{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3185840707964602,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008849557522123894,
      "eval_loss": NaN,
      "eval_runtime": 5.7459,
      "eval_samples_per_second": 33.067,
      "eval_steps_per_second": 4.177,
      "step": 1
    },
    {
      "epoch": 0.02654867256637168,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.07964601769911504,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.07964601769911504,
      "eval_loss": NaN,
      "eval_runtime": 5.2422,
      "eval_samples_per_second": 36.244,
      "eval_steps_per_second": 4.578,
      "step": 9
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.1592920353982301,
      "eval_loss": NaN,
      "eval_runtime": 5.2369,
      "eval_samples_per_second": 36.281,
      "eval_steps_per_second": 4.583,
      "step": 18
    },
    {
      "epoch": 0.18584070796460178,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.23893805309734514,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.23893805309734514,
      "eval_loss": NaN,
      "eval_runtime": 5.2467,
      "eval_samples_per_second": 36.213,
      "eval_steps_per_second": 4.574,
      "step": 27
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.2920353982300885,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.3185840707964602,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.3185840707964602,
      "eval_loss": NaN,
      "eval_runtime": 5.252,
      "eval_samples_per_second": 36.177,
      "eval_steps_per_second": 4.57,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9797210304675840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}