{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009325326739667962,
  "eval_steps": 5,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": NaN,
      "eval_runtime": 171.1522,
      "eval_samples_per_second": 8.706,
      "eval_steps_per_second": 4.353,
      "step": 1
    },
    {
      "epoch": 0.0008477569763334511,
      "grad_norm": NaN,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001412928293889085,
      "eval_loss": NaN,
      "eval_runtime": 171.7075,
      "eval_samples_per_second": 8.678,
      "eval_steps_per_second": 4.339,
      "step": 5
    },
    {
      "epoch": 0.0016955139526669022,
      "grad_norm": NaN,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002543270929000353,
      "grad_norm": NaN,
      "learning_rate": 0.00010588235294117647,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00282585658777817,
      "eval_loss": NaN,
      "eval_runtime": 171.8729,
      "eval_samples_per_second": 8.669,
      "eval_steps_per_second": 4.335,
      "step": 10
    },
    {
      "epoch": 0.0033910279053338045,
      "grad_norm": NaN,
      "learning_rate": 0.0001411764705882353,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": NaN,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0042387848816672555,
      "eval_loss": NaN,
      "eval_runtime": 172.1197,
      "eval_samples_per_second": 8.657,
      "eval_steps_per_second": 4.328,
      "step": 15
    },
    {
      "epoch": 0.005086541858000706,
      "grad_norm": NaN,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00565171317555634,
      "eval_loss": NaN,
      "eval_runtime": 172.369,
      "eval_samples_per_second": 8.644,
      "eval_steps_per_second": 4.322,
      "step": 20
    },
    {
      "epoch": 0.0059342988343341575,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.006782055810667609,
      "grad_norm": NaN,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.007064641469445425,
      "eval_loss": NaN,
      "eval_runtime": 172.3518,
      "eval_samples_per_second": 8.645,
      "eval_steps_per_second": 4.323,
      "step": 25
    },
    {
      "epoch": 0.0076298127870010595,
      "grad_norm": NaN,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.008477569763334511,
      "grad_norm": NaN,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.008477569763334511,
      "eval_loss": NaN,
      "eval_runtime": 172.3614,
      "eval_samples_per_second": 8.645,
      "eval_steps_per_second": 4.322,
      "step": 30
    },
    {
      "epoch": 0.009325326739667962,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 33
    }
  ],
  "logging_steps": 3,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1606739149389824e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}