{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 972,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030864197530864196,
      "grad_norm": 5.566057508694927,
      "learning_rate": 1.0204081632653063e-06,
      "loss": 0.9078,
      "step": 10
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 2.402969993178742,
      "learning_rate": 2.0408163265306125e-06,
      "loss": 0.4908,
      "step": 20
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.5973191159110185,
      "learning_rate": 3.0612244897959185e-06,
      "loss": 0.3604,
      "step": 30
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 1.5212680542283326,
      "learning_rate": 4.081632653061225e-06,
      "loss": 0.2917,
      "step": 40
    },
    {
      "epoch": 0.15432098765432098,
      "grad_norm": 1.327762286536679,
      "learning_rate": 5.1020408163265315e-06,
      "loss": 0.2483,
      "step": 50
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.497773959020813,
      "learning_rate": 6.122448979591837e-06,
      "loss": 0.3335,
      "step": 60
    },
    {
      "epoch": 0.21604938271604937,
      "grad_norm": 1.452406056897556,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.2373,
      "step": 70
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.2333736335084606,
      "learning_rate": 8.16326530612245e-06,
      "loss": 0.2827,
      "step": 80
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.977571583115981,
      "learning_rate": 9.183673469387756e-06,
      "loss": 0.3493,
      "step": 90
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 0.43529393896151314,
      "learning_rate": 9.999870796282452e-06,
      "loss": 0.2379,
      "step": 100
    },
    {
      "epoch": 0.3395061728395062,
      "grad_norm": 1.1728868827035934,
      "learning_rate": 9.995349367260807e-06,
      "loss": 0.2865,
      "step": 110
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.8560454934036049,
      "learning_rate": 9.984374428250894e-06,
      "loss": 0.2797,
      "step": 120
    },
    {
      "epoch": 0.4012345679012346,
      "grad_norm": 0.8669441816278666,
      "learning_rate": 9.966960157816279e-06,
      "loss": 0.2909,
      "step": 130
    },
    {
      "epoch": 0.43209876543209874,
      "grad_norm": 1.1122798966875698,
      "learning_rate": 9.943129053516176e-06,
      "loss": 0.2224,
      "step": 140
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.3783001550147502,
      "learning_rate": 9.912911902840771e-06,
      "loss": 0.3475,
      "step": 150
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 1.1129606902235367,
      "learning_rate": 9.876347743436758e-06,
      "loss": 0.2754,
      "step": 160
    },
    {
      "epoch": 0.5246913580246914,
      "grad_norm": 0.5982987847884026,
      "learning_rate": 9.833483812674453e-06,
      "loss": 0.2668,
      "step": 170
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.151190335163041,
      "learning_rate": 9.78437548662167e-06,
      "loss": 0.304,
      "step": 180
    },
    {
      "epoch": 0.5864197530864198,
      "grad_norm": 0.9873399404098623,
      "learning_rate": 9.729086208503174e-06,
      "loss": 0.2839,
      "step": 190
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 1.0916371259601432,
      "learning_rate": 9.66768740673815e-06,
      "loss": 0.2536,
      "step": 200
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.8725822152638094,
      "learning_rate": 9.60025840266157e-06,
      "loss": 0.2941,
      "step": 210
    },
    {
      "epoch": 0.6790123456790124,
      "grad_norm": 0.9851282803801447,
      "learning_rate": 9.52688630804867e-06,
      "loss": 0.2636,
      "step": 220
    },
    {
      "epoch": 0.7098765432098766,
      "grad_norm": 1.2682899477638283,
      "learning_rate": 9.44766591257493e-06,
      "loss": 0.3098,
      "step": 230
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.9753967370936533,
      "learning_rate": 9.362699561356957e-06,
      "loss": 0.2596,
      "step": 240
    },
    {
      "epoch": 0.7716049382716049,
      "grad_norm": 1.2536107665402,
      "learning_rate": 9.272097022732444e-06,
      "loss": 0.3364,
      "step": 250
    },
    {
      "epoch": 0.8024691358024691,
      "grad_norm": 1.0948963090455852,
      "learning_rate": 9.175975346450063e-06,
      "loss": 0.2546,
      "step": 260
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.761843240861204,
      "learning_rate": 9.074458712452476e-06,
      "loss": 0.2366,
      "step": 270
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 1.183127668103192,
      "learning_rate": 8.9676782704478e-06,
      "loss": 0.2917,
      "step": 280
    },
    {
      "epoch": 0.8950617283950617,
      "grad_norm": 1.26099529846567,
      "learning_rate": 8.855771970476834e-06,
      "loss": 0.2808,
      "step": 290
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.2030992581122257,
      "learning_rate": 8.738884384694905e-06,
      "loss": 0.2532,
      "step": 300
    },
    {
      "epoch": 0.9567901234567902,
      "grad_norm": 0.9236541991188757,
      "learning_rate": 8.617166520598563e-06,
      "loss": 0.2135,
      "step": 310
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 1.142242691308657,
      "learning_rate": 8.490775625938452e-06,
      "loss": 0.248,
      "step": 320
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 0.9358677809806952,
      "learning_rate": 8.359874985570378e-06,
      "loss": 0.156,
      "step": 330
    },
    {
      "epoch": 1.0493827160493827,
      "grad_norm": 0.9685063215738038,
      "learning_rate": 8.224633710506997e-06,
      "loss": 0.1483,
      "step": 340
    },
    {
      "epoch": 1.0802469135802468,
      "grad_norm": 0.9972139407992048,
      "learning_rate": 8.085226519442697e-06,
      "loss": 0.1773,
      "step": 350
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.7866994795730093,
      "learning_rate": 7.941833513033873e-06,
      "loss": 0.1674,
      "step": 360
    },
    {
      "epoch": 1.1419753086419753,
      "grad_norm": 1.3594591232427207,
      "learning_rate": 7.794639941226238e-06,
      "loss": 0.1996,
      "step": 370
    },
    {
      "epoch": 1.1728395061728394,
      "grad_norm": 1.336485058939724,
      "learning_rate": 7.643835963929747e-06,
      "loss": 0.1992,
      "step": 380
    },
    {
      "epoch": 1.2037037037037037,
      "grad_norm": 1.0894387345805672,
      "learning_rate": 7.489616405350319e-06,
      "loss": 0.2009,
      "step": 390
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 0.8521396408327715,
      "learning_rate": 7.332180502295729e-06,
      "loss": 0.1551,
      "step": 400
    },
    {
      "epoch": 1.2654320987654322,
      "grad_norm": 1.280235377415998,
      "learning_rate": 7.171731646780867e-06,
      "loss": 0.1903,
      "step": 410
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 1.0177820006481466,
      "learning_rate": 7.008477123264849e-06,
      "loss": 0.1919,
      "step": 420
    },
    {
      "epoch": 1.3271604938271606,
      "grad_norm": 1.3792449227303458,
      "learning_rate": 6.842627840859461e-06,
      "loss": 0.1653,
      "step": 430
    },
    {
      "epoch": 1.3580246913580247,
      "grad_norm": 0.9886652944346411,
      "learning_rate": 6.674398060854931e-06,
      "loss": 0.1528,
      "step": 440
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.9738749120684131,
      "learning_rate": 6.5040051199149755e-06,
      "loss": 0.1859,
      "step": 450
    },
    {
      "epoch": 1.4197530864197532,
      "grad_norm": 1.0499735220491768,
      "learning_rate": 6.331669149298781e-06,
      "loss": 0.2089,
      "step": 460
    },
    {
      "epoch": 1.4506172839506173,
      "grad_norm": 1.3564424657138714,
      "learning_rate": 6.157612790472626e-06,
      "loss": 0.1956,
      "step": 470
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.7943373995297914,
      "learning_rate": 5.982060907478568e-06,
      "loss": 0.1462,
      "step": 480
    },
    {
      "epoch": 1.5123456790123457,
      "grad_norm": 1.5557938987689983,
      "learning_rate": 5.805240296431765e-06,
      "loss": 0.2092,
      "step": 490
    },
    {
      "epoch": 1.5432098765432098,
      "grad_norm": 0.9522144954857849,
      "learning_rate": 5.627379392521758e-06,
      "loss": 0.1653,
      "step": 500
    },
    {
      "epoch": 1.5432098765432098,
      "eval_loss": 0.23522016406059265,
      "eval_runtime": 72.3023,
      "eval_samples_per_second": 7.967,
      "eval_steps_per_second": 7.967,
      "step": 500
    },
    {
      "epoch": 1.574074074074074,
      "grad_norm": 1.0277772820113307,
      "learning_rate": 5.448707974896214e-06,
      "loss": 0.1934,
      "step": 510
    },
    {
      "epoch": 1.6049382716049383,
      "grad_norm": 1.498458469156437,
      "learning_rate": 5.2694568698084085e-06,
      "loss": 0.2338,
      "step": 520
    },
    {
      "epoch": 1.6358024691358026,
      "grad_norm": 1.2380870016139613,
      "learning_rate": 5.089857652411961e-06,
      "loss": 0.1551,
      "step": 530
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.2431560615526187,
      "learning_rate": 4.910142347588041e-06,
      "loss": 0.211,
      "step": 540
    },
    {
      "epoch": 1.6975308641975309,
      "grad_norm": 0.8069111004848413,
      "learning_rate": 4.730543130191594e-06,
      "loss": 0.1598,
      "step": 550
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 0.748202151488271,
      "learning_rate": 4.551292025103789e-06,
      "loss": 0.1465,
      "step": 560
    },
    {
      "epoch": 1.7592592592592593,
      "grad_norm": 0.775409645399768,
      "learning_rate": 4.372620607478242e-06,
      "loss": 0.152,
      "step": 570
    },
    {
      "epoch": 1.7901234567901234,
      "grad_norm": 0.919987356247785,
      "learning_rate": 4.1947597035682355e-06,
      "loss": 0.2149,
      "step": 580
    },
    {
      "epoch": 1.8209876543209877,
      "grad_norm": 1.1312605755339111,
      "learning_rate": 4.017939092521434e-06,
      "loss": 0.1777,
      "step": 590
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 1.3626643893639394,
      "learning_rate": 3.842387209527374e-06,
      "loss": 0.1829,
      "step": 600
    },
    {
      "epoch": 1.882716049382716,
      "grad_norm": 1.227575534766062,
      "learning_rate": 3.6683308507012196e-06,
      "loss": 0.1799,
      "step": 610
    },
    {
      "epoch": 1.9135802469135803,
      "grad_norm": 1.2174251384264219,
      "learning_rate": 3.4959948800850253e-06,
      "loss": 0.1362,
      "step": 620
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 1.1078151820356543,
      "learning_rate": 3.3256019391450696e-06,
      "loss": 0.1562,
      "step": 630
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 1.0667445790104497,
      "learning_rate": 3.1573721591405405e-06,
      "loss": 0.1792,
      "step": 640
    },
    {
      "epoch": 2.006172839506173,
      "grad_norm": 0.9627653971639197,
      "learning_rate": 2.991522876735154e-06,
      "loss": 0.1473,
      "step": 650
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 0.8420822083166241,
      "learning_rate": 2.8282683532191333e-06,
      "loss": 0.0994,
      "step": 660
    },
    {
      "epoch": 2.067901234567901,
      "grad_norm": 1.001599199308316,
      "learning_rate": 2.6678194977042727e-06,
      "loss": 0.0865,
      "step": 670
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 0.9784608307244814,
      "learning_rate": 2.5103835946496846e-06,
      "loss": 0.1042,
      "step": 680
    },
    {
      "epoch": 2.1296296296296298,
      "grad_norm": 1.258037980079001,
      "learning_rate": 2.3561640360702525e-06,
      "loss": 0.0687,
      "step": 690
    },
    {
      "epoch": 2.1604938271604937,
      "grad_norm": 1.0158830256095577,
      "learning_rate": 2.205360058773764e-06,
      "loss": 0.0784,
      "step": 700
    },
    {
      "epoch": 2.191358024691358,
      "grad_norm": 0.9515473229873379,
      "learning_rate": 2.058166486966128e-06,
      "loss": 0.1027,
      "step": 710
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.9896704595537134,
      "learning_rate": 1.914773480557304e-06,
      "loss": 0.0921,
      "step": 720
    },
    {
      "epoch": 2.253086419753086,
      "grad_norm": 1.200715350686628,
      "learning_rate": 1.775366289493003e-06,
      "loss": 0.0772,
      "step": 730
    },
    {
      "epoch": 2.2839506172839505,
      "grad_norm": 1.2889212786691133,
      "learning_rate": 1.6401250144296239e-06,
      "loss": 0.0951,
      "step": 740
    },
    {
      "epoch": 2.314814814814815,
      "grad_norm": 1.364590190580036,
      "learning_rate": 1.5092243740615486e-06,
      "loss": 0.0871,
      "step": 750
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 1.0124869207352833,
      "learning_rate": 1.382833479401438e-06,
      "loss": 0.099,
      "step": 760
    },
    {
      "epoch": 2.376543209876543,
      "grad_norm": 1.0379306151771268,
      "learning_rate": 1.2611156153050963e-06,
      "loss": 0.1116,
      "step": 770
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 0.9907248139219855,
      "learning_rate": 1.1442280295231656e-06,
      "loss": 0.0753,
      "step": 780
    },
    {
      "epoch": 2.4382716049382718,
      "grad_norm": 1.1280634693251803,
      "learning_rate": 1.0323217295522026e-06,
      "loss": 0.0875,
      "step": 790
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 0.9944383353033676,
      "learning_rate": 9.255412875475256e-07,
      "loss": 0.0926,
      "step": 800
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.2340366986358158,
      "learning_rate": 8.240246535499369e-07,
      "loss": 0.0856,
      "step": 810
    },
    {
      "epoch": 2.5308641975308643,
      "grad_norm": 0.7578751117138942,
      "learning_rate": 7.279029772675572e-07,
      "loss": 0.0995,
      "step": 820
    },
    {
      "epoch": 2.5617283950617287,
      "grad_norm": 0.7485029876002154,
      "learning_rate": 6.373004386430442e-07,
      "loss": 0.0832,
      "step": 830
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 1.236625972178977,
      "learning_rate": 5.523340874250704e-07,
      "loss": 0.0927,
      "step": 840
    },
    {
      "epoch": 2.623456790123457,
      "grad_norm": 1.2710363913669391,
      "learning_rate": 4.7311369195133127e-07,
      "loss": 0.0865,
      "step": 850
    },
    {
      "epoch": 2.6543209876543212,
      "grad_norm": 0.7442084812404209,
      "learning_rate": 3.997415973384311e-07,
      "loss": 0.079,
      "step": 860
    },
    {
      "epoch": 2.685185185185185,
      "grad_norm": 1.0024538750298015,
      "learning_rate": 3.3231259326184983e-07,
      "loss": 0.0988,
      "step": 870
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 0.8295790721782684,
      "learning_rate": 2.7091379149682683e-07,
      "loss": 0.0809,
      "step": 880
    },
    {
      "epoch": 2.746913580246914,
      "grad_norm": 1.0737158797857456,
      "learning_rate": 2.156245133783308e-07,
      "loss": 0.0787,
      "step": 890
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.9634211271913754,
      "learning_rate": 1.6651618732554774e-07,
      "loss": 0.0692,
      "step": 900
    },
    {
      "epoch": 2.808641975308642,
      "grad_norm": 1.0387449050019724,
      "learning_rate": 1.2365225656324308e-07,
      "loss": 0.0831,
      "step": 910
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 1.284046717570844,
      "learning_rate": 8.708809715922973e-08,
      "loss": 0.0868,
      "step": 920
    },
    {
      "epoch": 2.8703703703703702,
      "grad_norm": 1.3674065078147544,
      "learning_rate": 5.687094648382518e-08,
      "loss": 0.1005,
      "step": 930
    },
    {
      "epoch": 2.9012345679012346,
      "grad_norm": 1.1040914867606508,
      "learning_rate": 3.303984218372136e-08,
      "loss": 0.1167,
      "step": 940
    },
    {
      "epoch": 2.932098765432099,
      "grad_norm": 1.093365577556806,
      "learning_rate": 1.562557174910606e-08,
      "loss": 0.0875,
      "step": 950
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 1.034221852693663,
      "learning_rate": 4.650632739194305e-09,
      "loss": 0.0802,
      "step": 960
    },
    {
      "epoch": 2.993827160493827,
      "grad_norm": 1.1039194966989203,
      "learning_rate": 1.2920371754931994e-10,
      "loss": 0.0794,
      "step": 970
    },
    {
      "epoch": 3.0,
      "step": 972,
      "total_flos": 20295904002048.0,
      "train_loss": 0.19039062806117682,
      "train_runtime": 4309.0281,
      "train_samples_per_second": 3.607,
      "train_steps_per_second": 0.226
    }
  ],
  "logging_steps": 10,
  "max_steps": 972,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 20295904002048.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}