{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003333333333333333,
      "grad_norm": 230.90853881835938,
      "learning_rate": 5.6e-07,
      "loss": 166.26241455078124,
      "original_ce_loss": 10.3909,
      "step": 10
    },
    {
      "epoch": 0.0006666666666666666,
      "grad_norm": 230.48590087890625,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 166.0879150390625,
      "original_ce_loss": 10.38,
      "step": 20
    },
    {
      "epoch": 0.001,
      "grad_norm": 227.33383178710938,
      "learning_rate": 2.16e-06,
      "loss": 165.6192138671875,
      "original_ce_loss": 10.3507,
      "step": 30
    },
    {
      "epoch": 0.0013333333333333333,
      "grad_norm": 247.27252197265625,
      "learning_rate": 2.96e-06,
      "loss": 164.7415771484375,
      "original_ce_loss": 10.2958,
      "step": 40
    },
    {
      "epoch": 0.0016666666666666668,
      "grad_norm": 294.6886901855469,
      "learning_rate": 3.7600000000000004e-06,
      "loss": 162.94903564453125,
      "original_ce_loss": 10.1838,
      "step": 50
    },
    {
      "epoch": 0.002,
      "grad_norm": 333.21942138671875,
      "learning_rate": 4.48e-06,
      "loss": 159.0419677734375,
      "original_ce_loss": 9.9396,
      "step": 60
    },
    {
      "epoch": 0.0023333333333333335,
      "grad_norm": 117.77169036865234,
      "learning_rate": 5.28e-06,
      "loss": 148.51612548828126,
      "original_ce_loss": 9.2817,
      "step": 70
    },
    {
      "epoch": 0.0026666666666666666,
      "grad_norm": 47.33100128173828,
      "learning_rate": 6.08e-06,
      "loss": 139.47933349609374,
      "original_ce_loss": 8.7169,
      "step": 80
    },
    {
      "epoch": 0.003,
      "grad_norm": 46.20034408569336,
      "learning_rate": 6.88e-06,
      "loss": 133.7960693359375,
      "original_ce_loss": 8.3617,
      "step": 90
    },
    {
      "epoch": 0.0033333333333333335,
      "grad_norm": 45.889854431152344,
      "learning_rate": 7.440000000000001e-06,
      "loss": 128.855322265625,
      "original_ce_loss": 8.0529,
      "step": 100
    },
    {
      "epoch": 0.0036666666666666666,
      "grad_norm": 42.315040588378906,
      "learning_rate": 8.24e-06,
      "loss": 124.37742919921875,
      "original_ce_loss": 7.7731,
      "step": 110
    },
    {
      "epoch": 0.004,
      "grad_norm": 30.78986167907715,
      "learning_rate": 9.040000000000002e-06,
      "loss": 118.6448486328125,
      "original_ce_loss": 7.4148,
      "step": 120
    },
    {
      "epoch": 0.004333333333333333,
      "grad_norm": 25.084131240844727,
      "learning_rate": 9.84e-06,
      "loss": 113.5805419921875,
      "original_ce_loss": 7.0982,
      "step": 130
    },
    {
      "epoch": 0.004666666666666667,
      "grad_norm": 16.696340560913086,
      "learning_rate": 1.0640000000000001e-05,
      "loss": 109.56595458984376,
      "original_ce_loss": 6.8473,
      "step": 140
    },
    {
      "epoch": 0.005,
      "grad_norm": 15.930886268615723,
      "learning_rate": 1.144e-05,
      "loss": 106.9578125,
      "original_ce_loss": 6.6843,
      "step": 150
    },
    {
      "epoch": 0.005333333333333333,
      "grad_norm": 16.46701431274414,
      "learning_rate": 1.2240000000000001e-05,
      "loss": 104.34500732421876,
      "original_ce_loss": 6.521,
      "step": 160
    },
    {
      "epoch": 0.005666666666666667,
      "grad_norm": 15.883834838867188,
      "learning_rate": 1.3040000000000002e-05,
      "loss": 103.16146240234374,
      "original_ce_loss": 6.4471,
      "step": 170
    },
    {
      "epoch": 0.006,
      "grad_norm": 13.470544815063477,
      "learning_rate": 1.384e-05,
      "loss": 102.31043090820313,
      "original_ce_loss": 6.3939,
      "step": 180
    },
    {
      "epoch": 0.006333333333333333,
      "grad_norm": 10.655685424804688,
      "learning_rate": 1.464e-05,
      "loss": 101.584765625,
      "original_ce_loss": 6.3485,
      "step": 190
    },
    {
      "epoch": 0.006666666666666667,
      "grad_norm": 14.607922554016113,
      "learning_rate": 1.544e-05,
      "loss": 100.68308715820312,
      "original_ce_loss": 6.2922,
      "step": 200
    },
    {
      "epoch": 0.007,
      "grad_norm": 25.438148498535156,
      "learning_rate": 1.6240000000000004e-05,
      "loss": 100.5173583984375,
      "original_ce_loss": 6.2818,
      "step": 210
    },
    {
      "epoch": 0.007333333333333333,
      "grad_norm": 21.892425537109375,
      "learning_rate": 1.704e-05,
      "loss": 99.87816772460937,
      "original_ce_loss": 6.2419,
      "step": 220
    },
    {
      "epoch": 0.007666666666666666,
      "grad_norm": 14.658900260925293,
      "learning_rate": 1.7840000000000002e-05,
      "loss": 98.83479614257813,
      "original_ce_loss": 6.1766,
      "step": 230
    },
    {
      "epoch": 0.008,
      "grad_norm": 20.833744049072266,
      "learning_rate": 1.864e-05,
      "loss": 98.17310180664063,
      "original_ce_loss": 6.1353,
      "step": 240
    },
    {
      "epoch": 0.008333333333333333,
      "grad_norm": 30.270259857177734,
      "learning_rate": 1.944e-05,
      "loss": 96.62825317382813,
      "original_ce_loss": 6.0387,
      "step": 250
    },
    {
      "epoch": 0.008666666666666666,
      "grad_norm": 22.719432830810547,
      "learning_rate": 2.016e-05,
      "loss": 95.52803955078124,
      "original_ce_loss": 5.97,
      "step": 260
    },
    {
      "epoch": 0.009,
      "grad_norm": 18.795289993286133,
      "learning_rate": 2.0960000000000003e-05,
      "loss": 93.84133911132812,
      "original_ce_loss": 5.8646,
      "step": 270
    },
    {
      "epoch": 0.009333333333333334,
      "grad_norm": 20.057626724243164,
      "learning_rate": 2.1760000000000002e-05,
      "loss": 92.70704345703125,
      "original_ce_loss": 5.7937,
      "step": 280
    },
    {
      "epoch": 0.009666666666666667,
      "grad_norm": 14.02243709564209,
      "learning_rate": 2.256e-05,
      "loss": 91.17881469726562,
      "original_ce_loss": 5.6981,
      "step": 290
    },
    {
      "epoch": 0.01,
      "grad_norm": 18.947725296020508,
      "learning_rate": 2.336e-05,
      "loss": 89.94291381835937,
      "original_ce_loss": 5.6209,
      "step": 300
    },
    {
      "epoch": 0.010333333333333333,
      "grad_norm": 26.08535385131836,
      "learning_rate": 2.4160000000000002e-05,
      "loss": 88.84134521484376,
      "original_ce_loss": 5.5521,
      "step": 310
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 29.568086624145508,
      "learning_rate": 2.496e-05,
      "loss": 87.48712768554688,
      "original_ce_loss": 5.4674,
      "step": 320
    },
    {
      "epoch": 0.011,
      "grad_norm": 18.3470516204834,
      "learning_rate": 2.5760000000000004e-05,
      "loss": 86.43890991210938,
      "original_ce_loss": 5.4019,
      "step": 330
    },
    {
      "epoch": 0.011333333333333334,
      "grad_norm": 19.26087188720703,
      "learning_rate": 2.6480000000000004e-05,
      "loss": 85.92128295898438,
      "original_ce_loss": 5.3695,
      "step": 340
    },
    {
      "epoch": 0.011666666666666667,
      "grad_norm": 27.251527786254883,
      "learning_rate": 2.7280000000000003e-05,
      "loss": 84.48787841796874,
      "original_ce_loss": 5.28,
      "step": 350
    },
    {
      "epoch": 0.012,
      "grad_norm": 29.83866310119629,
      "learning_rate": 2.8080000000000002e-05,
      "loss": 83.74765014648438,
      "original_ce_loss": 5.2337,
      "step": 360
    },
    {
      "epoch": 0.012333333333333333,
      "grad_norm": 23.42278289794922,
      "learning_rate": 2.8800000000000002e-05,
      "loss": 83.72489013671876,
      "original_ce_loss": 5.2323,
      "step": 370
    },
    {
      "epoch": 0.012666666666666666,
      "grad_norm": 24.038286209106445,
      "learning_rate": 2.9360000000000003e-05,
      "loss": 92.80264282226562,
      "original_ce_loss": 5.7996,
      "step": 380
    },
    {
      "epoch": 0.013,
      "grad_norm": 26.263559341430664,
      "learning_rate": 3.0160000000000003e-05,
      "loss": 87.11851196289062,
      "original_ce_loss": 5.4444,
      "step": 390
    },
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 31.93290138244629,
      "learning_rate": 3.08e-05,
      "loss": 82.21952514648437,
      "original_ce_loss": 5.1382,
      "step": 400
    },
    {
      "epoch": 0.013666666666666667,
      "grad_norm": 24.344730377197266,
      "learning_rate": 3.16e-05,
      "loss": 80.71455078125,
      "original_ce_loss": 5.0441,
      "step": 410
    },
    {
      "epoch": 0.014,
      "grad_norm": 164893.9375,
      "learning_rate": 3.24e-05,
      "loss": 78.23656005859375,
      "original_ce_loss": 4.8893,
      "step": 420
    },
    {
      "epoch": 0.014333333333333333,
      "grad_norm": 28.34848976135254,
      "learning_rate": 3.32e-05,
      "loss": 75.88787231445312,
      "original_ce_loss": 4.7425,
      "step": 430
    },
    {
      "epoch": 0.014666666666666666,
      "grad_norm": 22.918657302856445,
      "learning_rate": 3.4e-05,
      "loss": 73.90650024414063,
      "original_ce_loss": 4.6186,
      "step": 440
    },
    {
      "epoch": 0.015,
      "grad_norm": 38.609947204589844,
      "learning_rate": 3.4800000000000006e-05,
      "loss": 72.005029296875,
      "original_ce_loss": 4.4998,
      "step": 450
    },
    {
      "epoch": 0.015333333333333332,
      "grad_norm": 33.122589111328125,
      "learning_rate": 3.5600000000000005e-05,
      "loss": 70.87250366210938,
      "original_ce_loss": 4.429,
      "step": 460
    },
    {
      "epoch": 0.015666666666666666,
      "grad_norm": 36.62314987182617,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 69.0450439453125,
      "original_ce_loss": 4.3148,
      "step": 470
    },
    {
      "epoch": 0.016,
      "grad_norm": 29.61248779296875,
      "learning_rate": 3.72e-05,
      "loss": 67.96724853515624,
      "original_ce_loss": 4.2474,
      "step": 480
    },
    {
      "epoch": 0.01633333333333333,
      "grad_norm": 43.793861389160156,
      "learning_rate": 3.8e-05,
      "loss": 66.93857421875,
      "original_ce_loss": 4.1831,
      "step": 490
    },
    {
      "epoch": 0.016666666666666666,
      "grad_norm": 38.667362213134766,
      "learning_rate": 3.88e-05,
      "loss": 65.86553955078125,
      "original_ce_loss": 4.1161,
      "step": 500
    },
    {
      "epoch": 0.017,
      "grad_norm": 33.40896224975586,
      "learning_rate": 3.96e-05,
      "loss": 64.6124267578125,
      "original_ce_loss": 4.0377,
      "step": 510
    },
    {
      "epoch": 0.017333333333333333,
      "grad_norm": 36.0204963684082,
      "learning_rate": 3.9999997164721584e-05,
      "loss": 63.63116455078125,
      "original_ce_loss": 3.9764,
      "step": 520
    },
    {
      "epoch": 0.017666666666666667,
      "grad_norm": 28.736785888671875,
      "learning_rate": 3.9999974482499076e-05,
      "loss": 62.352001953125,
      "original_ce_loss": 3.8965,
      "step": 530
    },
    {
      "epoch": 0.018,
      "grad_norm": 43.71065139770508,
      "learning_rate": 3.999992911807978e-05,
      "loss": 61.264703369140626,
      "original_ce_loss": 3.8285,
      "step": 540
    },
    {
      "epoch": 0.018333333333333333,
      "grad_norm": 31.114343643188477,
      "learning_rate": 3.999986107151515e-05,
      "loss": 60.20930786132813,
      "original_ce_loss": 3.7626,
      "step": 550
    },
    {
      "epoch": 0.018666666666666668,
      "grad_norm": 35.500030517578125,
      "learning_rate": 3.999977034288236e-05,
      "loss": 58.905145263671876,
      "original_ce_loss": 3.681,
      "step": 560
    },
    {
      "epoch": 0.019,
      "grad_norm": 45.580894470214844,
      "learning_rate": 3.99996569322843e-05,
      "loss": 58.148040771484375,
      "original_ce_loss": 3.6337,
      "step": 570
    },
    {
      "epoch": 0.019333333333333334,
      "grad_norm": 27.553281784057617,
      "learning_rate": 3.999952083984959e-05,
      "loss": 57.779388427734375,
      "original_ce_loss": 3.6107,
      "step": 580
    },
    {
      "epoch": 0.019666666666666666,
      "grad_norm": 37.40439224243164,
      "learning_rate": 3.9999362065732574e-05,
      "loss": 56.65672607421875,
      "original_ce_loss": 3.5405,
      "step": 590
    },
    {
      "epoch": 0.02,
      "grad_norm": 43.446800231933594,
      "learning_rate": 3.9999180610113326e-05,
      "loss": 56.07798461914062,
      "original_ce_loss": 3.5043,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 30000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.42118754533376e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}