{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019422189851905802,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009711094925952901,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0009711094925952901,
      "eval_loss": NaN,
      "eval_runtime": 229.916,
      "eval_samples_per_second": 7.546,
      "eval_steps_per_second": 3.775,
      "step": 1
    },
    {
      "epoch": 0.0019422189851905803,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0029133284777858705,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0038844379703811605,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.004855547462976451,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 787.3378,
      "step": 5
    },
    {
      "epoch": 0.004855547462976451,
      "eval_loss": NaN,
      "eval_runtime": 74.9408,
      "eval_samples_per_second": 23.152,
      "eval_steps_per_second": 11.582,
      "step": 5
    },
    {
      "epoch": 0.005826656955571741,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006797766448167031,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.007768875940762321,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00873998543335761,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009711094925952901,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.009711094925952901,
      "eval_loss": NaN,
      "eval_runtime": 107.7404,
      "eval_samples_per_second": 16.104,
      "eval_steps_per_second": 8.056,
      "step": 10
    },
    {
      "epoch": 0.010682204418548192,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.011653313911143482,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5773,
      "step": 12
    },
    {
      "epoch": 0.01262442340373877,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.013595532896334061,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.014566642388929352,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.014566642388929352,
      "eval_loss": NaN,
      "eval_runtime": 66.431,
      "eval_samples_per_second": 26.117,
      "eval_steps_per_second": 13.066,
      "step": 15
    },
    {
      "epoch": 0.015537751881524642,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.016508861374119933,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.01747997086671522,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.018451080359310514,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3268,
      "step": 19
    },
    {
      "epoch": 0.019422189851905802,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.019422189851905802,
      "eval_loss": NaN,
      "eval_runtime": 66.4805,
      "eval_samples_per_second": 26.098,
      "eval_steps_per_second": 13.056,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.520031288098816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}