": 0.08336842105263158,
      "grad_norm": 0.4559321999549866,
      "learning_rate": 2e-05,
      "loss": 0.6543,
      "step": 990
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.4368566870689392,
      "learning_rate": 2e-05,
      "loss": 0.6695,
      "step": 1000
    },
    {
      "epoch": 0.08505263157894737,
      "grad_norm": 0.5327503681182861,
      "learning_rate": 2e-05,
      "loss": 0.6673,
      "step": 1010
    },
    {
      "epoch": 0.08589473684210526,
      "grad_norm": 0.4721207618713379,
      "learning_rate": 2e-05,
      "loss": 0.661,
      "step": 1020
    },
    {
      "epoch": 0.08673684210526315,
      "grad_norm": 0.4939779043197632,
      "learning_rate": 2e-05,
      "loss": 0.661,
      "step": 1030
    },
    {
      "epoch": 0.08757894736842105,
      "grad_norm": 0.5211036205291748,
      "learning_rate": 2e-05,
      "loss": 0.675,
      "step": 1040
    },
    {
      "epoch": 0.08842105263157894,
      "grad_norm": 0.46270859241485596,
      "learning_rate": 2e-05,
      "loss": 0.6489,
      "step": 1050
    },
    {
      "epoch": 0.08926315789473684,
      "grad_norm": 0.47459232807159424,
      "learning_rate": 2e-05,
      "loss": 0.6745,
      "step": 1060
    },
    {
      "epoch": 0.09010526315789473,
      "grad_norm": 0.4822026491165161,
      "learning_rate": 2e-05,
      "loss": 0.6526,
      "step": 1070
    },
    {
      "epoch": 0.09094736842105264,
      "grad_norm": 0.4457903802394867,
      "learning_rate": 2e-05,
      "loss": 0.6424,
      "step": 1080
    },
    {
      "epoch": 0.09178947368421053,
      "grad_norm": 0.47300124168395996,
      "learning_rate": 2e-05,
      "loss": 0.6719,
      "step": 1090
    },
    {
      "epoch": 0.09263157894736843,
      "grad_norm": 0.4323350191116333,
      "learning_rate": 2e-05,
      "loss": 0.6504,
      "step": 1100
    },
    {
      "epoch": 0.09347368421052632,
      "grad_norm": 0.4604896903038025,
      "learning_rate": 2e-05,
      "loss": 0.6919,
      "step": 1110
    },
    {
      "epoch": 0.09431578947368421,
      "grad_norm": 0.5188210010528564,
      "learning_rate": 2e-05,
      "loss": 0.6535,
      "step": 1120
    },
    {
      "epoch": 0.09515789473684211,
      "grad_norm": 0.45725199580192566,
      "learning_rate": 2e-05,
      "loss": 0.6514,
      "step": 1130
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.5177894234657288,
      "learning_rate": 2e-05,
      "loss": 0.6717,
      "step": 1140
    },
    {
      "epoch": 0.0968421052631579,
      "grad_norm": 0.4111453592777252,
      "learning_rate": 2e-05,
      "loss": 0.6502,
      "step": 1150
    },
    {
      "epoch": 0.09768421052631579,
      "grad_norm": 0.4603477716445923,
      "learning_rate": 2e-05,
      "loss": 0.6706,
      "step": 1160
    },
    {
      "epoch": 0.09852631578947368,
      "grad_norm": 0.46829044818878174,
      "learning_rate": 2e-05,
      "loss": 0.6777,
      "step": 1170
    },
    {
      "epoch": 0.09936842105263158,
      "grad_norm": 0.4708096981048584,
      "learning_rate": 2e-05,
      "loss": 0.6644,
      "step": 1180
    },
    {
      "epoch": 0.10021052631578947,
      "grad_norm": 0.549617350101471,
      "learning_rate": 2e-05,
      "loss": 0.6651,
      "step": 1190
    },
    {
      "epoch": 0.10105263157894737,
      "grad_norm": 0.4585419297218323,
      "learning_rate": 2e-05,
      "loss": 0.6312,
      "step": 1200
    },
    {
      "epoch": 0.10189473684210526,
      "grad_norm": 0.44110795855522156,
      "learning_rate": 2e-05,
      "loss": 0.6528,
      "step": 1210
    },
    {
      "epoch": 0.10273684210526315,
      "grad_norm": 0.43249937891960144,
      "learning_rate": 2e-05,
      "loss": 0.6506,
      "step": 1220
    },
    {
      "epoch": 0.10357894736842105,
      "grad_norm": 1.2289555072784424,
      "learning_rate": 2e-05,
      "loss": 0.6548,
      "step": 1230
    },
    {
      "epoch": 0.10442105263157894,
      "grad_norm": 0.446972131729126,
      "learning_rate": 2e-05,
      "loss": 0.6751,
      "step": 1240
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.4171697199344635,
      "learning_rate": 2e-05,
      "loss": 0.6726,
      "step": 1250
    },
    {
      "epoch": 0.10610526315789473,
      "grad_norm": 0.5522831678390503,
      "learning_rate": 2e-05,
      "loss": 0.6818,
      "step": 1260
    },
    {
      "epoch": 0.10694736842105264,
      "grad_norm": 0.4587099850177765,
      "learning_rate": 2e-05,
      "loss": 0.667,
      "step": 1270
    },
    {
      "epoch": 0.10778947368421053,
      "grad_norm": 0.458698034286499,
      "learning_rate": 2e-05,
      "loss": 0.6864,
      "step": 1280
    },
    {
      "epoch": 0.10863157894736843,
      "grad_norm": 0.4405956566333771,
      "learning_rate": 2e-05,
      "loss": 0.6711,
      "step": 1290
    },
    {
      "epoch": 0.10947368421052632,
      "grad_norm": 0.41542065143585205,
      "learning_rate": 2e-05,
      "loss": 0.6635,
      "step": 1300
    },
    {
      "epoch": 0.11031578947368421,
      "grad_norm": 0.45384955406188965,
      "learning_rate": 2e-05,
      "loss": 0.6456,
      "step": 1310
    },
    {
      "epoch": 0.11115789473684211,
      "grad_norm": 0.4372265636920929,
      "learning_rate": 2e-05,
      "loss": 0.6656,
      "step": 1320
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.4737173318862915,
      "learning_rate": 2e-05,
      "loss": 0.6733,
      "step": 1330
    },
    {
      "epoch": 0.1128421052631579,
      "grad_norm": 0.45308926701545715,
      "learning_rate": 2e-05,
      "loss": 0.6657,
      "step": 1340
    },
    {
      "epoch": 0.11368421052631579,
      "grad_norm": 0.5928835868835449,
      "learning_rate": 2e-05,
      "loss": 0.6444,
      "step": 1350
    },
    {
      "epoch": 0.11452631578947368,
      "grad_norm": 0.4407281279563904,
      "learning_rate": 2e-05,
      "loss": 0.6676,
      "step": 1360
    },
    {
      "epoch": 0.11536842105263158,
      "grad_norm": 0.4661693871021271,
      "learning_rate": 2e-05,
      "loss": 0.6484,
      "step": 1370
    },
    {
      "epoch": 0.11621052631578947,
      "grad_norm": 0.42691245675086975,
      "learning_rate": 2e-05,
      "loss": 0.6584,
      "step": 1380
    },
    {
      "epoch": 0.11705263157894737,
      "grad_norm": 0.47203555703163147,
      "learning_rate": 2e-05,
      "loss": 0.6474,
      "step": 1390
    },
    {
      "epoch": 0.11789473684210526,
      "grad_norm": 0.5509248375892639,
      "learning_rate": 2e-05,
      "loss": 0.6564,
      "step": 1400
    },
    {
      "epoch": 0.11873684210526315,
      "grad_norm": 0.4351705312728882,
      "learning_rate": 2e-05,
      "loss": 0.6395,
      "step": 1410
    },
    {
      "epoch": 0.11957894736842105,
      "grad_norm": 0.47608712315559387,
      "learning_rate": 2e-05,
      "loss": 0.6501,
      "step": 1420
    },
    {
      "epoch": 0.12042105263157894,
      "grad_norm": 0.4292226731777191,
      "learning_rate": 2e-05,
      "loss": 0.6558,
      "step": 1430
    },
    {
      "epoch": 0.12126315789473684,
      "grad_norm": 0.45191818475723267,
      "learning_rate": 2e-05,
      "loss": 0.6883,
      "step": 1440
    },
    {
      "epoch": 0.12210526315789473,
      "grad_norm": 0.4589603543281555,
      "learning_rate": 2e-05,
      "loss": 0.6898,
      "step": 1450
    },
    {
      "epoch": 0.12294736842105262,
      "grad_norm": 0.43541625142097473,
      "learning_rate": 2e-05,
      "loss": 0.6486,
      "step": 1460
    },
    {
      "epoch": 0.12378947368421053,
      "grad_norm": 0.445057213306427,
      "learning_rate": 2e-05,
      "loss": 0.6617,
      "step": 1470
    },
    {
      "epoch": 0.12463157894736843,
      "grad_norm": 0.46918973326683044,
      "learning_rate": 2e-05,
      "loss": 0.6665,
      "step": 1480
    },
    {
      "epoch": 0.12547368421052632,
      "grad_norm": 0.43344002962112427,
      "learning_rate": 2e-05,
      "loss": 0.6417,
      "step": 1490
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.4777977168560028,
      "learning_rate": 2e-05,
      "loss": 0.6682,
      "step": 1500
    },
    {
      "epoch": 0.1271578947368421,
      "grad_norm": 0.5021777153015137,
      "learning_rate": 2e-05,
      "loss": 0.6712,
      "step": 1510
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.4618164300918579,
      "learning_rate": 2e-05,
      "loss": 0.6564,
      "step": 1520
    },
    {
      "epoch": 0.1288421052631579,
      "grad_norm": 0.40703055262565613,
      "learning_rate": 2e-05,
      "loss": 0.6763,
      "step": 1530
    },
    {
      "epoch": 0.1296842105263158,
      "grad_norm": 0.45353758335113525,
      "learning_rate": 2e-05,
      "loss": 0.652,
      "step": 1540
    },
    {
      "epoch": 0.13052631578947368,
      "grad_norm": 0.4652615189552307,
      "learning_rate": 2e-05,
      "loss": 0.6308,
      "step": 1550
    },
    {
      "epoch": 0.13136842105263158,
      "grad_norm": 0.4542207419872284,
      "learning_rate": 2e-05,
      "loss": 0.6535,
      "step": 1560
    },
    {
      "epoch": 0.13221052631578947,
      "grad_norm": 0.4470004141330719,
      "learning_rate": 2e-05,
      "loss": 0.6408,
      "step": 1570
    },
    {
      "epoch": 0.13305263157894737,
      "grad_norm": 0.40870246291160583,
      "learning_rate": 2e-05,
      "loss": 0.6644,
      "step": 1580
    },
    {
      "epoch": 0.13389473684210526,
      "grad_norm": 0.42540448904037476,
      "learning_rate": 2e-05,
      "loss": 0.6327,
      "step": 1590
    },
    {
      "epoch": 0.13473684210526315,
      "grad_norm": 0.4614720046520233,
      "learning_rate": 2e-05,
      "loss": 0.6607,
      "step": 1600
    },
    {
      "epoch": 0.13557894736842105,
      "grad_norm": 0.4467135965824127,
      "learning_rate": 2e-05,
      "loss": 0.6814,
      "step": 1610
    },
    {
      "epoch": 0.13642105263157894,
      "grad_norm": 0.4206336438655853,
      "learning_rate": 2e-05,
      "loss": 0.6639,
      "step": 1620
    },
    {
      "epoch": 0.13726315789473684,
      "grad_norm": 0.48927173018455505,
      "learning_rate": 2e-05,
      "loss": 0.6688,
      "step": 1630
    },
    {
      "epoch": 0.13810526315789473,
      "grad_norm": 0.45843756198883057,
      "learning_rate": 2e-05,
      "loss": 0.6575,
      "step": 1640
    },
    {
      "epoch": 0.13894736842105262,
      "grad_norm": 0.449156254529953,
      "learning_rate": 2e-05,
      "loss": 0.6458,
      "step": 1650
    },
    {
      "epoch": 0.13978947368421052,
      "grad_norm": 0.4332134425640106,
      "learning_rate": 2e-05,
      "loss": 0.6432,
      "step": 1660
    },
    {
      "epoch": 0.1406315789473684,
      "grad_norm": 0.42238250374794006,
      "learning_rate": 2e-05,
      "loss": 0.6419,
      "step": 1670
    },
    {
      "epoch": 0.1414736842105263,
      "grad_norm": 0.4564463198184967,
      "learning_rate": 2e-05,
      "loss": 0.6476,
      "step": 1680
    },
    {
      "epoch": 0.1423157894736842,
      "grad_norm": 0.44483888149261475,
      "learning_rate": 2e-05,
      "loss": 0.6517,
      "step": 1690
    },
    {
      "epoch": 0.1431578947368421,
      "grad_norm": 0.5297313332557678,
      "learning_rate": 2e-05,
      "loss": 0.6585,
      "step": 1700
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.40007227659225464,
      "learning_rate": 2e-05,
      "loss": 0.6309,
      "step": 1710
    },
    {
      "epoch": 0.14484210526315788,
      "grad_norm": 0.4941370487213135,
      "learning_rate": 2e-05,
      "loss": 0.6561,
      "step": 1720
    },
    {
      "epoch": 0.14568421052631578,
      "grad_norm": 0.43409863114356995,
      "learning_rate": 2e-05,
      "loss": 0.6369,
      "step": 1730
    },
    {
      "epoch": 0.14652631578947367,
      "grad_norm": 0.44366204738616943,
      "learning_rate": 2e-05,
      "loss": 0.6416,
      "step": 1740
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.4011799395084381,
      "learning_rate": 2e-05,
      "loss": 0.6538,
      "step": 1750
    },
    {
      "epoch": 0.1482105263157895,
      "grad_norm": 0.40802836418151855,
      "learning_rate": 2e-05,
      "loss": 0.6335,
      "step": 1760
    },
    {
      "epoch": 0.14905263157894738,
      "grad_norm": 0.4368784427642822,
      "learning_rate": 2e-05,
      "loss": 0.67,
      "step": 1770
    },
    {
      "epoch": 0.14989473684210528,
      "grad_norm": 0.4641876816749573,
      "learning_rate": 2e-05,
      "loss": 0.65,
      "step": 1780
    },
    {
      "epoch": 0.15073684210526317,
      "grad_norm": 0.4642079174518585,
      "learning_rate": 2e-05,
      "loss": 0.6557,
      "step": 1790
    },
    {
      "epoch": 0.15157894736842106,
      "grad_norm": 0.4088793396949768,
      "learning_rate": 2e-05,
      "loss": 0.6439,
      "step": 1800
    },
    {
      "epoch": 0.15242105263157896,
      "grad_norm": 0.7351284027099609,
      "learning_rate": 2e-05,
      "loss": 0.6546,
      "step": 1810
    },
    {
      "epoch": 0.15326315789473685,
      "grad_norm": 0.43712669610977173,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 1820
    },
    {
      "epoch": 0.15410526315789475,
      "grad_norm": 0.4419451951980591,
      "learning_rate": 2e-05,
      "loss": 0.6759,
      "step": 1830
    },
    {
      "epoch": 0.15494736842105264,
      "grad_norm": 0.49290475249290466,
      "learning_rate": 2e-05,
      "loss": 0.6478,
      "step": 1840
    },
    {
      "epoch": 0.15578947368421053,
      "grad_norm": 0.4438256323337555,
      "learning_rate": 2e-05,
      "loss": 0.6812,
      "step": 1850
    },
    {
      "epoch": 0.15663157894736843,
      "grad_norm": 0.40685737133026123,
      "learning_rate": 2e-05,
      "loss": 0.6719,
      "step": 1860
    },
    {
      "epoch": 0.15747368421052632,
      "grad_norm": 0.49131378531455994,
      "learning_rate": 2e-05,
      "loss": 0.6722,
      "step": 1870
    },
    {
      "epoch": 0.15831578947368422,
      "grad_norm": 0.4030827283859253,
      "learning_rate": 2e-05,
      "loss": 0.6466,
      "step": 1880
    },
    {
      "epoch": 0.1591578947368421,
      "grad_norm": 1.2659680843353271,
      "learning_rate": 2e-05,
      "loss": 0.6377,
      "step": 1890
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.4396963119506836,
      "learning_rate": 2e-05,
      "loss": 0.6758,
      "step": 1900
    },
    {
      "epoch": 0.1608421052631579,
      "grad_norm": 0.42015787959098816,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 1910
    },
    {
      "epoch": 0.1616842105263158,
      "grad_norm": 0.3945922553539276,
      "learning_rate": 2e-05,
      "loss": 0.6597,
      "step": 1920
    },
    {
      "epoch": 0.16252631578947369,
      "grad_norm": 0.4661765396595001,
      "learning_rate": 2e-05,
      "loss": 0.654,
      "step": 1930
    },
    {
      "epoch": 0.16336842105263158,
      "grad_norm": 0.42668765783309937,
      "learning_rate": 2e-05,
      "loss": 0.6621,
      "step": 1940
    },
    {
      "epoch": 0.16421052631578947,
      "grad_norm": 0.42763540148735046,
      "learning_rate": 2e-05,
      "loss": 0.672,
      "step": 1950
    },
    {
      "epoch": 0.16505263157894737,
      "grad_norm": 0.449554443359375,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 1960
    },
    {
      "epoch": 0.16589473684210526,
      "grad_norm": 0.3989042341709137,
      "learning_rate": 2e-05,
      "loss": 0.6293,
      "step": 1970
    },
    {
      "epoch": 0.16673684210526316,
      "grad_norm": 0.3974854648113251,
      "learning_rate": 2e-05,
      "loss": 0.6444,
      "step": 1980
    },
    {
      "epoch": 0.16757894736842105,
      "grad_norm": 0.4603552222251892,
      "learning_rate": 2e-05,
      "loss": 0.6417,
      "step": 1990
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.42975977063179016,
      "learning_rate": 2e-05,
      "loss": 0.6428,
      "step": 2000
    },
    {
      "epoch": 0.16926315789473684,
      "grad_norm": 0.4494156241416931,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 2010
    },
    {
      "epoch": 0.17010526315789473,
      "grad_norm": 0.43503236770629883,
      "learning_rate": 2e-05,
      "loss": 0.6475,
      "step": 2020
    },
    {
      "epoch": 0.17094736842105263,
      "grad_norm": 0.4536204934120178,
      "learning_rate": 2e-05,
      "loss": 0.6413,
      "step": 2030
    },
    {
      "epoch": 0.17178947368421052,
      "grad_norm": 0.44027554988861084,
      "learning_rate": 2e-05,
      "loss": 0.6308,
      "step": 2040
    },
    {
      "epoch": 0.1726315789473684,
      "grad_norm": 0.43327200412750244,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 2050
    },
    {
      "epoch": 0.1734736842105263,
      "grad_norm": 0.45290684700012207,
      "learning_rate": 2e-05,
      "loss": 0.6468,
      "step": 2060
    },
    {
      "epoch": 0.1743157894736842,
      "grad_norm": 0.4675568640232086,
      "learning_rate": 2e-05,
      "loss": 0.6374,
      "step": 2070
    },
    {
      "epoch": 0.1751578947368421,
      "grad_norm": 0.4425695836544037,
      "learning_rate": 2e-05,
      "loss": 0.6317,
      "step": 2080
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.42776045203208923,
      "learning_rate": 2e-05,
      "loss": 0.6872,
      "step": 2090
    },
    {
      "epoch": 0.17684210526315788,
      "grad_norm": 0.4114616811275482,
      "learning_rate": 2e-05,
      "loss": 0.6337,
      "step": 2100
    },
    {
      "epoch": 0.17768421052631578,
      "grad_norm": 0.41503867506980896,
      "learning_rate": 2e-05,
      "loss": 0.6504,
      "step": 2110
    },
    {
      "epoch": 0.17852631578947367,
      "grad_norm": 0.4861103594303131,
      "learning_rate": 2e-05,
      "loss": 0.6585,
      "step": 2120
    },
    {
      "epoch": 0.17936842105263157,
      "grad_norm": 0.512718141078949,
      "learning_rate": 2e-05,
      "loss": 0.653,
      "step": 2130
    },
    {
      "epoch": 0.18021052631578946,
      "grad_norm": 0.45127350091934204,
      "learning_rate": 2e-05,
      "loss": 0.6752,
      "step": 2140
    },
    {
      "epoch": 0.18105263157894738,
      "grad_norm": 0.3995113670825958,
      "learning_rate": 2e-05,
      "loss": 0.6498,
      "step": 2150
    },
    {
      "epoch": 0.18189473684210528,
      "grad_norm": 0.39956554770469666,
      "learning_rate": 2e-05,
      "loss": 0.6284,
      "step": 2160
    },
    {
      "epoch": 0.18273684210526317,
      "grad_norm": 0.5028399229049683,
      "learning_rate": 2e-05,
      "loss": 0.6669,
      "step": 2170
    },
    {
      "epoch": 0.18357894736842106,
      "grad_norm": 0.4250260591506958,
      "learning_rate": 2e-05,
      "loss": 0.6449,
      "step": 2180
    },
    {
      "epoch": 0.18442105263157896,
      "grad_norm": 0.4396851658821106,
      "learning_rate": 2e-05,
      "loss": 0.6561,
      "step": 2190
    },
    {
      "epoch": 0.18526315789473685,
      "grad_norm": 0.49678802490234375,
      "learning_rate": 2e-05,
      "loss": 0.6744,
      "step": 2200
    },
    {
      "epoch": 0.18610526315789475,
      "grad_norm": 0.49938711524009705,
      "learning_rate": 2e-05,
      "loss": 0.6266,
      "step": 2210
    },
    {
      "epoch": 0.18694736842105264,
      "grad_norm": 0.4113972783088684,
      "learning_rate": 2e-05,
      "loss": 0.6611,
      "step": 2220
    },
    {
      "epoch": 0.18778947368421053,
      "grad_norm": 0.4604727029800415,
      "learning_rate": 2e-05,
      "loss": 0.6476,
      "step": 2230
    },
    {
      "epoch": 0.18863157894736843,
      "grad_norm": 0.39633166790008545,
      "learning_rate": 2e-05,
      "loss": 0.6588,
      "step": 2240
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 0.39922624826431274,
      "learning_rate": 2e-05,
      "loss": 0.6544,
      "step": 2250
    },
    {
      "epoch": 0.19031578947368422,
      "grad_norm": 0.4407571852207184,
      "learning_rate": 2e-05,
      "loss": 0.6725,
      "step": 2260
    },
    {
      "epoch": 0.1911578947368421,
      "grad_norm": 0.4127040505409241,
      "learning_rate": 2e-05,
      "loss": 0.6622,
      "step": 2270
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.42205244302749634,
      "learning_rate": 2e-05,
      "loss": 0.6445,
      "step": 2280
    },
    {
      "epoch": 0.1928421052631579,
      "grad_norm": 0.4369538724422455,
      "learning_rate": 2e-05,
      "loss": 0.6544,
      "step": 2290
    },
    {
      "epoch": 0.1936842105263158,
      "grad_norm": 0.46700286865234375,
      "learning_rate": 2e-05,
      "loss": 0.6546,
      "step": 2300
    },
    {
      "epoch": 0.19452631578947369,
      "grad_norm": 1.3719345331192017,
      "learning_rate": 2e-05,
      "loss": 0.662,
      "step": 2310
    },
    {
      "epoch": 0.19536842105263158,
      "grad_norm": 0.8232142925262451,
      "learning_rate": 2e-05,
      "loss": 0.6373,
      "step": 2320
    },
    {
      "epoch": 0.19621052631578947,
      "grad_norm": 0.45501574873924255,
      "learning_rate": 2e-05,
      "loss": 0.663,
      "step": 2330
    },
    {
      "epoch": 0.19705263157894737,
      "grad_norm": 0.38035255670547485,
      "learning_rate": 2e-05,
      "loss": 0.6413,
      "step": 2340
    },
    {
      "epoch": 0.19789473684210526,
      "grad_norm": 0.42564475536346436,
      "learning_rate": 2e-05,
      "loss": 0.6566,
      "step": 2350
    },
    {
      "epoch": 0.19873684210526316,
      "grad_norm": 0.42836716771125793,
      "learning_rate": 2e-05,
      "loss": 0.6443,
      "step": 2360
    },
    {
      "epoch": 0.19957894736842105,
      "grad_norm": 0.4486235976219177,
      "learning_rate": 2e-05,
      "loss": 0.6445,
      "step": 2370
    },
    {
      "epoch": 0.20042105263157894,
      "grad_norm": 0.43508684635162354,
      "learning_rate": 2e-05,
      "loss": 0.6485,
      "step": 2380
    },
    {
      "epoch": 0.20126315789473684,
      "grad_norm": 0.43823474645614624,
      "learning_rate": 2e-05,
      "loss": 0.6319,
      "step": 2390
    },
    {
      "epoch": 0.20210526315789473,
      "grad_norm": 0.4307081699371338,
      "learning_rate": 2e-05,
      "loss": 0.6383,
      "step": 2400
    },
    {
      "epoch": 0.20294736842105263,
      "grad_norm": 0.45380184054374695,
      "learning_rate": 2e-05,
      "loss": 0.6461,
      "step": 2410
    },
    {
      "epoch": 0.20378947368421052,
      "grad_norm": 0.4245603084564209,
      "learning_rate": 2e-05,
      "loss": 0.6485,
      "step": 2420
    },
    {
      "epoch": 0.20463157894736841,
      "grad_norm": 0.42921018600463867,
      "learning_rate": 2e-05,
      "loss": 0.6598,
      "step": 2430
    },
    {
      "epoch": 0.2054736842105263,
      "grad_norm": 0.40832093358039856,
      "learning_rate": 2e-05,
      "loss": 0.6429,
      "step": 2440
    },
    {
      "epoch": 0.2063157894736842,
      "grad_norm": 0.40788644552230835,
      "learning_rate": 2e-05,
      "loss": 0.6509,
      "step": 2450
    },
    {
      "epoch": 0.2071578947368421,
      "grad_norm": 0.3845847547054291,
      "learning_rate": 2e-05,
      "loss": 0.6618,
      "step": 2460
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.4283493161201477,
      "learning_rate": 2e-05,
      "loss": 0.6459,
      "step": 2470
    },
    {
      "epoch": 0.20884210526315788,
      "grad_norm": 0.4894337058067322,
      "learning_rate": 2e-05,
      "loss": 0.6477,
      "step": 2480
    },
    {
      "epoch": 0.20968421052631578,
      "grad_norm": 0.5109031200408936,
      "learning_rate": 2e-05,
      "loss": 0.6527,
      "step": 2490
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.44362136721611023,
      "learning_rate": 2e-05,
      "loss": 0.63,
      "step": 2500
    },
    {
      "epoch": 0.21136842105263157,
      "grad_norm": 0.40784358978271484,
      "learning_rate": 2e-05,
      "loss": 0.6499,
      "step": 2510
    },
    {
      "epoch": 0.21221052631578946,
      "grad_norm": 0.37488508224487305,
      "learning_rate": 2e-05,
      "loss": 0.6355,
      "step": 2520
    },
    {
      "epoch": 0.21305263157894735,
      "grad_norm": 0.40795764327049255,
      "learning_rate": 2e-05,
      "loss": 0.646,
      "step": 2530
    },
    {
      "epoch": 0.21389473684210528,
      "grad_norm": 0.4658086895942688,
      "learning_rate": 2e-05,
      "loss": 0.6756,
      "step": 2540
    },
    {
      "epoch": 0.21473684210526317,
      "grad_norm": 0.44552069902420044,
      "learning_rate": 1.997261400182901e-05,
      "loss": 0.6718,
      "step": 2550
    },
    {
      "epoch": 0.21557894736842106,
      "grad_norm": 0.41642454266548157,
      "learning_rate": 1.9805800746810423e-05,
      "loss": 0.6447,
      "step": 2560
    },
    {
      "epoch": 0.21642105263157896,
      "grad_norm": 0.5255375504493713,
      "learning_rate": 1.9489934220110274e-05,
      "loss": 0.6336,
      "step": 2570
    },
    {
      "epoch": 0.21726315789473685,
      "grad_norm": 0.40813690423965454,
      "learning_rate": 1.9029840364820392e-05,
      "loss": 0.6255,
      "step": 2580
    },
    {
      "epoch": 0.21810526315789475,
      "grad_norm": 0.39391443133354187,
      "learning_rate": 1.8432548690479908e-05,
      "loss": 0.6326,
      "step": 2590
    },
    {
      "epoch": 0.21894736842105264,
      "grad_norm": 0.4173458516597748,
      "learning_rate": 1.7707184873239772e-05,
      "loss": 0.652,
      "step": 2600
    },
    {
      "epoch": 0.21978947368421053,
      "grad_norm": 0.3993004560470581,
      "learning_rate": 1.6864831329902565e-05,
      "loss": 0.6435,
      "step": 2610
    },
    {
      "epoch": 0.22063157894736843,
      "grad_norm": 0.47844523191452026,
      "learning_rate": 1.591835789604667e-05,
      "loss": 0.6501,
      "step": 2620
    },
    {
      "epoch": 0.22147368421052632,
      "grad_norm": 0.4590757489204407,
      "learning_rate": 1.4882225195206459e-05,
      "loss": 0.6605,
      "step": 2630
    },
    {
      "epoch": 0.22231578947368422,
      "grad_norm": 0.4211150109767914,
      "learning_rate": 1.3772263703317695e-05,
      "loss": 0.6538,
      "step": 2640
    },
    {
      "epoch": 0.2231578947368421,
      "grad_norm": 0.4034784138202667,
      "learning_rate": 1.2605431883975547e-05,
      "loss": 0.6562,
      "step": 2650
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.4007567763328552,
      "learning_rate": 1.1399557089817574e-05,
      "loss": 0.6367,
      "step": 2660
    },
    {
      "epoch": 0.2248421052631579,
      "grad_norm": 0.4099075496196747,
      "learning_rate": 1.0173063188650463e-05,
      "loss": 0.6304,
      "step": 2670
    },
    {
      "epoch": 0.2256842105263158,
      "grad_norm": 0.40898409485816956,
      "learning_rate": 8.944689075764396e-06,
      "loss": 0.641,
      "step": 2680
    },
    {
      "epoch": 0.2265263157894737,
      "grad_norm": 0.4005719721317291,
      "learning_rate": 7.73320237312362e-06,
      "loss": 0.6609,
      "step": 2690
    },
    {
      "epoch": 0.22736842105263158,
      "grad_norm": 0.4293281137943268,
      "learning_rate": 6.557112689658629e-06,
      "loss": 0.6312,
      "step": 2700
    },
    {
      "epoch": 0.22821052631578947,
      "grad_norm": 0.3957161009311676,
      "learning_rate": 5.434388823591213e-06,
      "loss": 0.6487,
      "step": 2710
    },
    {
      "epoch": 0.22905263157894737,
      "grad_norm": 0.41935431957244873,
      "learning_rate": 4.382184227495424e-06,
      "loss": 0.6304,
      "step": 2720
    },
    {
      "epoch": 0.22989473684210526,
      "grad_norm": 0.4202288091182709,
      "learning_rate": 3.4165749305560203e-06,
      "loss": 0.6359,
      "step": 2730
    },
    {
      "epoch": 0.23073684210526316,
      "grad_norm": 0.3848573863506317,
      "learning_rate": 2.5523139221595556e-06,
      "loss": 0.6066,
      "step": 2740
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 0.4024999737739563,
      "learning_rate": 1.8026057494499821e-06,
      "loss": 0.6402,
      "step": 2750
    },
    {
      "epoch": 0.23242105263157894,
      "grad_norm": 0.42342954874038696,
      "learning_rate": 1.178904772643223e-06,
      "loss": 0.6685,
      "step": 2760
    },
    {
      "epoch": 0.23326315789473684,
      "grad_norm": 0.3709671199321747,
      "learning_rate": 6.90740160441754e-07,
      "loss": 0.6224,
      "step": 2770
    },
    {
      "epoch": 0.23410526315789473,
      "grad_norm": 0.3992233872413635,
      "learning_rate": 3.45570299343632e-07,
      "loss": 0.6497,
      "step": 2780
    },
    {
      "epoch": 0.23494736842105263,
      "grad_norm": 0.4092631936073303,
      "learning_rate": 1.486688412425152e-07,
      "loss": 0.6237,
      "step": 2790
    },
    {
      "epoch": 0.23553684210526316,
      "step": 2797,
      "total_flos": 1.2485883762455871e+19,
      "train_loss": 0.058299484873482875,
      "train_runtime": 2889.5425,
      "train_samples_per_second": 11.616,
      "train_steps_per_second": 0.968
    }
  ],
  "logging_steps": 10,
  "max_steps": 2797,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2543,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2485883762455871e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}