{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.923076923076923,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 1.4702763557434082,
      "learning_rate": 0.00018333333333333334,
      "loss": 9.483,
      "step": 2
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 2.237931966781616,
      "learning_rate": 0.0001666666666666667,
      "loss": 8.8833,
      "step": 4
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 2.2123219966888428,
      "learning_rate": 0.00015000000000000001,
      "loss": 8.119,
      "step": 6
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 2.0387604236602783,
      "learning_rate": 0.00013333333333333334,
      "loss": 7.6202,
      "step": 8
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 1.8973811864852905,
      "learning_rate": 0.00011666666666666668,
      "loss": 6.9965,
      "step": 10
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.8106874227523804,
      "learning_rate": 0.0001,
      "loss": 6.8357,
      "step": 12
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 1.7481627464294434,
      "learning_rate": 8.333333333333334e-05,
      "loss": 6.7018,
      "step": 14
    },
    {
      "epoch": 3.282051282051282,
      "grad_norm": 0.9489405155181885,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.7105,
      "step": 16
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 1.1118030548095703,
      "learning_rate": 5e-05,
      "loss": 6.4967,
      "step": 18
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 1.162569522857666,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.6138,
      "step": 20
    },
    {
      "epoch": 4.512820512820513,
      "grad_norm": 1.045633316040039,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 6.4841,
      "step": 22
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.8710927367210388,
      "learning_rate": 0.0,
      "loss": 6.5578,
      "step": 24
    },
    {
      "epoch": 4.923076923076923,
      "step": 24,
      "total_flos": 147993926084196.0,
      "train_loss": 7.291865587234497,
      "train_runtime": 97.928,
      "train_samples_per_second": 4.718,
      "train_steps_per_second": 0.245
    }
  ],
  "logging_steps": 2,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 147993926084196.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}