{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1030,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 2.154229164123535,
      "learning_rate": 7.587548638132295e-05,
      "loss": 0.6104,
      "step": 250
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 1.9545427560806274,
      "learning_rate": 5.155642023346303e-05,
      "loss": 0.3677,
      "step": 500
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 2.771542549133301,
      "learning_rate": 2.7237354085603113e-05,
      "loss": 0.3307,
      "step": 750
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 2.780686140060425,
      "learning_rate": 2.9182879377431908e-06,
      "loss": 0.2978,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "step": 1030,
      "total_flos": 7.232215420241879e+17,
      "train_loss": 0.39821495037634397,
      "train_runtime": 29524.5328,
      "train_samples_per_second": 8.931,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 250,
  "max_steps": 1030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.232215420241879e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}