{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010279840091376356,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001142204454597373,
      "grad_norm": 4.046668982482515e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.001142204454597373,
      "eval_loss": 11.5,
      "eval_runtime": 16.5645,
      "eval_samples_per_second": 22.277,
      "eval_steps_per_second": 11.168,
      "step": 1
    },
    {
      "epoch": 0.002284408909194746,
      "grad_norm": 3.402375659788959e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0034266133637921186,
      "grad_norm": 5.209252776694484e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0034266133637921186,
      "eval_loss": 11.5,
      "eval_runtime": 14.5053,
      "eval_samples_per_second": 25.439,
      "eval_steps_per_second": 12.754,
      "step": 3
    },
    {
      "epoch": 0.004568817818389492,
      "grad_norm": 4.771175736095756e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0057110222729868645,
      "grad_norm": 5.1080482080578804e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.006853226727584237,
      "grad_norm": 3.507751534925774e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.006853226727584237,
      "eval_loss": 11.5,
      "eval_runtime": 13.4501,
      "eval_samples_per_second": 27.435,
      "eval_steps_per_second": 13.755,
      "step": 6
    },
    {
      "epoch": 0.00799543118218161,
      "grad_norm": 4.689860361395404e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.009137635636778984,
      "grad_norm": 6.249466969165951e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.010279840091376356,
      "grad_norm": 4.8370591684943065e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.010279840091376356,
      "eval_loss": 11.5,
      "eval_runtime": 13.5098,
      "eval_samples_per_second": 27.313,
      "eval_steps_per_second": 13.694,
      "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": 204209504256.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}