{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09230414214837891,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015384023691396484,
      "grad_norm": 11396.142578125,
      "learning_rate": 3e-07,
      "loss": 8.8759,
      "step": 10
    },
    {
      "epoch": 0.003076804738279297,
      "grad_norm": 689.1935424804688,
      "learning_rate": 1.2999999999999998e-06,
      "loss": 8.2644,
      "step": 20
    },
    {
      "epoch": 0.004615207107418946,
      "grad_norm": 454.8230285644531,
      "learning_rate": 2.2999999999999996e-06,
      "loss": 7.2145,
      "step": 30
    },
    {
      "epoch": 0.006153609476558594,
      "grad_norm": 169.3773193359375,
      "learning_rate": 3.2999999999999993e-06,
      "loss": 6.899,
      "step": 40
    },
    {
      "epoch": 0.007692011845698243,
      "grad_norm": 121.77935028076172,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 6.7803,
      "step": 50
    },
    {
      "epoch": 0.009230414214837892,
      "grad_norm": 1289.1287841796875,
      "learning_rate": 5.3e-06,
      "loss": 6.5956,
      "step": 60
    },
    {
      "epoch": 0.010768816583977539,
      "grad_norm": 157.25286865234375,
      "learning_rate": 6.3e-06,
      "loss": 6.6402,
      "step": 70
    },
    {
      "epoch": 0.012307218953117188,
      "grad_norm": 384.85919189453125,
      "learning_rate": 7.299999999999999e-06,
      "loss": 6.4978,
      "step": 80
    },
    {
      "epoch": 0.013845621322256836,
      "grad_norm": 301.0735778808594,
      "learning_rate": 8.299999999999998e-06,
      "loss": 6.3964,
      "step": 90
    },
    {
      "epoch": 0.015384023691396485,
      "grad_norm": 226.9570770263672,
      "learning_rate": 9.299999999999999e-06,
      "loss": 6.3804,
      "step": 100
    },
    {
      "epoch": 0.016922426060536132,
      "grad_norm": 101.4676513671875,
      "learning_rate": 1.03e-05,
      "loss": 6.3698,
      "step": 110
    },
    {
      "epoch": 0.018460828429675783,
      "grad_norm": 230.73281860351562,
      "learning_rate": 1.1299999999999999e-05,
      "loss": 6.4247,
      "step": 120
    },
    {
      "epoch": 0.01999923079881543,
      "grad_norm": 124.10091400146484,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 6.3109,
      "step": 130
    },
    {
      "epoch": 0.021537633167955077,
      "grad_norm": 97.28553009033203,
      "learning_rate": 1.33e-05,
      "loss": 6.3895,
      "step": 140
    },
    {
      "epoch": 0.023076035537094728,
      "grad_norm": 182.08811950683594,
      "learning_rate": 1.43e-05,
      "loss": 6.4089,
      "step": 150
    },
    {
      "epoch": 0.024614437906234375,
      "grad_norm": 433.91973876953125,
      "learning_rate": 1.53e-05,
      "loss": 6.3014,
      "step": 160
    },
    {
      "epoch": 0.026152840275374026,
      "grad_norm": 352.3630065917969,
      "learning_rate": 1.6299999999999996e-05,
      "loss": 6.3332,
      "step": 170
    },
    {
      "epoch": 0.027691242644513673,
      "grad_norm": 74.03328704833984,
      "learning_rate": 1.7299999999999997e-05,
      "loss": 6.315,
      "step": 180
    },
    {
      "epoch": 0.02922964501365332,
      "grad_norm": 264.071044921875,
      "learning_rate": 1.8299999999999998e-05,
      "loss": 6.3367,
      "step": 190
    },
    {
      "epoch": 0.03076804738279297,
      "grad_norm": 92.3805160522461,
      "learning_rate": 1.93e-05,
      "loss": 6.306,
      "step": 200
    },
    {
      "epoch": 0.03230644975193262,
      "grad_norm": 105.78662872314453,
      "learning_rate": 2.03e-05,
      "loss": 6.272,
      "step": 210
    },
    {
      "epoch": 0.033844852121072265,
      "grad_norm": 34.507057189941406,
      "learning_rate": 2.1299999999999996e-05,
      "loss": 6.2943,
      "step": 220
    },
    {
      "epoch": 0.035383254490211916,
      "grad_norm": 29.95108985900879,
      "learning_rate": 2.23e-05,
      "loss": 6.2231,
      "step": 230
    },
    {
      "epoch": 0.036921656859351566,
      "grad_norm": 105.78109741210938,
      "learning_rate": 2.3299999999999997e-05,
      "loss": 6.2223,
      "step": 240
    },
    {
      "epoch": 0.03846005922849121,
      "grad_norm": 115.77278900146484,
      "learning_rate": 2.4299999999999998e-05,
      "loss": 6.1873,
      "step": 250
    },
    {
      "epoch": 0.03999846159763086,
      "grad_norm": 117.57398223876953,
      "learning_rate": 2.53e-05,
      "loss": 6.1889,
      "step": 260
    },
    {
      "epoch": 0.04153686396677051,
      "grad_norm": 27.769681930541992,
      "learning_rate": 2.63e-05,
      "loss": 6.1833,
      "step": 270
    },
    {
      "epoch": 0.043075266335910155,
      "grad_norm": 50.23863220214844,
      "learning_rate": 2.7299999999999996e-05,
      "loss": 6.1718,
      "step": 280
    },
    {
      "epoch": 0.044613668705049805,
      "grad_norm": 16.450408935546875,
      "learning_rate": 2.83e-05,
      "loss": 6.0966,
      "step": 290
    },
    {
      "epoch": 0.046152071074189456,
      "grad_norm": 28.899629592895508,
      "learning_rate": 2.9299999999999997e-05,
      "loss": 6.146,
      "step": 300
    },
    {
      "epoch": 0.0476904734433291,
      "grad_norm": 47.915279388427734,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 6.1493,
      "step": 310
    },
    {
      "epoch": 0.04922887581246875,
      "grad_norm": 27.1001033782959,
      "learning_rate": 3.1299999999999995e-05,
      "loss": 6.1186,
      "step": 320
    },
    {
      "epoch": 0.0507672781816084,
      "grad_norm": 22.059106826782227,
      "learning_rate": 3.229999999999999e-05,
      "loss": 6.0607,
      "step": 330
    },
    {
      "epoch": 0.05230568055074805,
      "grad_norm": 19.7325496673584,
      "learning_rate": 3.3299999999999996e-05,
      "loss": 6.1196,
      "step": 340
    },
    {
      "epoch": 0.053844082919887695,
      "grad_norm": 100.60061645507812,
      "learning_rate": 3.4299999999999993e-05,
      "loss": 6.1176,
      "step": 350
    },
    {
      "epoch": 0.055382485289027346,
      "grad_norm": 18.382129669189453,
      "learning_rate": 3.53e-05,
      "loss": 6.1501,
      "step": 360
    },
    {
      "epoch": 0.056920887658166996,
      "grad_norm": 31.890426635742188,
      "learning_rate": 3.6299999999999995e-05,
      "loss": 6.0863,
      "step": 370
    },
    {
      "epoch": 0.05845929002730664,
      "grad_norm": 22.61912727355957,
      "learning_rate": 3.73e-05,
      "loss": 6.0543,
      "step": 380
    },
    {
      "epoch": 0.05999769239644629,
      "grad_norm": 30.638811111450195,
      "learning_rate": 3.83e-05,
      "loss": 5.989,
      "step": 390
    },
    {
      "epoch": 0.06153609476558594,
      "grad_norm": 45.842227935791016,
      "learning_rate": 3.93e-05,
      "loss": 6.0216,
      "step": 400
    },
    {
      "epoch": 0.06307449713472559,
      "grad_norm": 61.62559127807617,
      "learning_rate": 4.03e-05,
      "loss": 6.0232,
      "step": 410
    },
    {
      "epoch": 0.06461289950386524,
      "grad_norm": 24.91366958618164,
      "learning_rate": 4.1299999999999994e-05,
      "loss": 6.0153,
      "step": 420
    },
    {
      "epoch": 0.06615130187300489,
      "grad_norm": 22.554046630859375,
      "learning_rate": 4.229999999999999e-05,
      "loss": 5.9533,
      "step": 430
    },
    {
      "epoch": 0.06768970424214453,
      "grad_norm": 22.699480056762695,
      "learning_rate": 4.3299999999999995e-05,
      "loss": 5.9179,
      "step": 440
    },
    {
      "epoch": 0.06922810661128419,
      "grad_norm": 17.466867446899414,
      "learning_rate": 4.43e-05,
      "loss": 5.9714,
      "step": 450
    },
    {
      "epoch": 0.07076650898042383,
      "grad_norm": 20.46624183654785,
      "learning_rate": 4.5299999999999997e-05,
      "loss": 5.9621,
      "step": 460
    },
    {
      "epoch": 0.07230491134956347,
      "grad_norm": 15.140242576599121,
      "learning_rate": 4.6299999999999994e-05,
      "loss": 5.94,
      "step": 470
    },
    {
      "epoch": 0.07384331371870313,
      "grad_norm": 23.270614624023438,
      "learning_rate": 4.73e-05,
      "loss": 5.9387,
      "step": 480
    },
    {
      "epoch": 0.07538171608784278,
      "grad_norm": 23.621036529541016,
      "learning_rate": 4.8299999999999995e-05,
      "loss": 5.9683,
      "step": 490
    },
    {
      "epoch": 0.07692011845698242,
      "grad_norm": 16.960304260253906,
      "learning_rate": 4.929999999999999e-05,
      "loss": 5.9136,
      "step": 500
    },
    {
      "epoch": 0.07845852082612208,
      "grad_norm": 17.167306900024414,
      "learning_rate": 5.0299999999999996e-05,
      "loss": 5.9011,
      "step": 510
    },
    {
      "epoch": 0.07999692319526172,
      "grad_norm": 28.44086456298828,
      "learning_rate": 5.13e-05,
      "loss": 5.88,
      "step": 520
    },
    {
      "epoch": 0.08153532556440136,
      "grad_norm": 19.138957977294922,
      "learning_rate": 5.23e-05,
      "loss": 5.8525,
      "step": 530
    },
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 23.37527847290039,
      "learning_rate": 5.3299999999999995e-05,
      "loss": 5.9051,
      "step": 540
    },
    {
      "epoch": 0.08461213030268067,
      "grad_norm": 14.438946723937988,
      "learning_rate": 5.429999999999999e-05,
      "loss": 5.8024,
      "step": 550
    },
    {
      "epoch": 0.08615053267182031,
      "grad_norm": 17.277740478515625,
      "learning_rate": 5.529999999999999e-05,
      "loss": 5.764,
      "step": 560
    },
    {
      "epoch": 0.08768893504095997,
      "grad_norm": 18.269975662231445,
      "learning_rate": 5.63e-05,
      "loss": 5.8667,
      "step": 570
    },
    {
      "epoch": 0.08922733741009961,
      "grad_norm": 17.265398025512695,
      "learning_rate": 5.73e-05,
      "loss": 5.7963,
      "step": 580
    },
    {
      "epoch": 0.09076573977923925,
      "grad_norm": 20.076812744140625,
      "learning_rate": 5.8299999999999994e-05,
      "loss": 5.7426,
      "step": 590
    },
    {
      "epoch": 0.09230414214837891,
      "grad_norm": 25.95227813720703,
      "learning_rate": 5.929999999999999e-05,
      "loss": 5.7171,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 16,
  "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": 1.1563454945624064e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}