{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 1.8985621929168701,
      "learning_rate": 9.910000000000001e-05,
      "loss": 0.2229,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.6959447860717773,
      "learning_rate": 9.81e-05,
      "loss": 0.0395,
      "step": 20
    },
    {
      "epoch": 1.5,
      "grad_norm": 6.28496789932251,
      "learning_rate": 9.71e-05,
      "loss": 0.0261,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8198316097259521,
      "learning_rate": 9.61e-05,
      "loss": 0.0346,
      "step": 40
    },
    {
      "epoch": 2.5,
      "grad_norm": 3.930227518081665,
      "learning_rate": 9.51e-05,
      "loss": 0.0237,
      "step": 50
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.24117116630077362,
      "learning_rate": 9.41e-05,
      "loss": 0.0144,
      "step": 60
    },
    {
      "epoch": 3.5,
      "grad_norm": 2.9592466354370117,
      "learning_rate": 9.310000000000001e-05,
      "loss": 0.0136,
      "step": 70
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.1739702224731445,
      "learning_rate": 9.21e-05,
      "loss": 0.0143,
      "step": 80
    },
    {
      "epoch": 4.5,
      "grad_norm": 1.1602582931518555,
      "learning_rate": 9.11e-05,
      "loss": 0.0166,
      "step": 90
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.7479774951934814,
      "learning_rate": 9.010000000000001e-05,
      "loss": 0.0174,
      "step": 100
    },
    {
      "epoch": 5.5,
      "grad_norm": 1.2943713665008545,
      "learning_rate": 8.910000000000001e-05,
      "loss": 0.0127,
      "step": 110
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.9738529920578003,
      "learning_rate": 8.81e-05,
      "loss": 0.0056,
      "step": 120
    },
    {
      "epoch": 6.5,
      "grad_norm": 1.6200770139694214,
      "learning_rate": 8.71e-05,
      "loss": 0.0053,
      "step": 130
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.116046667098999,
      "learning_rate": 8.61e-05,
      "loss": 0.0058,
      "step": 140
    },
    {
      "epoch": 7.5,
      "grad_norm": 1.7189213037490845,
      "learning_rate": 8.510000000000001e-05,
      "loss": 0.0035,
      "step": 150
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.13006743788719177,
      "learning_rate": 8.41e-05,
      "loss": 0.0025,
      "step": 160
    },
    {
      "epoch": 8.5,
      "grad_norm": 0.35229212045669556,
      "learning_rate": 8.31e-05,
      "loss": 0.002,
      "step": 170
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.5283310413360596,
      "learning_rate": 8.21e-05,
      "loss": 0.0026,
      "step": 180
    },
    {
      "epoch": 9.5,
      "grad_norm": 1.4066272974014282,
      "learning_rate": 8.11e-05,
      "loss": 0.0028,
      "step": 190
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6277774572372437,
      "learning_rate": 8.010000000000001e-05,
      "loss": 0.0018,
      "step": 200
    },
    {
      "epoch": 10.5,
      "grad_norm": 1.3672561645507812,
      "learning_rate": 7.910000000000001e-05,
      "loss": 0.0019,
      "step": 210
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.849717915058136,
      "learning_rate": 7.81e-05,
      "loss": 0.0014,
      "step": 220
    },
    {
      "epoch": 11.5,
      "grad_norm": 1.2382935285568237,
      "learning_rate": 7.71e-05,
      "loss": 0.0017,
      "step": 230
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.3568917512893677,
      "learning_rate": 7.61e-05,
      "loss": 0.0015,
      "step": 240
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.02996239811182022,
      "learning_rate": 7.510000000000001e-05,
      "loss": 0.0009,
      "step": 250
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.3278927206993103,
      "learning_rate": 7.41e-05,
      "loss": 0.0016,
      "step": 260
    },
    {
      "epoch": 13.5,
      "grad_norm": 0.78089839220047,
      "learning_rate": 7.31e-05,
      "loss": 0.0015,
      "step": 270
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.049814224243164,
      "learning_rate": 7.21e-05,
      "loss": 0.0008,
      "step": 280
    },
    {
      "epoch": 14.5,
      "grad_norm": 0.05354577675461769,
      "learning_rate": 7.11e-05,
      "loss": 0.0012,
      "step": 290
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.7721472978591919,
      "learning_rate": 7.01e-05,
      "loss": 0.0007,
      "step": 300
    },
    {
      "epoch": 15.5,
      "grad_norm": 0.5011315941810608,
      "learning_rate": 6.91e-05,
      "loss": 0.0006,
      "step": 310
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.2097933441400528,
      "learning_rate": 6.81e-05,
      "loss": 0.001,
      "step": 320
    },
    {
      "epoch": 16.5,
      "grad_norm": 0.6485989689826965,
      "learning_rate": 6.71e-05,
      "loss": 0.0011,
      "step": 330
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.46603426337242126,
      "learning_rate": 6.610000000000001e-05,
      "loss": 0.0008,
      "step": 340
    },
    {
      "epoch": 17.5,
      "grad_norm": 1.16153883934021,
      "learning_rate": 6.510000000000001e-05,
      "loss": 0.0012,
      "step": 350
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.509899377822876,
      "learning_rate": 6.41e-05,
      "loss": 0.001,
      "step": 360
    },
    {
      "epoch": 18.5,
      "grad_norm": 0.22210121154785156,
      "learning_rate": 6.31e-05,
      "loss": 0.0006,
      "step": 370
    },
    {
      "epoch": 19.0,
      "grad_norm": 1.4337605237960815,
      "learning_rate": 6.21e-05,
      "loss": 0.0014,
      "step": 380
    },
    {
      "epoch": 19.5,
      "grad_norm": 0.6034935116767883,
      "learning_rate": 6.110000000000001e-05,
      "loss": 0.0006,
      "step": 390
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.27057749032974243,
      "learning_rate": 6.0100000000000004e-05,
      "loss": 0.0009,
      "step": 400
    },
    {
      "epoch": 20.5,
      "grad_norm": 0.6695419549942017,
      "learning_rate": 5.91e-05,
      "loss": 0.0004,
      "step": 410
    },
    {
      "epoch": 21.0,
      "grad_norm": 1.8617427349090576,
      "learning_rate": 5.8099999999999996e-05,
      "loss": 0.002,
      "step": 420
    },
    {
      "epoch": 21.5,
      "grad_norm": 0.7135971784591675,
      "learning_rate": 5.71e-05,
      "loss": 0.0022,
      "step": 430
    },
    {
      "epoch": 22.0,
      "grad_norm": 1.104410171508789,
      "learning_rate": 5.610000000000001e-05,
      "loss": 0.0018,
      "step": 440
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.5932751297950745,
      "learning_rate": 5.5100000000000004e-05,
      "loss": 0.0014,
      "step": 450
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.4027913510799408,
      "learning_rate": 5.410000000000001e-05,
      "loss": 0.0008,
      "step": 460
    },
    {
      "epoch": 23.5,
      "grad_norm": 0.7953199148178101,
      "learning_rate": 5.31e-05,
      "loss": 0.0011,
      "step": 470
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.25498589873313904,
      "learning_rate": 5.2100000000000006e-05,
      "loss": 0.0004,
      "step": 480
    },
    {
      "epoch": 24.5,
      "grad_norm": 0.8258208632469177,
      "learning_rate": 5.11e-05,
      "loss": 0.0007,
      "step": 490
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.18510620296001434,
      "learning_rate": 5.0100000000000005e-05,
      "loss": 0.0007,
      "step": 500
    },
    {
      "epoch": 25.5,
      "grad_norm": 0.8307366371154785,
      "learning_rate": 4.91e-05,
      "loss": 0.0007,
      "step": 510
    },
    {
      "epoch": 26.0,
      "grad_norm": 0.7541914582252502,
      "learning_rate": 4.8100000000000004e-05,
      "loss": 0.0007,
      "step": 520
    },
    {
      "epoch": 26.5,
      "grad_norm": 0.3338281214237213,
      "learning_rate": 4.71e-05,
      "loss": 0.0004,
      "step": 530
    },
    {
      "epoch": 27.0,
      "grad_norm": 0.06798086315393448,
      "learning_rate": 4.61e-05,
      "loss": 0.0007,
      "step": 540
    },
    {
      "epoch": 27.5,
      "grad_norm": 0.15522146224975586,
      "learning_rate": 4.5100000000000005e-05,
      "loss": 0.0004,
      "step": 550
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.4013696610927582,
      "learning_rate": 4.41e-05,
      "loss": 0.0006,
      "step": 560
    },
    {
      "epoch": 28.5,
      "grad_norm": 0.40657514333724976,
      "learning_rate": 4.3100000000000004e-05,
      "loss": 0.0007,
      "step": 570
    },
    {
      "epoch": 29.0,
      "grad_norm": 0.14566798508167267,
      "learning_rate": 4.21e-05,
      "loss": 0.0001,
      "step": 580
    },
    {
      "epoch": 29.5,
      "grad_norm": 0.4930070638656616,
      "learning_rate": 4.11e-05,
      "loss": 0.0003,
      "step": 590
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.2327234447002411,
      "learning_rate": 4.0100000000000006e-05,
      "loss": 0.0005,
      "step": 600
    },
    {
      "epoch": 30.5,
      "grad_norm": 0.5080268383026123,
      "learning_rate": 3.91e-05,
      "loss": 0.0003,
      "step": 610
    },
    {
      "epoch": 31.0,
      "grad_norm": 0.5666539669036865,
      "learning_rate": 3.8100000000000005e-05,
      "loss": 0.0004,
      "step": 620
    },
    {
      "epoch": 31.5,
      "grad_norm": 0.03347349166870117,
      "learning_rate": 3.71e-05,
      "loss": 0.0006,
      "step": 630
    },
    {
      "epoch": 32.0,
      "grad_norm": 0.4377991557121277,
      "learning_rate": 3.61e-05,
      "loss": 0.0001,
      "step": 640
    },
    {
      "epoch": 32.5,
      "grad_norm": 0.19413357973098755,
      "learning_rate": 3.51e-05,
      "loss": 0.0005,
      "step": 650
    },
    {
      "epoch": 33.0,
      "grad_norm": 0.18701113760471344,
      "learning_rate": 3.41e-05,
      "loss": 0.0001,
      "step": 660
    },
    {
      "epoch": 33.5,
      "grad_norm": 0.31651440262794495,
      "learning_rate": 3.3100000000000005e-05,
      "loss": 0.0005,
      "step": 670
    },
    {
      "epoch": 34.0,
      "grad_norm": 0.02828579768538475,
      "learning_rate": 3.21e-05,
      "loss": 0.0,
      "step": 680
    },
    {
      "epoch": 34.5,
      "grad_norm": 0.34173232316970825,
      "learning_rate": 3.1100000000000004e-05,
      "loss": 0.0006,
      "step": 690
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.09027812629938126,
      "learning_rate": 3.01e-05,
      "loss": 0.0001,
      "step": 700
    },
    {
      "epoch": 35.5,
      "grad_norm": 0.22914953529834747,
      "learning_rate": 2.91e-05,
      "loss": 0.0001,
      "step": 710
    },
    {
      "epoch": 36.0,
      "grad_norm": 0.2684924900531769,
      "learning_rate": 2.8100000000000005e-05,
      "loss": 0.0006,
      "step": 720
    },
    {
      "epoch": 36.5,
      "grad_norm": 0.29140010476112366,
      "learning_rate": 2.7100000000000005e-05,
      "loss": 0.0003,
      "step": 730
    },
    {
      "epoch": 37.0,
      "grad_norm": 0.39679646492004395,
      "learning_rate": 2.61e-05,
      "loss": 0.0003,
      "step": 740
    },
    {
      "epoch": 37.5,
      "grad_norm": 0.08030686527490616,
      "learning_rate": 2.51e-05,
      "loss": 0.0005,
      "step": 750
    },
    {
      "epoch": 38.0,
      "grad_norm": 0.06952106207609177,
      "learning_rate": 2.41e-05,
      "loss": 0.0,
      "step": 760
    },
    {
      "epoch": 38.5,
      "grad_norm": 0.03430015593767166,
      "learning_rate": 2.3100000000000002e-05,
      "loss": 0.0003,
      "step": 770
    },
    {
      "epoch": 39.0,
      "grad_norm": 0.31544044613838196,
      "learning_rate": 2.2100000000000002e-05,
      "loss": 0.0003,
      "step": 780
    },
    {
      "epoch": 39.5,
      "grad_norm": 0.20336127281188965,
      "learning_rate": 2.11e-05,
      "loss": 0.0,
      "step": 790
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.028785208240151405,
      "learning_rate": 2.01e-05,
      "loss": 0.0005,
      "step": 800
    },
    {
      "epoch": 40.5,
      "grad_norm": 0.1161634773015976,
      "learning_rate": 1.91e-05,
      "loss": 0.0004,
      "step": 810
    },
    {
      "epoch": 41.0,
      "grad_norm": 0.11442368477582932,
      "learning_rate": 1.81e-05,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 41.5,
      "grad_norm": 0.010891513898968697,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 0.0002,
      "step": 830
    },
    {
      "epoch": 42.0,
      "grad_norm": 0.2547859251499176,
      "learning_rate": 1.6100000000000002e-05,
      "loss": 0.0003,
      "step": 840
    },
    {
      "epoch": 42.5,
      "grad_norm": 0.006857059430330992,
      "learning_rate": 1.51e-05,
      "loss": 0.0002,
      "step": 850
    },
    {
      "epoch": 43.0,
      "grad_norm": 0.4951632618904114,
      "learning_rate": 1.4099999999999999e-05,
      "loss": 0.0003,
      "step": 860
    },
    {
      "epoch": 43.5,
      "grad_norm": 0.041084468364715576,
      "learning_rate": 1.3100000000000002e-05,
      "loss": 0.0004,
      "step": 870
    },
    {
      "epoch": 44.0,
      "grad_norm": 0.11843769252300262,
      "learning_rate": 1.2100000000000001e-05,
      "loss": 0.0,
      "step": 880
    },
    {
      "epoch": 44.5,
      "grad_norm": 0.03217615187168121,
      "learning_rate": 1.11e-05,
      "loss": 0.0005,
      "step": 890
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.018256094306707382,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 45.5,
      "grad_norm": 0.042205873876810074,
      "learning_rate": 9.100000000000001e-06,
      "loss": 0.0,
      "step": 910
    },
    {
      "epoch": 46.0,
      "grad_norm": 0.05937511846423149,
      "learning_rate": 8.1e-06,
      "loss": 0.0004,
      "step": 920
    },
    {
      "epoch": 46.5,
      "grad_norm": 0.10673025250434875,
      "learning_rate": 7.1e-06,
      "loss": 0.0002,
      "step": 930
    },
    {
      "epoch": 47.0,
      "grad_norm": 0.1283574253320694,
      "learning_rate": 6.1e-06,
      "loss": 0.0002,
      "step": 940
    },
    {
      "epoch": 47.5,
      "grad_norm": 0.04566584527492523,
      "learning_rate": 5.1e-06,
      "loss": 0.0004,
      "step": 950
    },
    {
      "epoch": 48.0,
      "grad_norm": 0.08355249464511871,
      "learning_rate": 4.1000000000000006e-06,
      "loss": 0.0,
      "step": 960
    },
    {
      "epoch": 48.5,
      "grad_norm": 0.12251041829586029,
      "learning_rate": 3.1e-06,
      "loss": 0.0002,
      "step": 970
    },
    {
      "epoch": 49.0,
      "grad_norm": 0.16482886672019958,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0002,
      "step": 980
    },
    {
      "epoch": 49.5,
      "grad_norm": 0.008726044557988644,
      "learning_rate": 1.1e-06,
      "loss": 0.0002,
      "step": 990
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.0353192463517189,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.0002,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}