{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00025529199021380705,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.509733007126901e-05,
      "grad_norm": 1.3362045288085938,
      "learning_rate": 2e-05,
      "loss": 2.3186,
      "step": 1
    },
    {
      "epoch": 8.509733007126901e-05,
      "eval_loss": 2.56070876121521,
      "eval_runtime": 244.3553,
      "eval_samples_per_second": 20.249,
      "eval_steps_per_second": 10.125,
      "step": 1
    },
    {
      "epoch": 0.00017019466014253802,
      "grad_norm": 1.5068103075027466,
      "learning_rate": 4e-05,
      "loss": 2.3577,
      "step": 2
    },
    {
      "epoch": 0.00025529199021380705,
      "grad_norm": 1.5330816507339478,
      "learning_rate": 6e-05,
      "loss": 2.5584,
      "step": 3
    },
    {
      "epoch": 0.00025529199021380705,
      "eval_loss": 2.552053451538086,
      "eval_runtime": 243.6642,
      "eval_samples_per_second": 20.307,
      "eval_steps_per_second": 10.153,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 949861629296640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}