{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2,
  "eval_steps": 50,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 0.9417065382003784,
      "learning_rate": 1e-05,
      "loss": 1.1501,
      "step": 1
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.9725092649459839,
      "eval_runtime": 0.0753,
      "eval_samples_per_second": 53.114,
      "eval_steps_per_second": 13.279,
      "step": 1
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9147453308105469,
      "learning_rate": 2e-05,
      "loss": 1.0762,
      "step": 2
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.9406640529632568,
      "learning_rate": 3e-05,
      "loss": 1.7364,
      "step": 3
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.8447690606117249,
      "learning_rate": 4e-05,
      "loss": 1.0243,
      "step": 4
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2929211854934692,
      "learning_rate": 5e-05,
      "loss": 1.4478,
      "step": 5
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8074672222137451,
      "learning_rate": 6e-05,
      "loss": 1.0367,
      "step": 6
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.8978586792945862,
      "learning_rate": 7e-05,
      "loss": 1.0725,
      "step": 7
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.5650267601013184,
      "learning_rate": 8e-05,
      "loss": 1.4492,
      "step": 8
    }
  ],
  "logging_steps": 1,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 898436082696192.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}