{
  "best_global_step": 1176,
  "best_metric": 5.884053707122803,
  "best_model_checkpoint": null,
  "epoch": 3.826530612244898,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002551020408163265,
      "grad_norm": 16.32339096069336,
      "learning_rate": 0.0,
      "loss": 10.3351,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6908162236213684,
      "learning_rate": 7.82e-05,
      "loss": 7.1094,
      "step": 392
    },
    {
      "epoch": 1.0,
      "eval_loss": 6.317445755004883,
      "eval_runtime": 15.5824,
      "eval_samples_per_second": 1616.887,
      "eval_steps_per_second": 6.353,
      "step": 392
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7368313074111938,
      "learning_rate": 9.613387978142077e-05,
      "loss": 6.0963,
      "step": 784
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.024065017700195,
      "eval_runtime": 15.5591,
      "eval_samples_per_second": 1619.314,
      "eval_steps_per_second": 6.363,
      "step": 784
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7423638701438904,
      "learning_rate": 9.077868852459017e-05,
      "loss": 5.8833,
      "step": 1176
    },
    {
      "epoch": 3.0,
      "eval_loss": 5.884053707122803,
      "eval_runtime": 15.6179,
      "eval_samples_per_second": 1613.212,
      "eval_steps_per_second": 6.339,
      "step": 1176
    }
  ],
  "logging_steps": 500,
  "max_steps": 7840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.506149863424e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}