{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0706401766004415,
  "eval_steps": 5,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017660044150110375,
      "grad_norm": 0.16865968704223633,
      "learning_rate": 0.0001,
      "loss": 0.0632,
      "step": 1
    },
    {
      "epoch": 0.03532008830022075,
      "grad_norm": 0.17272710800170898,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0663,
      "step": 2
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.07607847452163696,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0321,
      "step": 3
    },
    {
      "epoch": 0.0706401766004415,
      "grad_norm": 0.04925389587879181,
      "learning_rate": 0.0,
      "loss": 0.0232,
      "step": 4
    },
    {
      "epoch": 0.0706401766004415,
      "step": 4,
      "total_flos": 6231591865417728.0,
      "train_loss": 0.046210515312850475,
      "train_runtime": 123.7364,
      "train_samples_per_second": 1.034,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 1,
  "max_steps": 4,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6231591865417728.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}