{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 0.08136817067861557,
      "learning_rate": 0.0004,
      "loss": 1.158,
      "step": 25
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.0653829574584961,
      "learning_rate": 0.0004998852503731983,
      "loss": 1.0957,
      "step": 50
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.11592712253332138,
      "learning_rate": 0.0004993848168027977,
      "loss": 0.9276,
      "step": 75
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.08926476538181305,
      "learning_rate": 0.0004984880506341147,
      "loss": 1.0337,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9111642837524414,
      "eval_runtime": 843.8058,
      "eval_samples_per_second": 1.3,
      "eval_steps_per_second": 0.021,
      "step": 100
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.08632034063339233,
      "learning_rate": 0.0004971963770447935,
      "loss": 1.0219,
      "step": 125
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.12949417531490326,
      "learning_rate": 0.0004955118488155782,
      "loss": 0.784,
      "step": 150
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.09222520887851715,
      "learning_rate": 0.0004934371430679492,
      "loss": 1.0,
      "step": 175
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.10075929015874863,
      "learning_rate": 0.0004909755570095319,
      "loss": 0.9617,
      "step": 200
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.9380430579185486,
      "eval_runtime": 856.156,
      "eval_samples_per_second": 1.281,
      "eval_steps_per_second": 0.021,
      "step": 200
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.09567111730575562,
      "learning_rate": 0.0004881310026940389,
      "loss": 0.7051,
      "step": 225
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.09723825007677078,
      "learning_rate": 0.0004849080008040734,
      "loss": 0.9906,
      "step": 250
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.09430444985628128,
      "learning_rate": 0.00048131167346667446,
      "loss": 0.9113,
      "step": 275
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09439756721258163,
      "learning_rate": 0.00047734773611302284,
      "loss": 0.674,
      "step": 300
    },
    {
      "epoch": 0.15,
      "eval_loss": 0.9544369578361511,
      "eval_runtime": 850.9461,
      "eval_samples_per_second": 1.289,
      "eval_steps_per_second": 0.021,
      "step": 300
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.10961435735225677,
      "learning_rate": 0.0004730224883952422,
      "loss": 0.9701,
      "step": 325
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.09628895670175552,
      "learning_rate": 0.0004683428041747334,
      "loss": 0.8976,
      "step": 350
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.11085063964128494,
      "learning_rate": 0.0004633161205979517,
      "loss": 0.6683,
      "step": 375
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.10140710324048996,
      "learning_rate": 0.0004579504262769877,
      "loss": 0.9373,
      "step": 400
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.968166172504425,
      "eval_runtime": 853.0258,
      "eval_samples_per_second": 1.286,
      "eval_steps_per_second": 0.021,
      "step": 400
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.13868793845176697,
      "learning_rate": 0.0004522542485937369,
      "loss": 0.8822,
      "step": 425
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.11853040754795074,
      "learning_rate": 0.00044623664014783386,
      "loss": 0.6483,
      "step": 450
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.11668186634778976,
      "learning_rate": 0.00043990716436988924,
      "loss": 0.9374,
      "step": 475
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.11911585181951523,
      "learning_rate": 0.0004332758803228925,
      "loss": 0.8434,
      "step": 500
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.9753186702728271,
      "eval_runtime": 851.2812,
      "eval_samples_per_second": 1.289,
      "eval_steps_per_second": 0.021,
      "step": 500
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.09807440638542175,
      "learning_rate": 0.00042635332671593575,
      "loss": 0.6661,
      "step": 525
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.09675773978233337,
      "learning_rate": 0.00041915050515566445,
      "loss": 0.8999,
      "step": 550
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.0979737937450409,
      "learning_rate": 0.00041167886266207167,
      "loss": 0.8616,
      "step": 575
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08990875631570816,
      "learning_rate": 0.0004039502734764241,
      "loss": 0.8167,
      "step": 600
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.9926204681396484,
      "eval_runtime": 851.6484,
      "eval_samples_per_second": 1.288,
      "eval_steps_per_second": 0.021,
      "step": 600
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 6.031064373500314e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}