{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007778317938745746,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.778317938745747e-05,
      "eval_loss": 4.1108784675598145,
      "eval_runtime": 313.3219,
      "eval_samples_per_second": 17.279,
      "eval_steps_per_second": 8.64,
      "step": 1
    },
    {
      "epoch": 0.00023334953816237238,
      "grad_norm": 2.194282054901123,
      "learning_rate": 6e-05,
      "loss": 4.0209,
      "step": 3
    },
    {
      "epoch": 0.00046669907632474475,
      "grad_norm": 2.6679859161376953,
      "learning_rate": 0.00012,
      "loss": 3.8277,
      "step": 6
    },
    {
      "epoch": 0.0006222654350996597,
      "eval_loss": 3.1946327686309814,
      "eval_runtime": 312.5781,
      "eval_samples_per_second": 17.32,
      "eval_steps_per_second": 8.66,
      "step": 8
    },
    {
      "epoch": 0.0007000486144871172,
      "grad_norm": 3.270036458969116,
      "learning_rate": 0.00018,
      "loss": 3.4381,
      "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": 3709436417802240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}