{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988041138483617,
  "eval_steps": 500,
  "global_step": 522,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09567089213106912,
      "grad_norm": 19.851242065429688,
      "learning_rate": 0.00011666666666666667,
      "loss": 121.1525,
      "step": 50
    },
    {
      "epoch": 0.19134178426213824,
      "grad_norm": 13.892197608947754,
      "learning_rate": 0.00023333333333333333,
      "loss": 77.1477,
      "step": 100
    },
    {
      "epoch": 0.2870126763932074,
      "grad_norm": 12.60777759552002,
      "learning_rate": 0.00035,
      "loss": 64.8839,
      "step": 150
    },
    {
      "epoch": 0.3826835685242765,
      "grad_norm": 8.890196800231934,
      "learning_rate": 0.00046666666666666666,
      "loss": 59.8849,
      "step": 200
    },
    {
      "epoch": 0.4783544606553456,
      "grad_norm": 8.705379486083984,
      "learning_rate": 0.0005833333333333334,
      "loss": 57.5299,
      "step": 250
    },
    {
      "epoch": 0.5740253527864148,
      "grad_norm": 7.457199573516846,
      "learning_rate": 0.0007,
      "loss": 56.2806,
      "step": 300
    },
    {
      "epoch": 0.6696962449174838,
      "grad_norm": 7.943981647491455,
      "learning_rate": 0.000699821634561209,
      "loss": 55.3251,
      "step": 350
    },
    {
      "epoch": 0.765367137048553,
      "grad_norm": 7.716305732727051,
      "learning_rate": 0.0006992867200404345,
      "loss": 52.4636,
      "step": 400
    },
    {
      "epoch": 0.8610380291796221,
      "grad_norm": 7.123641014099121,
      "learning_rate": 0.0006983958016391807,
      "loss": 52.215,
      "step": 450
    },
    {
      "epoch": 0.9567089213106912,
      "grad_norm": 7.223691463470459,
      "learning_rate": 0.0006971497874091708,
      "loss": 52.1157,
      "step": 500
    },
    {
      "epoch": 0.9988041138483617,
      "eval_accuracy": 0.0,
      "eval_loss": 8.116789817810059,
      "eval_normalizer": 685885.0,
      "eval_runtime": 103.9352,
      "eval_samples_per_second": 514.33,
      "eval_steps_per_second": 1.01,
      "step": 522
    }
  ],
  "logging_steps": 50,
  "max_steps": 5220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1.3082708964409344e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}