{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016256197675363732,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003251239535072746,
      "grad_norm": 0.021640103310346603,
      "learning_rate": 1e-05,
      "loss": 11.7645,
      "step": 1
    },
    {
      "epoch": 0.0003251239535072746,
      "eval_loss": 11.76447582244873,
      "eval_runtime": 249.3031,
      "eval_samples_per_second": 41.56,
      "eval_steps_per_second": 20.782,
      "step": 1
    },
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": 0.024706723168492317,
      "learning_rate": 2e-05,
      "loss": 11.7658,
      "step": 2
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 0.022929754108190536,
      "learning_rate": 3e-05,
      "loss": 11.7649,
      "step": 3
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": 0.022171195596456528,
      "learning_rate": 4e-05,
      "loss": 11.7648,
      "step": 4
    },
    {
      "epoch": 0.0016256197675363732,
      "grad_norm": 0.02208411693572998,
      "learning_rate": 5e-05,
      "loss": 11.7649,
      "step": 5
    },
    {
      "epoch": 0.0016256197675363732,
      "eval_loss": 11.764402389526367,
      "eval_runtime": 249.1579,
      "eval_samples_per_second": 41.584,
      "eval_steps_per_second": 20.794,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 16296003502080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}