{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005,
      "grad_norm": 10.3125,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.2492,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 11.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3168,
      "step": 20
    },
    {
      "epoch": 0.015,
      "grad_norm": 8.9375,
      "learning_rate": 3e-06,
      "loss": 1.3578,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 10.1875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2434,
      "step": 40
    },
    {
      "epoch": 0.025,
      "grad_norm": 9.5625,
      "learning_rate": 5e-06,
      "loss": 1.2461,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.4375,
      "learning_rate": 6e-06,
      "loss": 1.1131,
      "step": 60
    },
    {
      "epoch": 0.035,
      "grad_norm": 11.6875,
      "learning_rate": 7e-06,
      "loss": 1.1562,
      "step": 70
    },
    {
      "epoch": 0.04,
      "grad_norm": 8.6875,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2025,
      "step": 80
    },
    {
      "epoch": 0.045,
      "grad_norm": 6.875,
      "learning_rate": 9e-06,
      "loss": 1.1477,
      "step": 90
    },
    {
      "epoch": 0.05,
      "grad_norm": 6.90625,
      "learning_rate": 1e-05,
      "loss": 1.0277,
      "step": 100
    },
    {
      "epoch": 0.055,
      "grad_norm": 8.25,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.0428,
      "step": 110
    },
    {
      "epoch": 0.06,
      "grad_norm": 7.78125,
      "learning_rate": 1.2e-05,
      "loss": 0.9688,
      "step": 120
    },
    {
      "epoch": 0.065,
      "grad_norm": 6.71875,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.9908,
      "step": 130
    },
    {
      "epoch": 0.07,
      "grad_norm": 8.125,
      "learning_rate": 1.4e-05,
      "loss": 1.0992,
      "step": 140
    },
    {
      "epoch": 0.075,
      "grad_norm": 8.4375,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9598,
      "step": 150
    },
    {
      "epoch": 0.08,
      "grad_norm": 9.25,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9885,
      "step": 160
    },
    {
      "epoch": 0.085,
      "grad_norm": 13.875,
      "learning_rate": 1.7e-05,
      "loss": 1.2307,
      "step": 170
    },
    {
      "epoch": 0.09,
      "grad_norm": 9.3125,
      "learning_rate": 1.8e-05,
      "loss": 0.9137,
      "step": 180
    },
    {
      "epoch": 0.095,
      "grad_norm": 9.25,
      "learning_rate": 1.9e-05,
      "loss": 1.5107,
      "step": 190
    },
    {
      "epoch": 0.1,
      "grad_norm": 96.0,
      "learning_rate": 2e-05,
      "loss": 0.9955,
      "step": 200
    },
    {
      "epoch": 0.105,
      "grad_norm": 26.25,
      "learning_rate": 1.9998476951563914e-05,
      "loss": 1.6652,
      "step": 210
    },
    {
      "epoch": 0.11,
      "grad_norm": 7.21875,
      "learning_rate": 1.999390827019096e-05,
      "loss": 0.86,
      "step": 220
    },
    {
      "epoch": 0.115,
      "grad_norm": 56.0,
      "learning_rate": 1.9986295347545738e-05,
      "loss": 1.9418,
      "step": 230
    },
    {
      "epoch": 0.12,
      "grad_norm": 11.625,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.8643,
      "step": 240
    },
    {
      "epoch": 0.125,
      "grad_norm": 52.0,
      "learning_rate": 1.9961946980917457e-05,
      "loss": 1.3936,
      "step": 250
    },
    {
      "epoch": 0.13,
      "grad_norm": 28.125,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 0.8059,
      "step": 260
    },
    {
      "epoch": 0.135,
      "grad_norm": 12.125,
      "learning_rate": 1.9925461516413224e-05,
      "loss": 0.8197,
      "step": 270
    },
    {
      "epoch": 0.14,
      "grad_norm": 30.5,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 1.3477,
      "step": 280
    },
    {
      "epoch": 0.145,
      "grad_norm": 24.5,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 1.0397,
      "step": 290
    },
    {
      "epoch": 0.15,
      "grad_norm": 7.15625,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.8006,
      "step": 300
    },
    {
      "epoch": 0.155,
      "grad_norm": 87.0,
      "learning_rate": 1.9816271834476642e-05,
      "loss": 1.0712,
      "step": 310
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.375,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.6074,
      "step": 320
    },
    {
      "epoch": 0.165,
      "grad_norm": 74.0,
      "learning_rate": 1.9743700647852356e-05,
      "loss": 0.8439,
      "step": 330
    },
    {
      "epoch": 0.17,
      "grad_norm": 7.59375,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 0.6888,
      "step": 340
    },
    {
      "epoch": 0.175,
      "grad_norm": 59.25,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 0.7408,
      "step": 350
    },
    {
      "epoch": 0.18,
      "grad_norm": 24.0,
      "learning_rate": 1.961261695938319e-05,
      "loss": 0.6303,
      "step": 360
    },
    {
      "epoch": 0.185,
      "grad_norm": 7.625,
      "learning_rate": 1.9563047559630356e-05,
      "loss": 2.4628,
      "step": 370
    },
    {
      "epoch": 0.19,
      "grad_norm": 20.125,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.7479,
      "step": 380
    },
    {
      "epoch": 0.195,
      "grad_norm": 9.0,
      "learning_rate": 1.945518575599317e-05,
      "loss": 0.6927,
      "step": 390
    },
    {
      "epoch": 0.2,
      "grad_norm": 11.5625,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.5542,
      "step": 400
    },
    {
      "epoch": 0.205,
      "grad_norm": 6.9375,
      "learning_rate": 1.9335804264972018e-05,
      "loss": 1.097,
      "step": 410
    },
    {
      "epoch": 0.21,
      "grad_norm": 118.5,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 1.0457,
      "step": 420
    },
    {
      "epoch": 0.215,
      "grad_norm": 9.0,
      "learning_rate": 1.9205048534524405e-05,
      "loss": 0.9044,
      "step": 430
    },
    {
      "epoch": 0.22,
      "grad_norm": 8.3125,
      "learning_rate": 1.913545457642601e-05,
      "loss": 1.1971,
      "step": 440
    },
    {
      "epoch": 0.225,
      "grad_norm": 10.625,
      "learning_rate": 1.9063077870366504e-05,
      "loss": 0.9662,
      "step": 450
    },
    {
      "epoch": 0.23,
      "grad_norm": 68.5,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 0.5489,
      "step": 460
    },
    {
      "epoch": 0.235,
      "grad_norm": 21.625,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.3805,
      "step": 470
    },
    {
      "epoch": 0.24,
      "grad_norm": 22.125,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.4361,
      "step": 480
    },
    {
      "epoch": 0.245,
      "grad_norm": 8.6875,
      "learning_rate": 1.874619707139396e-05,
      "loss": 0.4573,
      "step": 490
    },
    {
      "epoch": 0.25,
      "grad_norm": 85.0,
      "learning_rate": 1.866025403784439e-05,
      "loss": 1.7953,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7832077697024e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}