{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04296455424274973,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.908679485321045,
      "eval_runtime": 61.0681,
      "eval_samples_per_second": 8.024,
      "eval_steps_per_second": 4.012,
      "step": 1
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 1.2413489818572998,
      "learning_rate": 5e-05,
      "loss": 2.9302,
      "step": 5
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 1.5586470365524292,
      "learning_rate": 0.0001,
      "loss": 2.6251,
      "step": 10
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 2.641623020172119,
      "eval_runtime": 61.5877,
      "eval_samples_per_second": 7.956,
      "eval_steps_per_second": 3.978,
      "step": 10
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 1.4996484518051147,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.5685,
      "step": 15
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 1.6058354377746582,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4174,
      "step": 20
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 2.3582465648651123,
      "eval_runtime": 61.7493,
      "eval_samples_per_second": 7.935,
      "eval_steps_per_second": 3.968,
      "step": 20
    },
    {
      "epoch": 0.021482277121374866,
      "grad_norm": 1.398178219795227,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2547,
      "step": 25
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 1.3723353147506714,
      "learning_rate": 5e-05,
      "loss": 2.2388,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 2.2458176612854004,
      "eval_runtime": 60.4579,
      "eval_samples_per_second": 8.105,
      "eval_steps_per_second": 4.052,
      "step": 30
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 1.2066928148269653,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.3131,
      "step": 35
    },
    {
      "epoch": 0.034371643394199784,
      "grad_norm": 1.3476109504699707,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.1465,
      "step": 40
    },
    {
      "epoch": 0.034371643394199784,
      "eval_loss": 2.2001399993896484,
      "eval_runtime": 61.4364,
      "eval_samples_per_second": 7.976,
      "eval_steps_per_second": 3.988,
      "step": 40
    },
    {
      "epoch": 0.03866809881847476,
      "grad_norm": 1.0822781324386597,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2524,
      "step": 45
    },
    {
      "epoch": 0.04296455424274973,
      "grad_norm": 1.0575940608978271,
      "learning_rate": 0.0,
      "loss": 2.0986,
      "step": 50
    },
    {
      "epoch": 0.04296455424274973,
      "eval_loss": 2.1926662921905518,
      "eval_runtime": 61.8764,
      "eval_samples_per_second": 7.919,
      "eval_steps_per_second": 3.96,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}