{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.94475138121547,
  "global_step": 1350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.9251,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.1925,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6688,
      "step": 30
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.778,
      "step": 40
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.6743,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.569,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.598,
      "step": 70
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.6713,
      "step": 80
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.571,
      "step": 90
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.503,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.7059,
      "step": 110
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5989,
      "step": 120
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.4895,
      "step": 130
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.623,
      "step": 140
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.637,
      "step": 150
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.5461,
      "step": 160
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.48,
      "step": 170
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.7108,
      "step": 180
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.5659,
      "step": 190
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.4692,
      "step": 200
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.674,
      "step": 210
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.5979,
      "step": 220
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 0.484,
      "step": 230
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 0.5799,
      "step": 240
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 0.6141,
      "step": 250
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 0.5177,
      "step": 260
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 0.4582,
      "step": 270
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.6667,
      "step": 280
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.56,
      "step": 290
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.4628,
      "step": 300
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0002,
      "loss": 0.5623,
      "step": 310
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002,
      "loss": 0.6027,
      "step": 320
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.4787,
      "step": 330
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.4718,
      "step": 340
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0002,
      "loss": 0.6168,
      "step": 350
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 0.5156,
      "step": 360
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0002,
      "loss": 0.4076,
      "step": 370
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0002,
      "loss": 0.6857,
      "step": 380
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0002,
      "loss": 0.5429,
      "step": 390
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0002,
      "loss": 0.43,
      "step": 400
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0002,
      "loss": 0.5163,
      "step": 410
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0002,
      "loss": 0.6072,
      "step": 420
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0002,
      "loss": 0.4804,
      "step": 430
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0002,
      "loss": 0.3655,
      "step": 440
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0002,
      "loss": 0.6351,
      "step": 450
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0002,
      "loss": 0.512,
      "step": 460
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0002,
      "loss": 0.3907,
      "step": 470
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0002,
      "loss": 0.5736,
      "step": 480
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0002,
      "loss": 0.5337,
      "step": 490
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0002,
      "loss": 0.4324,
      "step": 500
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0002,
      "loss": 0.4844,
      "step": 510
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0002,
      "loss": 0.5886,
      "step": 520
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0002,
      "loss": 0.4723,
      "step": 530
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0002,
      "loss": 0.3895,
      "step": 540
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0002,
      "loss": 0.58,
      "step": 550
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0002,
      "loss": 0.4998,
      "step": 560
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0002,
      "loss": 0.3901,
      "step": 570
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0002,
      "loss": 0.4494,
      "step": 580
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0002,
      "loss": 0.5282,
      "step": 590
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0002,
      "loss": 0.4162,
      "step": 600
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0002,
      "loss": 0.3818,
      "step": 610
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0002,
      "loss": 0.594,
      "step": 620
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0002,
      "loss": 0.4547,
      "step": 630
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0002,
      "loss": 0.3598,
      "step": 640
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0002,
      "loss": 0.5721,
      "step": 650
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0002,
      "loss": 0.4997,
      "step": 660
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0002,
      "loss": 0.3974,
      "step": 670
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.0002,
      "loss": 0.4133,
      "step": 680
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0002,
      "loss": 0.5438,
      "step": 690
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.0002,
      "loss": 0.408,
      "step": 700
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.0002,
      "loss": 0.3157,
      "step": 710
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.0002,
      "loss": 0.5219,
      "step": 720
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0002,
      "loss": 0.4365,
      "step": 730
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.0002,
      "loss": 0.3586,
      "step": 740
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0002,
      "loss": 0.462,
      "step": 750
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.0002,
      "loss": 0.4815,
      "step": 760
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.0002,
      "loss": 0.3818,
      "step": 770
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.0002,
      "loss": 0.3744,
      "step": 780
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.0002,
      "loss": 0.5412,
      "step": 790
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.0002,
      "loss": 0.4341,
      "step": 800
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.0002,
      "loss": 0.3258,
      "step": 810
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.0002,
      "loss": 0.4872,
      "step": 820
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.0002,
      "loss": 0.4313,
      "step": 830
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.0002,
      "loss": 0.3199,
      "step": 840
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.0002,
      "loss": 0.3386,
      "step": 850
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.0002,
      "loss": 0.4872,
      "step": 860
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.0002,
      "loss": 0.3744,
      "step": 870
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.0002,
      "loss": 0.277,
      "step": 880
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0002,
      "loss": 0.5125,
      "step": 890
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.0002,
      "loss": 0.4132,
      "step": 900
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.0002,
      "loss": 0.31,
      "step": 910
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.0002,
      "loss": 0.4628,
      "step": 920
    },
    {
      "epoch": 6.85,
      "learning_rate": 0.0002,
      "loss": 0.4471,
      "step": 930
    },
    {
      "epoch": 6.92,
      "learning_rate": 0.0002,
      "loss": 0.3348,
      "step": 940
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0002,
      "loss": 0.3292,
      "step": 950
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.0002,
      "loss": 0.4596,
      "step": 960
    },
    {
      "epoch": 7.15,
      "learning_rate": 0.0002,
      "loss": 0.3506,
      "step": 970
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.0002,
      "loss": 0.2606,
      "step": 980
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.0002,
      "loss": 0.4052,
      "step": 990
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.0002,
      "loss": 0.3891,
      "step": 1000
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.0002,
      "loss": 0.3116,
      "step": 1010
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.0002,
      "loss": 0.3483,
      "step": 1020
    },
    {
      "epoch": 7.59,
      "learning_rate": 0.0002,
      "loss": 0.4398,
      "step": 1030
    },
    {
      "epoch": 7.66,
      "learning_rate": 0.0002,
      "loss": 0.3157,
      "step": 1040
    },
    {
      "epoch": 7.73,
      "learning_rate": 0.0002,
      "loss": 0.268,
      "step": 1050
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.0002,
      "loss": 0.4692,
      "step": 1060
    },
    {
      "epoch": 7.88,
      "learning_rate": 0.0002,
      "loss": 0.3724,
      "step": 1070
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.0002,
      "loss": 0.2665,
      "step": 1080
    },
    {
      "epoch": 8.03,
      "learning_rate": 0.0002,
      "loss": 0.3718,
      "step": 1090
    },
    {
      "epoch": 8.1,
      "learning_rate": 0.0002,
      "loss": 0.372,
      "step": 1100
    },
    {
      "epoch": 8.18,
      "learning_rate": 0.0002,
      "loss": 0.2868,
      "step": 1110
    },
    {
      "epoch": 8.25,
      "learning_rate": 0.0002,
      "loss": 0.2351,
      "step": 1120
    },
    {
      "epoch": 8.32,
      "learning_rate": 0.0002,
      "loss": 0.4212,
      "step": 1130
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.0002,
      "loss": 0.3118,
      "step": 1140
    },
    {
      "epoch": 8.47,
      "learning_rate": 0.0002,
      "loss": 0.2195,
      "step": 1150
    },
    {
      "epoch": 8.55,
      "learning_rate": 0.0002,
      "loss": 0.3907,
      "step": 1160
    },
    {
      "epoch": 8.62,
      "learning_rate": 0.0002,
      "loss": 0.335,
      "step": 1170
    },
    {
      "epoch": 8.69,
      "learning_rate": 0.0002,
      "loss": 0.26,
      "step": 1180
    },
    {
      "epoch": 8.77,
      "learning_rate": 0.0002,
      "loss": 0.3481,
      "step": 1190
    },
    {
      "epoch": 8.84,
      "learning_rate": 0.0002,
      "loss": 0.3802,
      "step": 1200
    },
    {
      "epoch": 8.91,
      "learning_rate": 0.0002,
      "loss": 0.2834,
      "step": 1210
    },
    {
      "epoch": 8.99,
      "learning_rate": 0.0002,
      "loss": 0.2545,
      "step": 1220
    },
    {
      "epoch": 9.06,
      "learning_rate": 0.0002,
      "loss": 0.3557,
      "step": 1230
    },
    {
      "epoch": 9.13,
      "learning_rate": 0.0002,
      "loss": 0.2917,
      "step": 1240
    },
    {
      "epoch": 9.21,
      "learning_rate": 0.0002,
      "loss": 0.2154,
      "step": 1250
    },
    {
      "epoch": 9.28,
      "learning_rate": 0.0002,
      "loss": 0.2994,
      "step": 1260
    },
    {
      "epoch": 9.36,
      "learning_rate": 0.0002,
      "loss": 0.321,
      "step": 1270
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.0002,
      "loss": 0.2344,
      "step": 1280
    },
    {
      "epoch": 9.5,
      "learning_rate": 0.0002,
      "loss": 0.2356,
      "step": 1290
    },
    {
      "epoch": 9.58,
      "learning_rate": 0.0002,
      "loss": 0.3661,
      "step": 1300
    },
    {
      "epoch": 9.65,
      "learning_rate": 0.0002,
      "loss": 0.2786,
      "step": 1310
    },
    {
      "epoch": 9.72,
      "learning_rate": 0.0002,
      "loss": 0.1928,
      "step": 1320
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.0002,
      "loss": 0.3897,
      "step": 1330
    },
    {
      "epoch": 9.87,
      "learning_rate": 0.0002,
      "loss": 0.2978,
      "step": 1340
    },
    {
      "epoch": 9.94,
      "learning_rate": 0.0002,
      "loss": 0.2234,
      "step": 1350
    }
  ],
  "max_steps": 1350,
  "num_train_epochs": 10,
  "total_flos": 1.116092169148416e+17,
  "trial_name": null,
  "trial_params": null
}