{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 28,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3,
      "grad_norm": 1.747356920204807,
      "learning_rate": 3.9842294026289565e-05,
      "loss": 0.3412,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09391019493341446,
      "step": 5,
      "valid_targets_mean": 3636.6,
      "valid_targets_min": 1952
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.4706659924028225,
      "learning_rate": 3.457937254842823e-05,
      "loss": 0.226,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06339341402053833,
      "step": 10,
      "valid_targets_mean": 3708.0,
      "valid_targets_min": 2033
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.32375316387744746,
      "learning_rate": 2.37476262917145e-05,
      "loss": 0.1983,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05972842872142792,
      "step": 15,
      "valid_targets_mean": 3235.0,
      "valid_targets_min": 2033
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.34711114728029047,
      "learning_rate": 1.1484414168698547e-05,
      "loss": 0.1689,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.16862362623214722,
      "step": 20,
      "valid_targets_mean": 3472.8,
      "valid_targets_min": 1998
    },
    {
      "epoch": 6.3,
      "grad_norm": 0.1946364478726383,
      "learning_rate": 2.473866399122733e-06,
      "loss": 0.1586,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.055688951164484024,
      "step": 25,
      "valid_targets_mean": 4292.8,
      "valid_targets_min": 1959
    },
    {
      "epoch": 7.0,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.15134340524673462,
      "step": 28,
      "total_flos": 2.721300459238195e+16,
      "train_loss": 0.20857684739998408,
      "train_runtime": 313.206,
      "train_samples_per_second": 7.062,
      "train_steps_per_second": 0.089,
      "valid_targets_mean": 3738.5,
      "valid_targets_min": 1858
    }
  ],
  "logging_steps": 5,
  "max_steps": 28,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.721300459238195e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}