{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 0.002,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 0.002,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 3e-05,
      "loss": 0.002,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 4e-05,
      "loss": 0.0023,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.0021,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 6e-05,
      "loss": 0.0022,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 7e-05,
      "loss": 0.0037,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 8e-05,
      "loss": 0.0054,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 9e-05,
      "loss": 0.0153,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 0.0338,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.97584541062802e-05,
      "loss": 0.0546,
      "step": 110
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.951690821256039e-05,
      "loss": 0.0706,
      "step": 120
    },
    {
      "epoch": 0.31,
      "learning_rate": 9.927536231884058e-05,
      "loss": 0.0603,
      "step": 130
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.903381642512077e-05,
      "loss": 0.0698,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.879227053140096e-05,
      "loss": 0.0808,
      "step": 150
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.855072463768117e-05,
      "loss": 0.0792,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.830917874396136e-05,
      "loss": 0.0656,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.806763285024155e-05,
      "loss": 0.0673,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.782608695652174e-05,
      "loss": 0.0686,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 9.758454106280194e-05,
      "loss": 0.0717,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.734299516908213e-05,
      "loss": 0.066,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.710144927536232e-05,
      "loss": 0.08,
      "step": 220
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.685990338164251e-05,
      "loss": 0.084,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.66183574879227e-05,
      "loss": 0.0703,
      "step": 240
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.63768115942029e-05,
      "loss": 0.0589,
      "step": 250
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.61352657004831e-05,
      "loss": 0.0708,
      "step": 260
    },
    {
      "epoch": 0.64,
      "learning_rate": 9.589371980676329e-05,
      "loss": 0.0661,
      "step": 270
    },
    {
      "epoch": 0.66,
      "learning_rate": 9.565217391304348e-05,
      "loss": 0.0649,
      "step": 280
    },
    {
      "epoch": 0.68,
      "learning_rate": 9.541062801932368e-05,
      "loss": 0.063,
      "step": 290
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.516908212560387e-05,
      "loss": 0.0628,
      "step": 300
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.492753623188406e-05,
      "loss": 0.0699,
      "step": 310
    },
    {
      "epoch": 0.75,
      "learning_rate": 9.468599033816425e-05,
      "loss": 0.0716,
      "step": 320
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.444444444444444e-05,
      "loss": 0.0623,
      "step": 330
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.420289855072463e-05,
      "loss": 0.0661,
      "step": 340
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.396135265700483e-05,
      "loss": 0.0603,
      "step": 350
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.371980676328503e-05,
      "loss": 0.0591,
      "step": 360
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.347826086956522e-05,
      "loss": 0.054,
      "step": 370
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.323671497584541e-05,
      "loss": 0.0582,
      "step": 380
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.29951690821256e-05,
      "loss": 0.0617,
      "step": 390
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.27536231884058e-05,
      "loss": 0.0615,
      "step": 400
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.251207729468599e-05,
      "loss": 0.0648,
      "step": 410
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.227053140096618e-05,
      "loss": 0.0607,
      "step": 420
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.95200514793396,
      "eval_runtime": 26.5048,
      "eval_samples_per_second": 28.41,
      "eval_steps_per_second": 1.811,
      "step": 424
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.202898550724637e-05,
      "loss": 0.0516,
      "step": 430
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.178743961352657e-05,
      "loss": 0.0446,
      "step": 440
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.154589371980676e-05,
      "loss": 0.0452,
      "step": 450
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.130434782608696e-05,
      "loss": 0.0456,
      "step": 460
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.106280193236715e-05,
      "loss": 0.0483,
      "step": 470
    },
    {
      "epoch": 1.13,
      "learning_rate": 9.082125603864735e-05,
      "loss": 0.0575,
      "step": 480
    },
    {
      "epoch": 1.16,
      "learning_rate": 9.057971014492754e-05,
      "loss": 0.0485,
      "step": 490
    },
    {
      "epoch": 1.18,
      "learning_rate": 9.033816425120773e-05,
      "loss": 0.0471,
      "step": 500
    },
    {
      "epoch": 1.2,
      "learning_rate": 9.009661835748792e-05,
      "loss": 0.0517,
      "step": 510
    },
    {
      "epoch": 1.23,
      "learning_rate": 8.985507246376813e-05,
      "loss": 0.0482,
      "step": 520
    },
    {
      "epoch": 1.25,
      "learning_rate": 8.961352657004832e-05,
      "loss": 0.0449,
      "step": 530
    },
    {
      "epoch": 1.27,
      "learning_rate": 8.937198067632851e-05,
      "loss": 0.0598,
      "step": 540
    },
    {
      "epoch": 1.3,
      "learning_rate": 8.91304347826087e-05,
      "loss": 0.0539,
      "step": 550
    },
    {
      "epoch": 1.32,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.0481,
      "step": 560
    },
    {
      "epoch": 1.34,
      "learning_rate": 8.864734299516908e-05,
      "loss": 0.0553,
      "step": 570
    },
    {
      "epoch": 1.37,
      "learning_rate": 8.840579710144929e-05,
      "loss": 0.0474,
      "step": 580
    },
    {
      "epoch": 1.39,
      "learning_rate": 8.816425120772948e-05,
      "loss": 0.0536,
      "step": 590
    },
    {
      "epoch": 1.42,
      "learning_rate": 8.792270531400967e-05,
      "loss": 0.0552,
      "step": 600
    },
    {
      "epoch": 1.44,
      "learning_rate": 8.768115942028987e-05,
      "loss": 0.0494,
      "step": 610
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.743961352657006e-05,
      "loss": 0.0605,
      "step": 620
    },
    {
      "epoch": 1.49,
      "learning_rate": 8.719806763285025e-05,
      "loss": 0.0571,
      "step": 630
    },
    {
      "epoch": 1.51,
      "learning_rate": 8.695652173913044e-05,
      "loss": 0.0468,
      "step": 640
    },
    {
      "epoch": 1.53,
      "learning_rate": 8.671497584541063e-05,
      "loss": 0.058,
      "step": 650
    },
    {
      "epoch": 1.56,
      "learning_rate": 8.647342995169082e-05,
      "loss": 0.0523,
      "step": 660
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.623188405797103e-05,
      "loss": 0.0391,
      "step": 670
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.599033816425122e-05,
      "loss": 0.0488,
      "step": 680
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.574879227053141e-05,
      "loss": 0.056,
      "step": 690
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.55072463768116e-05,
      "loss": 0.0599,
      "step": 700
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.52657004830918e-05,
      "loss": 0.0536,
      "step": 710
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.502415458937199e-05,
      "loss": 0.0534,
      "step": 720
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.478260869565218e-05,
      "loss": 0.0484,
      "step": 730
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.454106280193237e-05,
      "loss": 0.0476,
      "step": 740
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.429951690821256e-05,
      "loss": 0.0426,
      "step": 750
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.405797101449276e-05,
      "loss": 0.0486,
      "step": 760
    },
    {
      "epoch": 1.82,
      "learning_rate": 8.381642512077295e-05,
      "loss": 0.0598,
      "step": 770
    },
    {
      "epoch": 1.84,
      "learning_rate": 8.357487922705315e-05,
      "loss": 0.0567,
      "step": 780
    },
    {
      "epoch": 1.86,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.0535,
      "step": 790
    },
    {
      "epoch": 1.89,
      "learning_rate": 8.309178743961354e-05,
      "loss": 0.0453,
      "step": 800
    },
    {
      "epoch": 1.91,
      "learning_rate": 8.285024154589373e-05,
      "loss": 0.0437,
      "step": 810
    },
    {
      "epoch": 1.93,
      "learning_rate": 8.260869565217392e-05,
      "loss": 0.0549,
      "step": 820
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.236714975845411e-05,
      "loss": 0.0522,
      "step": 830
    },
    {
      "epoch": 1.98,
      "learning_rate": 8.21256038647343e-05,
      "loss": 0.049,
      "step": 840
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9635112285614014,
      "eval_runtime": 26.4849,
      "eval_samples_per_second": 28.431,
      "eval_steps_per_second": 1.812,
      "step": 848
    },
    {
      "epoch": 2.0,
      "learning_rate": 8.18840579710145e-05,
      "loss": 0.0426,
      "step": 850
    },
    {
      "epoch": 2.03,
      "learning_rate": 8.164251207729469e-05,
      "loss": 0.0259,
      "step": 860
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.140096618357488e-05,
      "loss": 0.0255,
      "step": 870
    },
    {
      "epoch": 2.08,
      "learning_rate": 8.115942028985508e-05,
      "loss": 0.0209,
      "step": 880
    },
    {
      "epoch": 2.1,
      "learning_rate": 8.091787439613528e-05,
      "loss": 0.0244,
      "step": 890
    },
    {
      "epoch": 2.12,
      "learning_rate": 8.067632850241547e-05,
      "loss": 0.0319,
      "step": 900
    },
    {
      "epoch": 2.15,
      "learning_rate": 8.043478260869566e-05,
      "loss": 0.0257,
      "step": 910
    },
    {
      "epoch": 2.17,
      "learning_rate": 8.019323671497585e-05,
      "loss": 0.0286,
      "step": 920
    },
    {
      "epoch": 2.19,
      "learning_rate": 7.995169082125604e-05,
      "loss": 0.0265,
      "step": 930
    },
    {
      "epoch": 2.22,
      "learning_rate": 7.971014492753623e-05,
      "loss": 0.0229,
      "step": 940
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.946859903381643e-05,
      "loss": 0.0237,
      "step": 950
    },
    {
      "epoch": 2.26,
      "learning_rate": 7.922705314009662e-05,
      "loss": 0.0313,
      "step": 960
    },
    {
      "epoch": 2.29,
      "learning_rate": 7.898550724637681e-05,
      "loss": 0.035,
      "step": 970
    },
    {
      "epoch": 2.31,
      "learning_rate": 7.874396135265701e-05,
      "loss": 0.0324,
      "step": 980
    },
    {
      "epoch": 2.33,
      "learning_rate": 7.85024154589372e-05,
      "loss": 0.029,
      "step": 990
    },
    {
      "epoch": 2.36,
      "learning_rate": 7.82608695652174e-05,
      "loss": 0.0297,
      "step": 1000
    },
    {
      "epoch": 2.38,
      "learning_rate": 7.801932367149759e-05,
      "loss": 0.029,
      "step": 1010
    },
    {
      "epoch": 2.41,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.0289,
      "step": 1020
    },
    {
      "epoch": 2.43,
      "learning_rate": 7.753623188405797e-05,
      "loss": 0.0267,
      "step": 1030
    },
    {
      "epoch": 2.45,
      "learning_rate": 7.729468599033817e-05,
      "loss": 0.0373,
      "step": 1040
    },
    {
      "epoch": 2.48,
      "learning_rate": 7.705314009661836e-05,
      "loss": 0.0269,
      "step": 1050
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.681159420289855e-05,
      "loss": 0.0237,
      "step": 1060
    },
    {
      "epoch": 2.52,
      "learning_rate": 7.657004830917874e-05,
      "loss": 0.0222,
      "step": 1070
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.632850241545893e-05,
      "loss": 0.0378,
      "step": 1080
    },
    {
      "epoch": 2.57,
      "learning_rate": 7.608695652173914e-05,
      "loss": 0.0311,
      "step": 1090
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.584541062801933e-05,
      "loss": 0.0243,
      "step": 1100
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.560386473429952e-05,
      "loss": 0.0295,
      "step": 1110
    },
    {
      "epoch": 2.64,
      "learning_rate": 7.536231884057971e-05,
      "loss": 0.0293,
      "step": 1120
    },
    {
      "epoch": 2.67,
      "learning_rate": 7.51207729468599e-05,
      "loss": 0.029,
      "step": 1130
    },
    {
      "epoch": 2.69,
      "learning_rate": 7.48792270531401e-05,
      "loss": 0.0289,
      "step": 1140
    },
    {
      "epoch": 2.71,
      "learning_rate": 7.463768115942029e-05,
      "loss": 0.0394,
      "step": 1150
    },
    {
      "epoch": 2.74,
      "learning_rate": 7.439613526570048e-05,
      "loss": 0.0355,
      "step": 1160
    },
    {
      "epoch": 2.76,
      "learning_rate": 7.415458937198067e-05,
      "loss": 0.0273,
      "step": 1170
    },
    {
      "epoch": 2.78,
      "learning_rate": 7.391304347826086e-05,
      "loss": 0.0312,
      "step": 1180
    },
    {
      "epoch": 2.81,
      "learning_rate": 7.367149758454107e-05,
      "loss": 0.0284,
      "step": 1190
    },
    {
      "epoch": 2.83,
      "learning_rate": 7.342995169082126e-05,
      "loss": 0.0363,
      "step": 1200
    },
    {
      "epoch": 2.85,
      "learning_rate": 7.318840579710145e-05,
      "loss": 0.0307,
      "step": 1210
    },
    {
      "epoch": 2.88,
      "learning_rate": 7.294685990338164e-05,
      "loss": 0.0357,
      "step": 1220
    },
    {
      "epoch": 2.9,
      "learning_rate": 7.270531400966184e-05,
      "loss": 0.0332,
      "step": 1230
    },
    {
      "epoch": 2.92,
      "learning_rate": 7.246376811594203e-05,
      "loss": 0.0361,
      "step": 1240
    },
    {
      "epoch": 2.95,
      "learning_rate": 7.222222222222222e-05,
      "loss": 0.0318,
      "step": 1250
    },
    {
      "epoch": 2.97,
      "learning_rate": 7.198067632850241e-05,
      "loss": 0.0306,
      "step": 1260
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.17391304347826e-05,
      "loss": 0.0281,
      "step": 1270
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.9812633991241455,
      "eval_runtime": 27.1954,
      "eval_samples_per_second": 27.689,
      "eval_steps_per_second": 1.765,
      "step": 1272
    },
    {
      "epoch": 3.02,
      "learning_rate": 7.14975845410628e-05,
      "loss": 0.0175,
      "step": 1280
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.1256038647343e-05,
      "loss": 0.0208,
      "step": 1290
    },
    {
      "epoch": 3.07,
      "learning_rate": 7.101449275362319e-05,
      "loss": 0.0153,
      "step": 1300
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.077294685990338e-05,
      "loss": 0.0147,
      "step": 1310
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.053140096618357e-05,
      "loss": 0.0193,
      "step": 1320
    },
    {
      "epoch": 3.14,
      "learning_rate": 7.028985507246377e-05,
      "loss": 0.0173,
      "step": 1330
    },
    {
      "epoch": 3.16,
      "learning_rate": 7.004830917874396e-05,
      "loss": 0.0291,
      "step": 1340
    },
    {
      "epoch": 3.18,
      "learning_rate": 6.980676328502416e-05,
      "loss": 0.019,
      "step": 1350
    },
    {
      "epoch": 3.21,
      "learning_rate": 6.956521739130436e-05,
      "loss": 0.015,
      "step": 1360
    },
    {
      "epoch": 3.23,
      "learning_rate": 6.932367149758455e-05,
      "loss": 0.0208,
      "step": 1370
    },
    {
      "epoch": 3.25,
      "learning_rate": 6.908212560386474e-05,
      "loss": 0.0185,
      "step": 1380
    },
    {
      "epoch": 3.28,
      "learning_rate": 6.884057971014493e-05,
      "loss": 0.0162,
      "step": 1390
    },
    {
      "epoch": 3.3,
      "learning_rate": 6.859903381642512e-05,
      "loss": 0.0166,
      "step": 1400
    },
    {
      "epoch": 3.33,
      "learning_rate": 6.835748792270533e-05,
      "loss": 0.0178,
      "step": 1410
    },
    {
      "epoch": 3.35,
      "learning_rate": 6.811594202898552e-05,
      "loss": 0.0163,
      "step": 1420
    },
    {
      "epoch": 3.37,
      "learning_rate": 6.787439613526571e-05,
      "loss": 0.0227,
      "step": 1430
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.76328502415459e-05,
      "loss": 0.0144,
      "step": 1440
    },
    {
      "epoch": 3.42,
      "learning_rate": 6.73913043478261e-05,
      "loss": 0.0156,
      "step": 1450
    },
    {
      "epoch": 3.44,
      "learning_rate": 6.714975845410629e-05,
      "loss": 0.014,
      "step": 1460
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.690821256038648e-05,
      "loss": 0.0187,
      "step": 1470
    },
    {
      "epoch": 3.49,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0198,
      "step": 1480
    },
    {
      "epoch": 3.51,
      "learning_rate": 6.642512077294686e-05,
      "loss": 0.0127,
      "step": 1490
    },
    {
      "epoch": 3.54,
      "learning_rate": 6.618357487922707e-05,
      "loss": 0.0129,
      "step": 1500
    },
    {
      "epoch": 3.56,
      "learning_rate": 6.594202898550726e-05,
      "loss": 0.0174,
      "step": 1510
    },
    {
      "epoch": 3.58,
      "learning_rate": 6.570048309178745e-05,
      "loss": 0.0147,
      "step": 1520
    },
    {
      "epoch": 3.61,
      "learning_rate": 6.545893719806764e-05,
      "loss": 0.0188,
      "step": 1530
    },
    {
      "epoch": 3.63,
      "learning_rate": 6.521739130434783e-05,
      "loss": 0.0149,
      "step": 1540
    },
    {
      "epoch": 3.66,
      "learning_rate": 6.497584541062803e-05,
      "loss": 0.0255,
      "step": 1550
    },
    {
      "epoch": 3.68,
      "learning_rate": 6.473429951690822e-05,
      "loss": 0.0198,
      "step": 1560
    },
    {
      "epoch": 3.7,
      "learning_rate": 6.449275362318841e-05,
      "loss": 0.0219,
      "step": 1570
    },
    {
      "epoch": 3.73,
      "learning_rate": 6.42512077294686e-05,
      "loss": 0.0213,
      "step": 1580
    },
    {
      "epoch": 3.75,
      "learning_rate": 6.400966183574879e-05,
      "loss": 0.0214,
      "step": 1590
    },
    {
      "epoch": 3.77,
      "learning_rate": 6.376811594202898e-05,
      "loss": 0.0185,
      "step": 1600
    },
    {
      "epoch": 3.8,
      "learning_rate": 6.352657004830919e-05,
      "loss": 0.0191,
      "step": 1610
    },
    {
      "epoch": 3.82,
      "learning_rate": 6.328502415458938e-05,
      "loss": 0.0165,
      "step": 1620
    },
    {
      "epoch": 3.84,
      "learning_rate": 6.304347826086957e-05,
      "loss": 0.0205,
      "step": 1630
    },
    {
      "epoch": 3.87,
      "learning_rate": 6.280193236714976e-05,
      "loss": 0.017,
      "step": 1640
    },
    {
      "epoch": 3.89,
      "learning_rate": 6.256038647342996e-05,
      "loss": 0.0198,
      "step": 1650
    },
    {
      "epoch": 3.92,
      "learning_rate": 6.231884057971015e-05,
      "loss": 0.0171,
      "step": 1660
    },
    {
      "epoch": 3.94,
      "learning_rate": 6.207729468599034e-05,
      "loss": 0.0201,
      "step": 1670
    },
    {
      "epoch": 3.96,
      "learning_rate": 6.183574879227053e-05,
      "loss": 0.0253,
      "step": 1680
    },
    {
      "epoch": 3.99,
      "learning_rate": 6.159420289855072e-05,
      "loss": 0.0204,
      "step": 1690
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.0079989433288574,
      "eval_runtime": 26.4901,
      "eval_samples_per_second": 28.426,
      "eval_steps_per_second": 1.812,
      "step": 1696
    },
    {
      "epoch": 4.01,
      "learning_rate": 6.135265700483092e-05,
      "loss": 0.0136,
      "step": 1700
    },
    {
      "epoch": 4.03,
      "learning_rate": 6.111111111111112e-05,
      "loss": 0.0131,
      "step": 1710
    },
    {
      "epoch": 4.06,
      "learning_rate": 6.086956521739131e-05,
      "loss": 0.013,
      "step": 1720
    },
    {
      "epoch": 4.08,
      "learning_rate": 6.0628019323671504e-05,
      "loss": 0.009,
      "step": 1730
    },
    {
      "epoch": 4.1,
      "learning_rate": 6.0386473429951696e-05,
      "loss": 0.0075,
      "step": 1740
    },
    {
      "epoch": 4.13,
      "learning_rate": 6.014492753623189e-05,
      "loss": 0.0095,
      "step": 1750
    },
    {
      "epoch": 4.15,
      "learning_rate": 5.990338164251208e-05,
      "loss": 0.0078,
      "step": 1760
    },
    {
      "epoch": 4.17,
      "learning_rate": 5.966183574879227e-05,
      "loss": 0.0122,
      "step": 1770
    },
    {
      "epoch": 4.2,
      "learning_rate": 5.942028985507246e-05,
      "loss": 0.0089,
      "step": 1780
    },
    {
      "epoch": 4.22,
      "learning_rate": 5.9178743961352655e-05,
      "loss": 0.0085,
      "step": 1790
    },
    {
      "epoch": 4.25,
      "learning_rate": 5.8937198067632847e-05,
      "loss": 0.0103,
      "step": 1800
    },
    {
      "epoch": 4.27,
      "learning_rate": 5.869565217391305e-05,
      "loss": 0.0091,
      "step": 1810
    },
    {
      "epoch": 4.29,
      "learning_rate": 5.8454106280193244e-05,
      "loss": 0.0091,
      "step": 1820
    },
    {
      "epoch": 4.32,
      "learning_rate": 5.8212560386473435e-05,
      "loss": 0.0084,
      "step": 1830
    },
    {
      "epoch": 4.34,
      "learning_rate": 5.797101449275363e-05,
      "loss": 0.0095,
      "step": 1840
    },
    {
      "epoch": 4.36,
      "learning_rate": 5.772946859903382e-05,
      "loss": 0.0088,
      "step": 1850
    },
    {
      "epoch": 4.39,
      "learning_rate": 5.748792270531401e-05,
      "loss": 0.0096,
      "step": 1860
    },
    {
      "epoch": 4.41,
      "learning_rate": 5.72463768115942e-05,
      "loss": 0.0094,
      "step": 1870
    },
    {
      "epoch": 4.43,
      "learning_rate": 5.7004830917874394e-05,
      "loss": 0.0111,
      "step": 1880
    },
    {
      "epoch": 4.46,
      "learning_rate": 5.6763285024154586e-05,
      "loss": 0.015,
      "step": 1890
    },
    {
      "epoch": 4.48,
      "learning_rate": 5.652173913043478e-05,
      "loss": 0.0078,
      "step": 1900
    },
    {
      "epoch": 4.5,
      "learning_rate": 5.6280193236714976e-05,
      "loss": 0.0113,
      "step": 1910
    },
    {
      "epoch": 4.53,
      "learning_rate": 5.6038647342995175e-05,
      "loss": 0.0114,
      "step": 1920
    },
    {
      "epoch": 4.55,
      "learning_rate": 5.5797101449275366e-05,
      "loss": 0.0089,
      "step": 1930
    },
    {
      "epoch": 4.58,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.0137,
      "step": 1940
    },
    {
      "epoch": 4.6,
      "learning_rate": 5.531400966183575e-05,
      "loss": 0.0122,
      "step": 1950
    },
    {
      "epoch": 4.62,
      "learning_rate": 5.507246376811594e-05,
      "loss": 0.0075,
      "step": 1960
    },
    {
      "epoch": 4.65,
      "learning_rate": 5.483091787439614e-05,
      "loss": 0.011,
      "step": 1970
    },
    {
      "epoch": 4.67,
      "learning_rate": 5.458937198067633e-05,
      "loss": 0.0105,
      "step": 1980
    },
    {
      "epoch": 4.69,
      "learning_rate": 5.4347826086956524e-05,
      "loss": 0.0108,
      "step": 1990
    },
    {
      "epoch": 4.72,
      "learning_rate": 5.4106280193236716e-05,
      "loss": 0.0093,
      "step": 2000
    }
  ],
  "max_steps": 4240,
  "num_train_epochs": 10,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}