{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 0.7272480130195618,
      "learning_rate": 8.421052631578948e-05,
      "loss": 1.9563,
      "step": 25
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 0.3988882899284363,
      "learning_rate": 0.00017192982456140353,
      "loss": 0.78,
      "step": 50
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 0.23908574879169464,
      "learning_rate": 0.00019995801573733038,
      "loss": 0.5912,
      "step": 75
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.22981883585453033,
      "learning_rate": 0.00019974382771078473,
      "loss": 0.5734,
      "step": 100
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 0.22677601873874664,
      "learning_rate": 0.00019934852677927834,
      "loss": 0.5326,
      "step": 125
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 0.23226918280124664,
      "learning_rate": 0.00019877283072256436,
      "loss": 0.4978,
      "step": 150
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 0.265936017036438,
      "learning_rate": 0.00019801778487836048,
      "loss": 0.5083,
      "step": 175
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.2562519609928131,
      "learning_rate": 0.00019708476024424477,
      "loss": 0.5017,
      "step": 200
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 0.24657155573368073,
      "learning_rate": 0.00019597545098822504,
      "loss": 0.5355,
      "step": 225
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.2717723548412323,
      "learning_rate": 0.00019469187137250148,
      "loss": 0.5057,
      "step": 250
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 0.14394891262054443,
      "learning_rate": 0.00019323635209600841,
      "loss": 0.5435,
      "step": 275
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.2538720369338989,
      "learning_rate": 0.00019161153606237651,
      "loss": 0.4619,
      "step": 300
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 0.2302940934896469,
      "learning_rate": 0.00018982037358099963,
      "loss": 0.5144,
      "step": 325
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 0.23402678966522217,
      "learning_rate": 0.00018786611700992044,
      "loss": 0.5385,
      "step": 350
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 0.2835828363895416,
      "learning_rate": 0.0001857523148502617,
      "loss": 0.5324,
      "step": 375
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.2346741110086441,
      "learning_rate": 0.00018348280530292713,
      "loss": 0.5538,
      "step": 400
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 0.20240184664726257,
      "learning_rate": 0.00018106170929927035,
      "loss": 0.4757,
      "step": 425
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 0.23748184740543365,
      "learning_rate": 0.0001784934230183882,
      "loss": 0.4722,
      "step": 450
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.24441654980182648,
      "learning_rate": 0.00017578260990462372,
      "loss": 0.4765,
      "step": 475
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.21534137427806854,
      "learning_rate": 0.00017293419219977486,
      "loss": 0.511,
      "step": 500
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 0.18411624431610107,
      "learning_rate": 0.0001699533420053832,
      "loss": 0.459,
      "step": 525
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 0.22512228786945343,
      "learning_rate": 0.0001668454718913325,
      "loss": 0.4602,
      "step": 550
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 0.3007086515426636,
      "learning_rate": 0.00016361622506780944,
      "loss": 0.4723,
      "step": 575
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.24483013153076172,
      "learning_rate": 0.0001602714651384722,
      "loss": 0.4825,
      "step": 600
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 0.19368383288383484,
      "learning_rate": 0.0001568172654534328,
      "loss": 0.5199,
      "step": 625
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 0.27732446789741516,
      "learning_rate": 0.0001532598980813858,
      "loss": 0.4766,
      "step": 650
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 0.2359321564435959,
      "learning_rate": 0.0001496058224209082,
      "loss": 0.4315,
      "step": 675
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.25275617837905884,
      "learning_rate": 0.00014586167347160846,
      "loss": 0.4361,
      "step": 700
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 0.1912153959274292,
      "learning_rate": 0.00014203424978642337,
      "loss": 0.4467,
      "step": 725
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.23994949460029602,
      "learning_rate": 0.00013813050112693778,
      "loss": 0.4927,
      "step": 750
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 0.23791591823101044,
      "learning_rate": 0.00013415751584414215,
      "loss": 0.4032,
      "step": 775
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.2177554816007614,
      "learning_rate": 0.00013012250800754284,
      "loss": 0.5174,
      "step": 800
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 0.2537310719490051,
      "learning_rate": 0.0001260328043059947,
      "loss": 0.5024,
      "step": 825
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 0.3210338056087494,
      "learning_rate": 0.00012189583074404174,
      "loss": 0.4572,
      "step": 850
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 0.1832045167684555,
      "learning_rate": 0.0001177190991579223,
      "loss": 0.4374,
      "step": 875
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.21890908479690552,
      "learning_rate": 0.00011351019357572274,
      "loss": 0.446,
      "step": 900
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.2524813115596771,
      "learning_rate": 0.00010927675644644666,
      "loss": 0.4316,
      "step": 925
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.2024998813867569,
      "learning_rate": 0.0001050264747630043,
      "loss": 0.4264,
      "step": 950
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.23862822353839874,
      "learning_rate": 0.00010076706610432009,
      "loss": 0.4809,
      "step": 975
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.21620877087116241,
      "learning_rate": 9.650626462190294e-05,
      "loss": 0.4528,
      "step": 1000
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 0.2496652454137802,
      "learning_rate": 9.2251806996324e-05,
      "loss": 0.5165,
      "step": 1025
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 0.18958808481693268,
      "learning_rate": 8.801141838910238e-05,
      "loss": 0.461,
      "step": 1050
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 0.2566398084163666,
      "learning_rate": 8.379279841550693e-05,
      "loss": 0.4917,
      "step": 1075
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.2727346122264862,
      "learning_rate": 7.960360716374442e-05,
      "loss": 0.4035,
      "step": 1100
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 0.2812783718109131,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.4062,
      "step": 1125
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 0.13381074368953705,
      "learning_rate": 7.134387018602659e-05,
      "loss": 0.4147,
      "step": 1150
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 0.24165485799312592,
      "learning_rate": 6.728832233004054e-05,
      "loss": 0.4694,
      "step": 1175
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.1850873976945877,
      "learning_rate": 6.329217170298507e-05,
      "loss": 0.5144,
      "step": 1200
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 0.3044758439064026,
      "learning_rate": 5.936267443754863e-05,
      "loss": 0.448,
      "step": 1225
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.25881174206733704,
      "learning_rate": 5.550696563854032e-05,
      "loss": 0.4331,
      "step": 1250
    },
    {
      "epoch": 0.6710526315789473,
      "grad_norm": 0.1471320539712906,
      "learning_rate": 5.173204642710514e-05,
      "loss": 0.4162,
      "step": 1275
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.23026077449321747,
      "learning_rate": 4.804477122822432e-05,
      "loss": 0.4321,
      "step": 1300
    },
    {
      "epoch": 0.6973684210526315,
      "grad_norm": 0.2941257655620575,
      "learning_rate": 4.4451835324583326e-05,
      "loss": 0.4041,
      "step": 1325
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 0.2662881016731262,
      "learning_rate": 4.0959762699407766e-05,
      "loss": 0.4282,
      "step": 1350
    },
    {
      "epoch": 0.7236842105263158,
      "grad_norm": 0.27813515067100525,
      "learning_rate": 3.7574894190341404e-05,
      "loss": 0.4424,
      "step": 1375
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.25936228036880493,
      "learning_rate": 3.430337597587622e-05,
      "loss": 0.4325,
      "step": 1400
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.2591690421104431,
      "learning_rate": 3.1151148415241035e-05,
      "loss": 0.4389,
      "step": 1425
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 0.2798675298690796,
      "learning_rate": 2.8123935262012447e-05,
      "loss": 0.4832,
      "step": 1450
    },
    {
      "epoch": 0.7763157894736842,
      "grad_norm": 0.28093063831329346,
      "learning_rate": 2.5227233271034322e-05,
      "loss": 0.4171,
      "step": 1475
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.292204350233078,
      "learning_rate": 2.2466302217517133e-05,
      "loss": 0.4802,
      "step": 1500
    },
    {
      "epoch": 0.8026315789473685,
      "grad_norm": 0.2873384654521942,
      "learning_rate": 1.984615534644032e-05,
      "loss": 0.4688,
      "step": 1525
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 0.23933933675289154,
      "learning_rate": 1.7371550269599323e-05,
      "loss": 0.4687,
      "step": 1550
    },
    {
      "epoch": 0.8289473684210527,
      "grad_norm": 0.27426981925964355,
      "learning_rate": 1.50469803268267e-05,
      "loss": 0.4475,
      "step": 1575
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.2896619439125061,
      "learning_rate": 1.2876666427072703e-05,
      "loss": 0.4643,
      "step": 1600
    },
    {
      "epoch": 0.8552631578947368,
      "grad_norm": 0.15856152772903442,
      "learning_rate": 1.0864549384160927e-05,
      "loss": 0.4614,
      "step": 1625
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 0.32572880387306213,
      "learning_rate": 9.014282761135084e-06,
      "loss": 0.3922,
      "step": 1650
    },
    {
      "epoch": 0.881578947368421,
      "grad_norm": 0.2075156420469284,
      "learning_rate": 7.329226236190201e-06,
      "loss": 0.4834,
      "step": 1675
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.2609516978263855,
      "learning_rate": 5.81243950223419e-06,
      "loss": 0.4424,
      "step": 1700
    },
    {
      "epoch": 0.9078947368421053,
      "grad_norm": 0.27902549505233765,
      "learning_rate": 4.4666767111569474e-06,
      "loss": 0.4107,
      "step": 1725
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.1807645708322525,
      "learning_rate": 3.294381472894781e-06,
      "loss": 0.4095,
      "step": 1750
    },
    {
      "epoch": 0.9342105263157895,
      "grad_norm": 0.27969783544540405,
      "learning_rate": 2.2976824183709835e-06,
      "loss": 0.4665,
      "step": 1775
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.27561429142951965,
      "learning_rate": 1.4783893343691458e-06,
      "loss": 0.4077,
      "step": 1800
    },
    {
      "epoch": 0.9605263157894737,
      "grad_norm": 0.2988797426223755,
      "learning_rate": 8.379898773574924e-07,
      "loss": 0.4332,
      "step": 1825
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 0.2036939263343811,
      "learning_rate": 3.7764687223110773e-07,
      "loss": 0.401,
      "step": 1850
    },
    {
      "epoch": 0.9868421052631579,
      "grad_norm": 0.21864855289459229,
      "learning_rate": 9.8196200877132e-08,
      "loss": 0.4638,
      "step": 1875
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2675096392631531,
      "learning_rate": 1.452843966354145e-10,
      "loss": 0.465,
      "step": 1900
    }
  ],
  "logging_steps": 25,
  "max_steps": 1900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7343723267668173e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}