{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008513989549077829,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017027979098155658,
      "grad_norm": 0.04402392730116844,
      "learning_rate": 1e-05,
      "loss": 10.3868,
      "step": 1
    },
    {
      "epoch": 0.00017027979098155658,
      "eval_loss": 10.380681991577148,
      "eval_runtime": 75.7645,
      "eval_samples_per_second": 130.549,
      "eval_steps_per_second": 65.281,
      "step": 1
    },
    {
      "epoch": 0.00034055958196311316,
      "grad_norm": 0.05084071680903435,
      "learning_rate": 2e-05,
      "loss": 10.3833,
      "step": 2
    },
    {
      "epoch": 0.00034055958196311316,
      "eval_loss": 10.380674362182617,
      "eval_runtime": 49.9795,
      "eval_samples_per_second": 197.901,
      "eval_steps_per_second": 98.961,
      "step": 2
    },
    {
      "epoch": 0.0005108393729446697,
      "grad_norm": 0.051581379026174545,
      "learning_rate": 3e-05,
      "loss": 10.3842,
      "step": 3
    },
    {
      "epoch": 0.0006811191639262263,
      "grad_norm": 0.053208209574222565,
      "learning_rate": 4e-05,
      "loss": 10.3688,
      "step": 4
    },
    {
      "epoch": 0.0006811191639262263,
      "eval_loss": 10.380619049072266,
      "eval_runtime": 50.1064,
      "eval_samples_per_second": 197.4,
      "eval_steps_per_second": 98.71,
      "step": 4
    },
    {
      "epoch": 0.0008513989549077829,
      "grad_norm": 0.045814722776412964,
      "learning_rate": 5e-05,
      "loss": 10.3795,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 452581785600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}