{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.36921656859351565,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153609476558594,
      "grad_norm": 25468.8046875,
      "learning_rate": 1.9999999999999996e-07,
      "loss": 8.7082,
      "step": 10
    },
    {
      "epoch": 0.012307218953117188,
      "grad_norm": 1228.4501953125,
      "learning_rate": 1.2e-06,
      "loss": 8.0776,
      "step": 20
    },
    {
      "epoch": 0.018460828429675783,
      "grad_norm": 355.1081237792969,
      "learning_rate": 2.1999999999999997e-06,
      "loss": 7.2372,
      "step": 30
    },
    {
      "epoch": 0.024614437906234375,
      "grad_norm": 255.58433532714844,
      "learning_rate": 3.1999999999999994e-06,
      "loss": 6.9725,
      "step": 40
    },
    {
      "epoch": 0.03076804738279297,
      "grad_norm": 253.23995971679688,
      "learning_rate": 4.2e-06,
      "loss": 6.8585,
      "step": 50
    },
    {
      "epoch": 0.036921656859351566,
      "grad_norm": 241.82064819335938,
      "learning_rate": 5.199999999999999e-06,
      "loss": 6.7367,
      "step": 60
    },
    {
      "epoch": 0.043075266335910155,
      "grad_norm": 229.0261993408203,
      "learning_rate": 6.199999999999999e-06,
      "loss": 6.6534,
      "step": 70
    },
    {
      "epoch": 0.04922887581246875,
      "grad_norm": 321.6871337890625,
      "learning_rate": 7.2e-06,
      "loss": 6.6305,
      "step": 80
    },
    {
      "epoch": 0.055382485289027346,
      "grad_norm": 465.00543212890625,
      "learning_rate": 8.2e-06,
      "loss": 6.6253,
      "step": 90
    },
    {
      "epoch": 0.06153609476558594,
      "grad_norm": 566.6929321289062,
      "learning_rate": 9.199999999999998e-06,
      "loss": 6.5724,
      "step": 100
    },
    {
      "epoch": 0.06768970424214453,
      "grad_norm": 432.230712890625,
      "learning_rate": 1.02e-05,
      "loss": 6.5328,
      "step": 110
    },
    {
      "epoch": 0.07384331371870313,
      "grad_norm": 289.2374267578125,
      "learning_rate": 1.12e-05,
      "loss": 6.5547,
      "step": 120
    },
    {
      "epoch": 0.07999692319526172,
      "grad_norm": 595.7386474609375,
      "learning_rate": 1.2199999999999998e-05,
      "loss": 6.5651,
      "step": 130
    },
    {
      "epoch": 0.08615053267182031,
      "grad_norm": 861.4376220703125,
      "learning_rate": 1.3199999999999997e-05,
      "loss": 6.5337,
      "step": 140
    },
    {
      "epoch": 0.09230414214837891,
      "grad_norm": 689.42919921875,
      "learning_rate": 1.4199999999999998e-05,
      "loss": 6.4927,
      "step": 150
    },
    {
      "epoch": 0.0984577516249375,
      "grad_norm": 380.9496765136719,
      "learning_rate": 1.5199999999999998e-05,
      "loss": 6.4812,
      "step": 160
    },
    {
      "epoch": 0.1046113611014961,
      "grad_norm": 221.21005249023438,
      "learning_rate": 1.6199999999999997e-05,
      "loss": 6.4508,
      "step": 170
    },
    {
      "epoch": 0.11076497057805469,
      "grad_norm": 199.30874633789062,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 6.4642,
      "step": 180
    },
    {
      "epoch": 0.11691858005461328,
      "grad_norm": 252.44459533691406,
      "learning_rate": 1.82e-05,
      "loss": 6.45,
      "step": 190
    },
    {
      "epoch": 0.12307218953117188,
      "grad_norm": 121.32320404052734,
      "learning_rate": 1.92e-05,
      "loss": 6.4115,
      "step": 200
    },
    {
      "epoch": 0.12922579900773049,
      "grad_norm": 207.04344177246094,
      "learning_rate": 2.0199999999999996e-05,
      "loss": 6.4532,
      "step": 210
    },
    {
      "epoch": 0.13537940848428906,
      "grad_norm": 296.6274719238281,
      "learning_rate": 2.12e-05,
      "loss": 6.3985,
      "step": 220
    },
    {
      "epoch": 0.14153301796084766,
      "grad_norm": 140.3836212158203,
      "learning_rate": 2.2199999999999998e-05,
      "loss": 6.4152,
      "step": 230
    },
    {
      "epoch": 0.14768662743740626,
      "grad_norm": 168.14443969726562,
      "learning_rate": 2.3199999999999998e-05,
      "loss": 6.3686,
      "step": 240
    },
    {
      "epoch": 0.15384023691396484,
      "grad_norm": 141.07810974121094,
      "learning_rate": 2.42e-05,
      "loss": 6.3809,
      "step": 250
    },
    {
      "epoch": 0.15999384639052344,
      "grad_norm": 117.08052062988281,
      "learning_rate": 2.52e-05,
      "loss": 6.3423,
      "step": 260
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 122.97789764404297,
      "learning_rate": 2.6199999999999996e-05,
      "loss": 6.3486,
      "step": 270
    },
    {
      "epoch": 0.17230106534364062,
      "grad_norm": 73.85701751708984,
      "learning_rate": 2.72e-05,
      "loss": 6.329,
      "step": 280
    },
    {
      "epoch": 0.17845467482019922,
      "grad_norm": 78.00408935546875,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 6.3096,
      "step": 290
    },
    {
      "epoch": 0.18460828429675782,
      "grad_norm": 150.3341827392578,
      "learning_rate": 2.9199999999999995e-05,
      "loss": 6.3063,
      "step": 300
    },
    {
      "epoch": 0.1907618937733164,
      "grad_norm": 61.75702667236328,
      "learning_rate": 3.02e-05,
      "loss": 6.3004,
      "step": 310
    },
    {
      "epoch": 0.196915503249875,
      "grad_norm": 83.836181640625,
      "learning_rate": 3.119999999999999e-05,
      "loss": 6.2534,
      "step": 320
    },
    {
      "epoch": 0.2030691127264336,
      "grad_norm": 190.2839813232422,
      "learning_rate": 3.22e-05,
      "loss": 6.2603,
      "step": 330
    },
    {
      "epoch": 0.2092227222029922,
      "grad_norm": 52.196563720703125,
      "learning_rate": 3.3199999999999994e-05,
      "loss": 6.2439,
      "step": 340
    },
    {
      "epoch": 0.21537633167955078,
      "grad_norm": 65.71736907958984,
      "learning_rate": 3.42e-05,
      "loss": 6.227,
      "step": 350
    },
    {
      "epoch": 0.22152994115610938,
      "grad_norm": 66.71468353271484,
      "learning_rate": 3.5199999999999995e-05,
      "loss": 6.2164,
      "step": 360
    },
    {
      "epoch": 0.22768355063266799,
      "grad_norm": 37.26243209838867,
      "learning_rate": 3.62e-05,
      "loss": 6.212,
      "step": 370
    },
    {
      "epoch": 0.23383716010922656,
      "grad_norm": 190.98501586914062,
      "learning_rate": 3.7199999999999996e-05,
      "loss": 6.1833,
      "step": 380
    },
    {
      "epoch": 0.23999076958578516,
      "grad_norm": 51.51064682006836,
      "learning_rate": 3.8199999999999993e-05,
      "loss": 6.1796,
      "step": 390
    },
    {
      "epoch": 0.24614437906234377,
      "grad_norm": 71.14685821533203,
      "learning_rate": 3.919999999999999e-05,
      "loss": 6.1614,
      "step": 400
    },
    {
      "epoch": 0.25229798853890234,
      "grad_norm": 47.48910140991211,
      "learning_rate": 4.02e-05,
      "loss": 6.1277,
      "step": 410
    },
    {
      "epoch": 0.25845159801546097,
      "grad_norm": 49.60618209838867,
      "learning_rate": 4.12e-05,
      "loss": 6.107,
      "step": 420
    },
    {
      "epoch": 0.26460520749201955,
      "grad_norm": 38.03694534301758,
      "learning_rate": 4.2199999999999996e-05,
      "loss": 6.0939,
      "step": 430
    },
    {
      "epoch": 0.2707588169685781,
      "grad_norm": 38.81101989746094,
      "learning_rate": 4.319999999999999e-05,
      "loss": 6.118,
      "step": 440
    },
    {
      "epoch": 0.27691242644513675,
      "grad_norm": 45.36625671386719,
      "learning_rate": 4.42e-05,
      "loss": 6.0641,
      "step": 450
    },
    {
      "epoch": 0.2830660359216953,
      "grad_norm": 44.09037780761719,
      "learning_rate": 4.5199999999999994e-05,
      "loss": 6.0417,
      "step": 460
    },
    {
      "epoch": 0.2892196453982539,
      "grad_norm": 39.48929214477539,
      "learning_rate": 4.62e-05,
      "loss": 6.0371,
      "step": 470
    },
    {
      "epoch": 0.29537325487481253,
      "grad_norm": 44.747039794921875,
      "learning_rate": 4.7199999999999995e-05,
      "loss": 6.0157,
      "step": 480
    },
    {
      "epoch": 0.3015268643513711,
      "grad_norm": 51.372249603271484,
      "learning_rate": 4.82e-05,
      "loss": 6.0378,
      "step": 490
    },
    {
      "epoch": 0.3076804738279297,
      "grad_norm": 46.31863021850586,
      "learning_rate": 4.9199999999999997e-05,
      "loss": 5.9815,
      "step": 500
    },
    {
      "epoch": 0.3138340833044883,
      "grad_norm": 74.35610961914062,
      "learning_rate": 5.0199999999999994e-05,
      "loss": 6.0108,
      "step": 510
    },
    {
      "epoch": 0.3199876927810469,
      "grad_norm": 31.986116409301758,
      "learning_rate": 5.119999999999999e-05,
      "loss": 5.9452,
      "step": 520
    },
    {
      "epoch": 0.32614130225760546,
      "grad_norm": 62.82748794555664,
      "learning_rate": 5.2199999999999995e-05,
      "loss": 5.9396,
      "step": 530
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 36.623085021972656,
      "learning_rate": 5.32e-05,
      "loss": 5.9078,
      "step": 540
    },
    {
      "epoch": 0.33844852121072266,
      "grad_norm": 66.77005004882812,
      "learning_rate": 5.4199999999999996e-05,
      "loss": 5.9127,
      "step": 550
    },
    {
      "epoch": 0.34460213068728124,
      "grad_norm": 42.2696533203125,
      "learning_rate": 5.519999999999999e-05,
      "loss": 5.8751,
      "step": 560
    },
    {
      "epoch": 0.35075574016383987,
      "grad_norm": 36.03275680541992,
      "learning_rate": 5.619999999999999e-05,
      "loss": 5.8704,
      "step": 570
    },
    {
      "epoch": 0.35690934964039844,
      "grad_norm": 34.99599838256836,
      "learning_rate": 5.72e-05,
      "loss": 5.8357,
      "step": 580
    },
    {
      "epoch": 0.363062959116957,
      "grad_norm": 37.03520584106445,
      "learning_rate": 5.82e-05,
      "loss": 5.8248,
      "step": 590
    },
    {
      "epoch": 0.36921656859351565,
      "grad_norm": 39.70176696777344,
      "learning_rate": 5.9199999999999996e-05,
      "loss": 5.782,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 62,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.54385027776512e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}