{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 45.95256423950195,
      "learning_rate": 2.9998398686512352e-05,
      "loss": 1.5306,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 44.932003021240234,
      "learning_rate": 2.9840150521126656e-05,
      "loss": 1.5544,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 48.099021911621094,
      "learning_rate": 2.936400899862609e-05,
      "loss": 1.5323,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 29.961488723754883,
      "learning_rate": 2.8581723562397203e-05,
      "loss": 1.4654,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 39.670982360839844,
      "learning_rate": 2.7509967268348168e-05,
      "loss": 1.4692,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 25.670618057250977,
      "learning_rate": 2.617158274115673e-05,
      "loss": 1.5032,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 27.760440826416016,
      "learning_rate": 2.459509532338337e-05,
      "loss": 1.3045,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 28.674970626831055,
      "learning_rate": 2.2814105107318955e-05,
      "loss": 1.3333,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 23.12104034423828,
      "learning_rate": 2.086657080735234e-05,
      "loss": 1.2713,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 25.078445434570312,
      "learning_rate": 1.879400073587521e-05,
      "loss": 1.2217,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 31.621864318847656,
      "learning_rate": 1.664056812566812e-05,
      "loss": 1.2481,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 20.53476333618164,
      "learning_rate": 1.4452169654135116e-05,
      "loss": 1.1886,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 25.275989532470703,
      "learning_rate": 1.2275447235308454e-05,
      "loss": 1.3433,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 21.859668731689453,
      "learning_rate": 1.015679392842831e-05,
      "loss": 1.1479,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 20.691587448120117,
      "learning_rate": 8.141365150430423e-06,
      "loss": 1.2862,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 27.549251556396484,
      "learning_rate": 6.27211626663071e-06,
      "loss": 1.092,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 23.37948226928711,
      "learning_rate": 4.588887071690491e-06,
      "loss": 1.1193,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 28.8465518951416,
      "learning_rate": 3.12755267356119e-06,
      "loss": 1.054,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 25.067665100097656,
      "learning_rate": 1.9192588778428844e-06,
      "loss": 1.1021,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 20.678544998168945,
      "learning_rate": 9.897583690117813e-07,
      "loss": 0.9986,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 19.12417221069336,
      "learning_rate": 3.588618366610941e-07,
      "loss": 1.2002,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 18.664505004882812,
      "learning_rate": 4.0015745046725336e-08,
      "loss": 1.105,
      "step": 220
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 967989855780864.0,
      "train_loss": 1.2763203489887822,
      "train_runtime": 121.651,
      "train_samples_per_second": 29.001,
      "train_steps_per_second": 1.825
    }
  ],
  "logging_steps": 10,
  "max_steps": 222,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 967989855780864.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}