{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0060779189205616,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000121558378411232,
      "eval_loss": 2.5203659534454346,
      "eval_runtime": 129.4621,
      "eval_samples_per_second": 26.757,
      "eval_steps_per_second": 13.378,
      "step": 1
    },
    {
      "epoch": 0.00121558378411232,
      "grad_norm": 1.6431328058242798,
      "learning_rate": 0.00019967573081342103,
      "loss": 9.3908,
      "step": 10
    },
    {
      "epoch": 0.00243116756822464,
      "grad_norm": 2.2140567302703857,
      "learning_rate": 0.0001970941817426052,
      "loss": 9.4789,
      "step": 20
    },
    {
      "epoch": 0.0036467513523369597,
      "grad_norm": 2.526764392852783,
      "learning_rate": 0.00019199794436588243,
      "loss": 9.2779,
      "step": 30
    },
    {
      "epoch": 0.00486233513644928,
      "grad_norm": 1.9266506433486938,
      "learning_rate": 0.0001845190085543795,
      "loss": 9.338,
      "step": 40
    },
    {
      "epoch": 0.0060779189205616,
      "grad_norm": 3.146573066711426,
      "learning_rate": 0.00017485107481711012,
      "loss": 9.01,
      "step": 50
    },
    {
      "epoch": 0.0060779189205616,
      "eval_loss": 2.222339153289795,
      "eval_runtime": 129.5944,
      "eval_samples_per_second": 26.73,
      "eval_steps_per_second": 13.365,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9283870679629824.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}