{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2966808826256258,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07417022065640645,
      "grad_norm": 1.151120901107788,
      "learning_rate": 0.0002,
      "loss": 3.5121,
      "step": 100
    },
    {
      "epoch": 0.1483404413128129,
      "grad_norm": 0.8146340250968933,
      "learning_rate": 0.00019684829181681234,
      "loss": 2.7779,
      "step": 200
    },
    {
      "epoch": 0.22251066196921937,
      "grad_norm": 0.7336196303367615,
      "learning_rate": 0.0001875918325566888,
      "loss": 2.6147,
      "step": 300
    },
    {
      "epoch": 0.2966808826256258,
      "grad_norm": 0.7540659308433533,
      "learning_rate": 0.00017281409538757883,
      "loss": 2.5387,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1348,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.548356111302656e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}