{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.46036983043044577,
  "eval_steps": 325,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09974679659326326,
      "grad_norm": 0.548096239566803,
      "learning_rate": 0.00019526257508294887,
      "loss": 1.5773,
      "step": 325
    },
    {
      "epoch": 0.09974679659326326,
      "eval_loss": 1.652037262916565,
      "eval_runtime": 27.5817,
      "eval_samples_per_second": 8.158,
      "eval_steps_per_second": 1.051,
      "step": 325
    },
    {
      "epoch": 0.1994935931865265,
      "grad_norm": 0.6027694940567017,
      "learning_rate": 0.000181218401572851,
      "loss": 1.5494,
      "step": 650
    },
    {
      "epoch": 0.1994935931865265,
      "eval_loss": 1.6099203824996948,
      "eval_runtime": 5.7955,
      "eval_samples_per_second": 38.823,
      "eval_steps_per_second": 5.004,
      "step": 650
    },
    {
      "epoch": 0.2992403897797898,
      "grad_norm": 0.6409096121788025,
      "learning_rate": 0.00015923854154608087,
      "loss": 1.494,
      "step": 975
    },
    {
      "epoch": 0.2992403897797898,
      "eval_loss": 1.578147292137146,
      "eval_runtime": 5.8035,
      "eval_samples_per_second": 38.77,
      "eval_steps_per_second": 4.997,
      "step": 975
    },
    {
      "epoch": 0.398987186373053,
      "grad_norm": 0.5925875902175903,
      "learning_rate": 0.0001314706028781311,
      "loss": 1.4572,
      "step": 1300
    },
    {
      "epoch": 0.398987186373053,
      "eval_loss": 1.547926664352417,
      "eval_runtime": 5.8134,
      "eval_samples_per_second": 38.704,
      "eval_steps_per_second": 4.988,
      "step": 1300
    }
  ],
  "logging_steps": 325,
  "max_steps": 3258,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.691221009176822e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}