{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 8.25,
      "learning_rate": 9.423076923076923e-06,
      "loss": 2.2032,
      "step": 10
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 6.71875,
      "learning_rate": 8.782051282051283e-06,
      "loss": 1.3422,
      "step": 20
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 7.46875,
      "learning_rate": 8.141025641025641e-06,
      "loss": 1.2337,
      "step": 30
    },
    {
      "epoch": 1.025974025974026,
      "grad_norm": 6.8125,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1902,
      "step": 40
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 7.15625,
      "learning_rate": 6.858974358974359e-06,
      "loss": 1.0812,
      "step": 50
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 7.96875,
      "learning_rate": 6.217948717948718e-06,
      "loss": 1.0337,
      "step": 60
    },
    {
      "epoch": 1.8051948051948052,
      "grad_norm": 9.125,
      "learning_rate": 5.576923076923077e-06,
      "loss": 1.0404,
      "step": 70
    },
    {
      "epoch": 2.051948051948052,
      "grad_norm": 10.75,
      "learning_rate": 4.935897435897436e-06,
      "loss": 1.0258,
      "step": 80
    },
    {
      "epoch": 2.311688311688312,
      "grad_norm": 12.375,
      "learning_rate": 4.294871794871795e-06,
      "loss": 0.9748,
      "step": 90
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 13.9375,
      "learning_rate": 3.653846153846154e-06,
      "loss": 0.905,
      "step": 100
    },
    {
      "epoch": 2.8311688311688314,
      "grad_norm": 11.625,
      "learning_rate": 3.012820512820513e-06,
      "loss": 0.9027,
      "step": 110
    },
    {
      "epoch": 3.0779220779220777,
      "grad_norm": 10.6875,
      "learning_rate": 2.371794871794872e-06,
      "loss": 0.881,
      "step": 120
    },
    {
      "epoch": 3.3376623376623376,
      "grad_norm": 9.3125,
      "learning_rate": 1.7307692307692308e-06,
      "loss": 0.8781,
      "step": 130
    },
    {
      "epoch": 3.5974025974025974,
      "grad_norm": 8.875,
      "learning_rate": 1.0897435897435899e-06,
      "loss": 0.8626,
      "step": 140
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 8.75,
      "learning_rate": 4.4871794871794876e-07,
      "loss": 0.8874,
      "step": 150
    },
    {
      "epoch": 4.0,
      "step": 156,
      "total_flos": 2.1336249058983936e+16,
      "train_loss": 1.0869835859689958,
      "train_runtime": 267.2631,
      "train_samples_per_second": 9.279,
      "train_steps_per_second": 0.584
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 38,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1336249058983936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}