{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6747069241798094,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.7302,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6767,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6744,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6699,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.6799,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.6763,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.674,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.6733,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.668,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.6679,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.6722,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.6707,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.6737,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.6697,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.6663,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.6793,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.6706,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.6718,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.6725,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.6749,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.6748,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.6719,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.6722,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.6671,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.6688,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.6701,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.6828,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.6716,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.6725,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.6706,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.6669,
      "step": 310
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.667,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.6725,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.6635,
      "step": 340
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.6661,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.6624,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.6657,
      "step": 370
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.664,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.6605,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.6635,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 0.6664,
      "step": 410
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 0.6696,
      "step": 420
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.658,
      "step": 430
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.6649,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.6611,
      "step": 450
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.6575,
      "step": 460
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.6703,
      "step": 470
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.665,
      "step": 480
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.6617,
      "step": 490
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.6623,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.6557,
      "step": 510
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.6558,
      "step": 520
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.663,
      "step": 530
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.6627,
      "step": 540
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.6528,
      "step": 550
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.6586,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.659,
      "step": 570
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.6583,
      "step": 580
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.6594,
      "step": 590
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.6454,
      "step": 600
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.6572,
      "step": 610
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.6546,
      "step": 620
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.656,
      "step": 630
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.6544,
      "step": 640
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.6574,
      "step": 650
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.6528,
      "step": 660
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.6574,
      "step": 670
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.6566,
      "step": 680
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.6512,
      "step": 690
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.6517,
      "step": 700
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.6461,
      "step": 710
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.6562,
      "step": 720
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.6616,
      "step": 730
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.6606,
      "step": 740
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.6463,
      "step": 750
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.6494,
      "step": 760
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.6549,
      "step": 770
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.644,
      "step": 780
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.6535,
      "step": 790
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.6489,
      "step": 800
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.6477,
      "step": 810
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.6389,
      "step": 820
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.6459,
      "step": 830
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.6444,
      "step": 840
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.648,
      "step": 850
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.6353,
      "step": 860
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.6719,
      "step": 870
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.6566,
      "step": 880
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.64,
      "step": 890
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.6476,
      "step": 900
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.6469,
      "step": 910
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.6385,
      "step": 920
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.649,
      "step": 930
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.6551,
      "step": 940
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.6371,
      "step": 950
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.6512,
      "step": 960
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.6486,
      "step": 970
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.6461,
      "step": 980
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.6617,
      "step": 990
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.654,
      "step": 1000
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.6395,
      "step": 1010
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.6582,
      "step": 1020
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 0.6447,
      "step": 1030
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 0.6378,
      "step": 1040
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 0.6377,
      "step": 1050
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 0.633,
      "step": 1060
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 0.639,
      "step": 1070
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 0.6396,
      "step": 1080
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 0.6491,
      "step": 1090
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 0.6396,
      "step": 1100
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 0.6542,
      "step": 1110
    },
    {
      "epoch": 0.38,
      "learning_rate": 5e-05,
      "loss": 0.6399,
      "step": 1120
    },
    {
      "epoch": 0.38,
      "learning_rate": 5e-05,
      "loss": 0.648,
      "step": 1130
    },
    {
      "epoch": 0.38,
      "learning_rate": 5e-05,
      "loss": 0.6614,
      "step": 1140
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 0.6453,
      "step": 1150
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 0.6441,
      "step": 1160
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 0.6381,
      "step": 1170
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 0.6449,
      "step": 1180
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 0.6443,
      "step": 1190
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 0.6411,
      "step": 1200
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 0.6371,
      "step": 1210
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 0.6329,
      "step": 1220
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 0.642,
      "step": 1230
    },
    {
      "epoch": 0.42,
      "learning_rate": 5e-05,
      "loss": 0.6364,
      "step": 1240
    },
    {
      "epoch": 0.42,
      "learning_rate": 5e-05,
      "loss": 0.6349,
      "step": 1250
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 0.6341,
      "step": 1260
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 0.65,
      "step": 1270
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 0.645,
      "step": 1280
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 0.6401,
      "step": 1290
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 0.6329,
      "step": 1300
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 0.6373,
      "step": 1310
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 0.6379,
      "step": 1320
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 0.6383,
      "step": 1330
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 0.6452,
      "step": 1340
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 0.6312,
      "step": 1350
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 0.6334,
      "step": 1360
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 0.6395,
      "step": 1370
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 0.6425,
      "step": 1380
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 0.6422,
      "step": 1390
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 0.6393,
      "step": 1400
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 0.6357,
      "step": 1410
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 0.6274,
      "step": 1420
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 0.6421,
      "step": 1430
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 0.6319,
      "step": 1440
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 0.6441,
      "step": 1450
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 0.6327,
      "step": 1460
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 0.632,
      "step": 1470
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 0.6351,
      "step": 1480
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 0.6187,
      "step": 1490
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 0.6307,
      "step": 1500
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 0.6434,
      "step": 1510
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 0.6367,
      "step": 1520
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 0.6391,
      "step": 1530
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 0.6417,
      "step": 1540
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 0.6305,
      "step": 1550
    },
    {
      "epoch": 0.53,
      "learning_rate": 5e-05,
      "loss": 0.6391,
      "step": 1560
    },
    {
      "epoch": 0.53,
      "learning_rate": 5e-05,
      "loss": 0.6404,
      "step": 1570
    },
    {
      "epoch": 0.53,
      "learning_rate": 5e-05,
      "loss": 0.635,
      "step": 1580
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 0.6339,
      "step": 1590
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 0.6352,
      "step": 1600
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 0.6346,
      "step": 1610
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 0.6261,
      "step": 1620
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 0.6372,
      "step": 1630
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 0.632,
      "step": 1640
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-05,
      "loss": 0.6318,
      "step": 1650
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-05,
      "loss": 0.6439,
      "step": 1660
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-05,
      "loss": 0.646,
      "step": 1670
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 0.6389,
      "step": 1680
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 0.6267,
      "step": 1690
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 0.6339,
      "step": 1700
    },
    {
      "epoch": 0.58,
      "learning_rate": 5e-05,
      "loss": 0.6305,
      "step": 1710
    },
    {
      "epoch": 0.58,
      "learning_rate": 5e-05,
      "loss": 0.6241,
      "step": 1720
    },
    {
      "epoch": 0.58,
      "learning_rate": 5e-05,
      "loss": 0.6325,
      "step": 1730
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 0.6367,
      "step": 1740
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 0.6333,
      "step": 1750
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 0.6284,
      "step": 1760
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-05,
      "loss": 0.627,
      "step": 1770
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-05,
      "loss": 0.6327,
      "step": 1780
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-05,
      "loss": 0.6326,
      "step": 1790
    },
    {
      "epoch": 0.61,
      "learning_rate": 5e-05,
      "loss": 0.6384,
      "step": 1800
    },
    {
      "epoch": 0.61,
      "learning_rate": 5e-05,
      "loss": 0.6752,
      "step": 1810
    },
    {
      "epoch": 0.61,
      "learning_rate": 5e-05,
      "loss": 0.6355,
      "step": 1820
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 0.6387,
      "step": 1830
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 0.6319,
      "step": 1840
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 0.63,
      "step": 1850
    },
    {
      "epoch": 0.63,
      "learning_rate": 5e-05,
      "loss": 0.6361,
      "step": 1860
    },
    {
      "epoch": 0.63,
      "learning_rate": 5e-05,
      "loss": 0.6288,
      "step": 1870
    },
    {
      "epoch": 0.63,
      "learning_rate": 5e-05,
      "loss": 0.6311,
      "step": 1880
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 0.6319,
      "step": 1890
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 0.6394,
      "step": 1900
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 0.6236,
      "step": 1910
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-05,
      "loss": 0.6308,
      "step": 1920
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-05,
      "loss": 0.6302,
      "step": 1930
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-05,
      "loss": 0.6333,
      "step": 1940
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 0.6223,
      "step": 1950
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 0.6379,
      "step": 1960
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 0.6307,
      "step": 1970
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 0.6268,
      "step": 1980
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 0.6312,
      "step": 1990
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 0.6396,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 8892,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}