{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0711743772241993,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014234875444839857,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 3346.0093,
      "step": 1
    },
    {
      "epoch": 0.014234875444839857,
      "eval_loss": NaN,
      "eval_runtime": 69.0908,
      "eval_samples_per_second": 6.861,
      "eval_steps_per_second": 0.868,
      "step": 1
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 5441.3306,
      "step": 2
    },
    {
      "epoch": 0.042704626334519574,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 850.3894,
      "step": 3
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1138.0363,
      "step": 4
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 3671.7151,
      "step": 5
    },
    {
      "epoch": 0.0711743772241993,
      "eval_loss": NaN,
      "eval_runtime": 12.5954,
      "eval_samples_per_second": 37.633,
      "eval_steps_per_second": 4.764,
      "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": 2.561882493812736e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}