{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8025223016738892,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.4923,
      "step": 1
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8024629354476929,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.4923,
      "step": 2
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7746701240539551,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.4838,
      "step": 3
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6885385513305664,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.4412,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6546556353569031,
      "learning_rate": 0.00015,
      "loss": 1.3718,
      "step": 5
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7697901725769043,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.2978,
      "step": 6
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.8412020802497864,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.2189,
      "step": 7
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7889145016670227,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.1297,
      "step": 8
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.7386413812637329,
      "learning_rate": 0.00027,
      "loss": 1.0375,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.7709745168685913,
      "learning_rate": 0.0003,
      "loss": 0.9459,
      "step": 10
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.7179133296012878,
      "learning_rate": 0.0002967221401100708,
      "loss": 0.8415,
      "step": 11
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.696864128112793,
      "learning_rate": 0.0002870318186463901,
      "loss": 0.7327,
      "step": 12
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.6389071345329285,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.6332,
      "step": 13
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.5981886982917786,
      "learning_rate": 0.0002503695909538287,
      "loss": 0.5437,
      "step": 14
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.6274304389953613,
      "learning_rate": 0.000225,
      "loss": 0.4655,
      "step": 15
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.5762436389923096,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.394,
      "step": 16
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.5552861094474792,
      "learning_rate": 0.000165679269490148,
      "loss": 0.332,
      "step": 17
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.536261796951294,
      "learning_rate": 0.000134320730509852,
      "loss": 0.2785,
      "step": 18
    },
    {
      "epoch": 19.0,
      "grad_norm": 0.48586374521255493,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.2342,
      "step": 19
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.45940732955932617,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.1992,
      "step": 20
    },
    {
      "epoch": 21.0,
      "grad_norm": 0.42822158336639404,
      "learning_rate": 4.963040904617131e-05,
      "loss": 0.1728,
      "step": 21
    },
    {
      "epoch": 22.0,
      "grad_norm": 0.4039425849914551,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.1533,
      "step": 22
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.38404396176338196,
      "learning_rate": 1.2968181353609852e-05,
      "loss": 0.1403,
      "step": 23
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.3684459328651428,
      "learning_rate": 3.2778598899291465e-06,
      "loss": 0.1325,
      "step": 24
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.3580010235309601,
      "learning_rate": 0.0,
      "loss": 0.129,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3628959635865600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}