{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013044328977976825,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.3481096593256084e-05,
      "eval_loss": NaN,
      "eval_runtime": 1095.225,
      "eval_samples_per_second": 8.842,
      "eval_steps_per_second": 4.421,
      "step": 1
    },
    {
      "epoch": 0.00013044328977976824,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002174054829662804,
      "eval_loss": NaN,
      "eval_runtime": 1094.9154,
      "eval_samples_per_second": 8.845,
      "eval_steps_per_second": 4.422,
      "step": 5
    },
    {
      "epoch": 0.0002608865795595365,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00039132986933930475,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0004348109659325608,
      "eval_loss": NaN,
      "eval_runtime": 1096.8437,
      "eval_samples_per_second": 8.829,
      "eval_steps_per_second": 4.414,
      "step": 10
    },
    {
      "epoch": 0.000521773159119073,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0006522164488988412,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006522164488988412,
      "eval_loss": NaN,
      "eval_runtime": 1096.9132,
      "eval_samples_per_second": 8.828,
      "eval_steps_per_second": 4.414,
      "step": 15
    },
    {
      "epoch": 0.0007826597386786095,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0008696219318651216,
      "eval_loss": NaN,
      "eval_runtime": 1096.7895,
      "eval_samples_per_second": 8.829,
      "eval_steps_per_second": 4.415,
      "step": 20
    },
    {
      "epoch": 0.0009131030284583778,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.001043546318238146,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.001087027414831402,
      "eval_loss": NaN,
      "eval_runtime": 1096.9249,
      "eval_samples_per_second": 8.828,
      "eval_steps_per_second": 4.414,
      "step": 25
    },
    {
      "epoch": 0.0011739896080179143,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0013044328977976825,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0013044328977976825,
      "eval_loss": NaN,
      "eval_runtime": 1096.1934,
      "eval_samples_per_second": 8.834,
      "eval_steps_per_second": 4.417,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9888459569233920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}