{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 1382,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.7341040462427746e-06,
      "loss": 6.193,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.468208092485549e-06,
      "loss": 5.641,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.202312138728324e-06,
      "loss": 5.1531,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.936416184971098e-06,
      "loss": 4.9047,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.670520231213873e-06,
      "loss": 4.6805,
      "step": 50
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.0404624277456647e-05,
      "loss": 4.0871,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.2138728323699422e-05,
      "loss": 3.7475,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.3872832369942197e-05,
      "loss": 3.3551,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.560693641618497e-05,
      "loss": 2.201,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.7341040462427746e-05,
      "loss": 1.7477,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9075144508670522e-05,
      "loss": 1.8617,
      "step": 110
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.0809248554913295e-05,
      "loss": 1.4377,
      "step": 120
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.2543352601156068e-05,
      "loss": 1.3061,
      "step": 130
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.4277456647398844e-05,
      "loss": 1.0828,
      "step": 140
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.601156069364162e-05,
      "loss": 1.4315,
      "step": 150
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.7745664739884393e-05,
      "loss": 1.5473,
      "step": 160
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.9479768786127166e-05,
      "loss": 1.0229,
      "step": 170
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.121387283236994e-05,
      "loss": 1.1775,
      "step": 180
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.294797687861272e-05,
      "loss": 1.1478,
      "step": 190
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.468208092485549e-05,
      "loss": 1.3083,
      "step": 200
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.6416184971098265e-05,
      "loss": 1.087,
      "step": 210
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.8150289017341044e-05,
      "loss": 1.6076,
      "step": 220
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.988439306358381e-05,
      "loss": 1.2098,
      "step": 230
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.161849710982659e-05,
      "loss": 1.12,
      "step": 240
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.335260115606937e-05,
      "loss": 1.0021,
      "step": 250
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.5086705202312136e-05,
      "loss": 1.0726,
      "step": 260
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.6820809248554915e-05,
      "loss": 0.9225,
      "step": 270
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.855491329479769e-05,
      "loss": 0.9474,
      "step": 280
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.028901734104046e-05,
      "loss": 1.2694,
      "step": 290
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.202312138728324e-05,
      "loss": 1.0835,
      "step": 300
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.3757225433526014e-05,
      "loss": 0.9174,
      "step": 310
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.5491329479768787e-05,
      "loss": 1.5421,
      "step": 320
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.7225433526011566e-05,
      "loss": 0.9618,
      "step": 330
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.895953757225433e-05,
      "loss": 0.5463,
      "step": 340
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.976833976833977e-05,
      "loss": 0.8392,
      "step": 350
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.9189189189189195e-05,
      "loss": 0.9226,
      "step": 360
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.861003861003862e-05,
      "loss": 1.3196,
      "step": 370
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.8030888030888026e-05,
      "loss": 1.1419,
      "step": 380
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.745173745173745e-05,
      "loss": 1.3268,
      "step": 390
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.687258687258687e-05,
      "loss": 0.9793,
      "step": 400
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.629343629343629e-05,
      "loss": 0.8298,
      "step": 410
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.5714285714285715e-05,
      "loss": 1.0074,
      "step": 420
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.513513513513514e-05,
      "loss": 0.8881,
      "step": 430
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.455598455598455e-05,
      "loss": 1.2019,
      "step": 440
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.3976833976833975e-05,
      "loss": 0.9811,
      "step": 450
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.33976833976834e-05,
      "loss": 0.8954,
      "step": 460
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.281853281853282e-05,
      "loss": 0.8566,
      "step": 470
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.223938223938224e-05,
      "loss": 0.8032,
      "step": 480
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.166023166023166e-05,
      "loss": 1.1888,
      "step": 490
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.108108108108108e-05,
      "loss": 1.2299,
      "step": 500
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.05019305019305e-05,
      "loss": 1.1262,
      "step": 510
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.9922779922779924e-05,
      "loss": 0.7842,
      "step": 520
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.9343629343629346e-05,
      "loss": 0.5281,
      "step": 530
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.876447876447877e-05,
      "loss": 0.7704,
      "step": 540
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.8185328185328184e-05,
      "loss": 1.0325,
      "step": 550
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.7606177606177606e-05,
      "loss": 0.9719,
      "step": 560
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.702702702702703e-05,
      "loss": 0.5723,
      "step": 570
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.644787644787645e-05,
      "loss": 0.7936,
      "step": 580
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.586872586872587e-05,
      "loss": 0.7755,
      "step": 590
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.5289575289575295e-05,
      "loss": 0.8309,
      "step": 600
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.471042471042471e-05,
      "loss": 1.1389,
      "step": 610
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.413127413127413e-05,
      "loss": 0.8725,
      "step": 620
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3552123552123555e-05,
      "loss": 0.7626,
      "step": 630
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.297297297297298e-05,
      "loss": 0.9825,
      "step": 640
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.23938223938224e-05,
      "loss": 0.3986,
      "step": 650
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.181467181467182e-05,
      "loss": 0.8921,
      "step": 660
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.123552123552124e-05,
      "loss": 0.9631,
      "step": 670
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.065637065637066e-05,
      "loss": 0.782,
      "step": 680
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.0077220077220075e-05,
      "loss": 0.8098,
      "step": 690
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.94980694980695e-05,
      "loss": 0.4539,
      "step": 700
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.891891891891892e-05,
      "loss": 0.6934,
      "step": 710
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.833976833976834e-05,
      "loss": 0.3759,
      "step": 720
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.776061776061776e-05,
      "loss": 0.6816,
      "step": 730
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.718146718146718e-05,
      "loss": 0.6174,
      "step": 740
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.66023166023166e-05,
      "loss": 0.5918,
      "step": 750
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.6023166023166024e-05,
      "loss": 0.8005,
      "step": 760
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.5444015444015446e-05,
      "loss": 0.5895,
      "step": 770
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.486486486486486e-05,
      "loss": 0.7898,
      "step": 780
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.4285714285714284e-05,
      "loss": 0.6744,
      "step": 790
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.3706563706563706e-05,
      "loss": 0.7501,
      "step": 800
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.312741312741313e-05,
      "loss": 0.8325,
      "step": 810
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.254826254826255e-05,
      "loss": 0.5695,
      "step": 820
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.196911196911197e-05,
      "loss": 0.8383,
      "step": 830
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.138996138996139e-05,
      "loss": 1.0377,
      "step": 840
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.081081081081081e-05,
      "loss": 0.7829,
      "step": 850
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.0231660231660233e-05,
      "loss": 0.8918,
      "step": 860
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.9652509652509655e-05,
      "loss": 0.8774,
      "step": 870
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.9073359073359074e-05,
      "loss": 1.1418,
      "step": 880
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8494208494208496e-05,
      "loss": 0.7277,
      "step": 890
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.7915057915057918e-05,
      "loss": 0.931,
      "step": 900
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.7335907335907337e-05,
      "loss": 0.2893,
      "step": 910
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.6756756756756756e-05,
      "loss": 0.7633,
      "step": 920
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.6177606177606178e-05,
      "loss": 0.6092,
      "step": 930
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.5598455598455597e-05,
      "loss": 0.5479,
      "step": 940
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.501930501930502e-05,
      "loss": 0.4822,
      "step": 950
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.444015444015444e-05,
      "loss": 0.822,
      "step": 960
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.386100386100386e-05,
      "loss": 0.8179,
      "step": 970
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.3281853281853282e-05,
      "loss": 0.6271,
      "step": 980
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.2702702702702705e-05,
      "loss": 0.7264,
      "step": 990
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.2123552123552123e-05,
      "loss": 0.6068,
      "step": 1000
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.1544401544401546e-05,
      "loss": 0.5542,
      "step": 1010
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.0965250965250968e-05,
      "loss": 0.895,
      "step": 1020
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.0386100386100387e-05,
      "loss": 0.7742,
      "step": 1030
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.980694980694981e-05,
      "loss": 0.8531,
      "step": 1040
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.922779922779923e-05,
      "loss": 0.5329,
      "step": 1050
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.864864864864865e-05,
      "loss": 0.8632,
      "step": 1060
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.806949806949807e-05,
      "loss": 0.5655,
      "step": 1070
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.7490347490347488e-05,
      "loss": 0.3663,
      "step": 1080
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.691119691119691e-05,
      "loss": 0.5332,
      "step": 1090
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.6332046332046332e-05,
      "loss": 0.4962,
      "step": 1100
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.575289575289575e-05,
      "loss": 0.725,
      "step": 1110
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5173745173745173e-05,
      "loss": 0.6943,
      "step": 1120
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.4594594594594596e-05,
      "loss": 1.003,
      "step": 1130
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.4015444015444016e-05,
      "loss": 0.7074,
      "step": 1140
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.3436293436293437e-05,
      "loss": 0.6233,
      "step": 1150
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.7505,
      "step": 1160
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.227799227799228e-05,
      "loss": 0.8814,
      "step": 1170
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.1698841698841698e-05,
      "loss": 0.6993,
      "step": 1180
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.1119691119691119e-05,
      "loss": 0.8268,
      "step": 1190
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.0540540540540541e-05,
      "loss": 0.7882,
      "step": 1200
    },
    {
      "epoch": 1.75,
      "learning_rate": 9.961389961389962e-06,
      "loss": 0.833,
      "step": 1210
    },
    {
      "epoch": 1.77,
      "learning_rate": 9.382239382239382e-06,
      "loss": 0.9814,
      "step": 1220
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.803088803088804e-06,
      "loss": 0.2646,
      "step": 1230
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.223938223938225e-06,
      "loss": 0.6311,
      "step": 1240
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.644787644787645e-06,
      "loss": 0.6489,
      "step": 1250
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.065637065637066e-06,
      "loss": 0.5292,
      "step": 1260
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.6609,
      "step": 1270
    },
    {
      "epoch": 1.85,
      "learning_rate": 5.907335907335907e-06,
      "loss": 0.6312,
      "step": 1280
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.3281853281853285e-06,
      "loss": 0.5062,
      "step": 1290
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.749034749034749e-06,
      "loss": 0.6065,
      "step": 1300
    },
    {
      "epoch": 1.9,
      "learning_rate": 4.1698841698841696e-06,
      "loss": 0.7586,
      "step": 1310
    },
    {
      "epoch": 1.91,
      "learning_rate": 3.5907335907335905e-06,
      "loss": 0.5006,
      "step": 1320
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.0115830115830115e-06,
      "loss": 0.7565,
      "step": 1330
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.4324324324324325e-06,
      "loss": 0.5601,
      "step": 1340
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.8532818532818534e-06,
      "loss": 0.5827,
      "step": 1350
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.2741312741312742e-06,
      "loss": 0.5409,
      "step": 1360
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.949806949806949e-07,
      "loss": 0.6359,
      "step": 1370
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.1583011583011584e-07,
      "loss": 0.6002,
      "step": 1380
    },
    {
      "epoch": 2.0,
      "step": 1382,
      "total_flos": 5.175834887457866e+18,
      "train_loss": 1.0848320548337724,
      "train_runtime": 1094.3482,
      "train_samples_per_second": 161.831,
      "train_steps_per_second": 1.263
    }
  ],
  "max_steps": 1382,
  "num_train_epochs": 2,
  "total_flos": 5.175834887457866e+18,
  "trial_name": null,
  "trial_params": null
}