{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00046835665359171006,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6835665359171006e-05,
      "eval_loss": 1.7034660577774048,
      "eval_runtime": 1190.3593,
      "eval_samples_per_second": 7.552,
      "eval_steps_per_second": 3.776,
      "step": 1
    },
    {
      "epoch": 0.00014050699607751302,
      "grad_norm": 2.799278974533081,
      "learning_rate": 3e-05,
      "loss": 1.7239,
      "step": 3
    },
    {
      "epoch": 0.00028101399215502604,
      "grad_norm": 1.3826738595962524,
      "learning_rate": 6e-05,
      "loss": 1.3739,
      "step": 6
    },
    {
      "epoch": 0.00037468532287336805,
      "eval_loss": 1.3278619050979614,
      "eval_runtime": 1196.3758,
      "eval_samples_per_second": 7.514,
      "eval_steps_per_second": 3.757,
      "step": 8
    },
    {
      "epoch": 0.0004215209882325391,
      "grad_norm": 1.2530328035354614,
      "learning_rate": 9e-05,
      "loss": 1.411,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3802172328247296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}