{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.3267529010772705,
      "learning_rate": 3.984759689788058e-05,
      "loss": 3.9964,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.26488664746284485,
      "learning_rate": 3.923287969397442e-05,
      "loss": 3.6742,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3106290102005005,
      "learning_rate": 3.816256236058198e-05,
      "loss": 3.333,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.2936558425426483,
      "learning_rate": 3.6664941776944834e-05,
      "loss": 3.1105,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.29774364829063416,
      "learning_rate": 3.477961179759822e-05,
      "loss": 2.8481,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2768242657184601,
      "learning_rate": 3.255641647634906e-05,
      "loss": 2.5763,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2946491863062528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}