{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06345848757271286,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021152829190904283,
      "eval_loss": NaN,
      "eval_runtime": 33.9065,
      "eval_samples_per_second": 5.869,
      "eval_steps_per_second": 2.949,
      "step": 1
    },
    {
      "epoch": 0.006345848757271285,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.010576414595452142,
      "eval_loss": NaN,
      "eval_runtime": 33.4367,
      "eval_samples_per_second": 5.952,
      "eval_steps_per_second": 2.991,
      "step": 5
    },
    {
      "epoch": 0.01269169751454257,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.019037546271813855,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.021152829190904283,
      "eval_loss": NaN,
      "eval_runtime": 33.3812,
      "eval_samples_per_second": 5.961,
      "eval_steps_per_second": 2.996,
      "step": 10
    },
    {
      "epoch": 0.02538339502908514,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.03172924378635643,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03172924378635643,
      "eval_loss": NaN,
      "eval_runtime": 33.3669,
      "eval_samples_per_second": 5.964,
      "eval_steps_per_second": 2.997,
      "step": 15
    },
    {
      "epoch": 0.03807509254362771,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04230565838180857,
      "eval_loss": NaN,
      "eval_runtime": 33.2953,
      "eval_samples_per_second": 5.977,
      "eval_steps_per_second": 3.003,
      "step": 20
    },
    {
      "epoch": 0.044420941300899,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.05076679005817028,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05288207297726071,
      "eval_loss": NaN,
      "eval_runtime": 33.3598,
      "eval_samples_per_second": 5.965,
      "eval_steps_per_second": 2.998,
      "step": 25
    },
    {
      "epoch": 0.05711263881544157,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.06345848757271286,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.06345848757271286,
      "eval_loss": NaN,
      "eval_runtime": 33.407,
      "eval_samples_per_second": 5.957,
      "eval_steps_per_second": 2.993,
      "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": 9801969665310720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}