{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013777267508610792,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015308075009567547,
      "grad_norm": 0.029666228219866753,
      "learning_rate": 2e-05,
      "loss": 11.9389,
      "step": 1
    },
    {
      "epoch": 0.0030616150019135095,
      "grad_norm": 0.03394440561532974,
      "learning_rate": 4e-05,
      "loss": 11.9343,
      "step": 2
    },
    {
      "epoch": 0.004592422502870264,
      "grad_norm": 0.04432697221636772,
      "learning_rate": 6e-05,
      "loss": 11.9331,
      "step": 3
    },
    {
      "epoch": 0.004592422502870264,
      "eval_loss": 11.93177604675293,
      "eval_runtime": 7.0014,
      "eval_samples_per_second": 39.278,
      "eval_steps_per_second": 19.71,
      "step": 3
    },
    {
      "epoch": 0.006123230003827019,
      "grad_norm": 0.027879079803824425,
      "learning_rate": 8e-05,
      "loss": 11.9339,
      "step": 4
    },
    {
      "epoch": 0.007654037504783774,
      "grad_norm": 0.03863644227385521,
      "learning_rate": 0.0001,
      "loss": 11.9279,
      "step": 5
    },
    {
      "epoch": 0.009184845005740528,
      "grad_norm": 0.017864998430013657,
      "learning_rate": 0.00012,
      "loss": 11.9245,
      "step": 6
    },
    {
      "epoch": 0.009184845005740528,
      "eval_loss": 11.931724548339844,
      "eval_runtime": 7.1078,
      "eval_samples_per_second": 38.69,
      "eval_steps_per_second": 19.415,
      "step": 6
    },
    {
      "epoch": 0.010715652506697282,
      "grad_norm": 0.038272857666015625,
      "learning_rate": 0.00014,
      "loss": 11.9285,
      "step": 7
    },
    {
      "epoch": 0.012246460007654038,
      "grad_norm": 0.028404386714100838,
      "learning_rate": 0.00016,
      "loss": 11.9387,
      "step": 8
    },
    {
      "epoch": 0.013777267508610792,
      "grad_norm": 0.04053066298365593,
      "learning_rate": 0.00018,
      "loss": 11.9364,
      "step": 9
    },
    {
      "epoch": 0.013777267508610792,
      "eval_loss": 11.931608200073242,
      "eval_runtime": 7.8922,
      "eval_samples_per_second": 34.844,
      "eval_steps_per_second": 17.486,
      "step": 9
    }
  ],
  "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": 1063452672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}