{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01594896331738437,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001594896331738437,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 2.3784,
      "step": 1
    },
    {
      "epoch": 0.003189792663476874,
      "grad_norm": 5.191591739654541,
      "learning_rate": 0.0001,
      "loss": 1.4108,
      "step": 2
    },
    {
      "epoch": 0.004784688995215311,
      "grad_norm": 6.275367736816406,
      "learning_rate": 0.0002,
      "loss": 2.2442,
      "step": 3
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 5.685720443725586,
      "learning_rate": 0.000175,
      "loss": 1.8482,
      "step": 4
    },
    {
      "epoch": 0.007974481658692184,
      "grad_norm": 7.7756123542785645,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.0434,
      "step": 5
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 6.795759201049805,
      "learning_rate": 0.000125,
      "loss": 2.1721,
      "step": 6
    },
    {
      "epoch": 0.011164274322169059,
      "grad_norm": 6.884849548339844,
      "learning_rate": 0.0001,
      "loss": 2.1884,
      "step": 7
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 8.31216812133789,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4185,
      "step": 8
    },
    {
      "epoch": 0.014354066985645933,
      "grad_norm": 4.969106197357178,
      "learning_rate": 5e-05,
      "loss": 2.7419,
      "step": 9
    },
    {
      "epoch": 0.01594896331738437,
      "grad_norm": 10.967009544372559,
      "learning_rate": 2.5e-05,
      "loss": 2.1652,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 64947247349760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}