{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3125,
  "eval_steps": 10,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0625,
      "grad_norm": NaN,
      "learning_rate": 0.00017600000000000002,
      "loss": 5.3433,
      "step": 5
    },
    {
      "epoch": 0.125,
      "grad_norm": 22.1121883392334,
      "learning_rate": 0.00016,
      "loss": 0.8498,
      "step": 10
    },
    {
      "epoch": 0.125,
      "eval_loss": 0.46461257338523865,
      "eval_runtime": 675.933,
      "eval_samples_per_second": 0.473,
      "eval_steps_per_second": 0.237,
      "step": 10
    },
    {
      "epoch": 0.1875,
      "grad_norm": 5.5990471839904785,
      "learning_rate": 0.00012,
      "loss": 0.2796,
      "step": 15
    },
    {
      "epoch": 0.25,
      "grad_norm": 4.6768269538879395,
      "learning_rate": 8e-05,
      "loss": 0.0708,
      "step": 20
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.06857629865407944,
      "eval_runtime": 677.5709,
      "eval_samples_per_second": 0.472,
      "eval_steps_per_second": 0.236,
      "step": 20
    },
    {
      "epoch": 0.3125,
      "grad_norm": 1.486285924911499,
      "learning_rate": 4e-05,
      "loss": 0.0593,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1937423719150656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}