{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008730193373783229,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.730193373783229e-05,
      "grad_norm": 1.5248113870620728,
      "learning_rate": 2e-05,
      "loss": 8.6163,
      "step": 1
    },
    {
      "epoch": 8.730193373783229e-05,
      "eval_loss": 8.479676246643066,
      "eval_runtime": 32.024,
      "eval_samples_per_second": 150.606,
      "eval_steps_per_second": 75.319,
      "step": 1
    },
    {
      "epoch": 0.00017460386747566458,
      "grad_norm": 1.4446749687194824,
      "learning_rate": 4e-05,
      "loss": 8.5946,
      "step": 2
    },
    {
      "epoch": 0.00026190580121349685,
      "grad_norm": 1.486629843711853,
      "learning_rate": 6e-05,
      "loss": 8.2674,
      "step": 3
    },
    {
      "epoch": 0.00026190580121349685,
      "eval_loss": 8.478435516357422,
      "eval_runtime": 32.1185,
      "eval_samples_per_second": 150.163,
      "eval_steps_per_second": 75.097,
      "step": 3
    },
    {
      "epoch": 0.00034920773495132916,
      "grad_norm": 2.169105291366577,
      "learning_rate": 8e-05,
      "loss": 8.7129,
      "step": 4
    },
    {
      "epoch": 0.00043650966868916146,
      "grad_norm": 1.6277025938034058,
      "learning_rate": 0.0001,
      "loss": 8.7438,
      "step": 5
    },
    {
      "epoch": 0.0005238116024269937,
      "grad_norm": 1.7406617403030396,
      "learning_rate": 0.00012,
      "loss": 8.6583,
      "step": 6
    },
    {
      "epoch": 0.0005238116024269937,
      "eval_loss": 8.45960807800293,
      "eval_runtime": 32.3275,
      "eval_samples_per_second": 149.192,
      "eval_steps_per_second": 74.611,
      "step": 6
    },
    {
      "epoch": 0.000611113536164826,
      "grad_norm": 1.5705560445785522,
      "learning_rate": 0.00014,
      "loss": 8.5559,
      "step": 7
    },
    {
      "epoch": 0.0006984154699026583,
      "grad_norm": 1.5385314226150513,
      "learning_rate": 0.00016,
      "loss": 8.2896,
      "step": 8
    },
    {
      "epoch": 0.0007857174036404906,
      "grad_norm": 1.3292315006256104,
      "learning_rate": 0.00018,
      "loss": 8.5572,
      "step": 9
    },
    {
      "epoch": 0.0007857174036404906,
      "eval_loss": 8.412742614746094,
      "eval_runtime": 32.4714,
      "eval_samples_per_second": 148.531,
      "eval_steps_per_second": 74.281,
      "step": 9
    },
    {
      "epoch": 0.0008730193373783229,
      "grad_norm": 1.6804113388061523,
      "learning_rate": 0.0002,
      "loss": 9.0054,
      "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": 655585443840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}