{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10526315789473684,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 32.785560607910156,
      "learning_rate": 2e-05,
      "loss": 5.8338,
      "step": 1
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 5.785942554473877,
      "eval_runtime": 1.252,
      "eval_samples_per_second": 31.948,
      "eval_steps_per_second": 15.974,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 40.869415283203125,
      "learning_rate": 4e-05,
      "loss": 5.5921,
      "step": 2
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 21.129074096679688,
      "learning_rate": 6e-05,
      "loss": 5.4732,
      "step": 3
    },
    {
      "epoch": 0.031578947368421054,
      "eval_loss": 5.616696357727051,
      "eval_runtime": 0.7521,
      "eval_samples_per_second": 53.183,
      "eval_steps_per_second": 26.592,
      "step": 3
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 17.495750427246094,
      "learning_rate": 8e-05,
      "loss": 5.7311,
      "step": 4
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 8.690570831298828,
      "learning_rate": 0.0001,
      "loss": 5.3653,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 6.743778228759766,
      "learning_rate": 0.00012,
      "loss": 5.3032,
      "step": 6
    },
    {
      "epoch": 0.06315789473684211,
      "eval_loss": 5.205367088317871,
      "eval_runtime": 0.7629,
      "eval_samples_per_second": 52.433,
      "eval_steps_per_second": 26.217,
      "step": 6
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": 5.707422733306885,
      "learning_rate": 0.00014,
      "loss": 4.6758,
      "step": 7
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 6.963839530944824,
      "learning_rate": 0.00016,
      "loss": 4.4671,
      "step": 8
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 7.433150291442871,
      "learning_rate": 0.00018,
      "loss": 4.3537,
      "step": 9
    },
    {
      "epoch": 0.09473684210526316,
      "eval_loss": 4.387659549713135,
      "eval_runtime": 0.7423,
      "eval_samples_per_second": 53.887,
      "eval_steps_per_second": 26.943,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 8.091924667358398,
      "learning_rate": 0.0002,
      "loss": 4.3559,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}