{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9927710843373494,
  "eval_steps": 200,
  "global_step": 103,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00963855421686747,
      "grad_norm": Infinity,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 3.4879,
      "step": 1
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": Infinity,
      "learning_rate": 9.090909090909091e-06,
      "loss": 3.4675,
      "step": 5
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": Infinity,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 3.4684,
      "step": 10
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": Infinity,
      "learning_rate": 1.9906859460363307e-05,
      "loss": 3.4408,
      "step": 15
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 77.93306732177734,
      "learning_rate": 1.953144766814161e-05,
      "loss": 3.2006,
      "step": 20
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 35.581451416015625,
      "learning_rate": 1.8878852184023754e-05,
      "loss": 2.8973,
      "step": 25
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 18.48872184753418,
      "learning_rate": 1.7968051114159046e-05,
      "loss": 2.3267,
      "step": 30
    },
    {
      "epoch": 0.3373493975903614,
      "grad_norm": 8.314779281616211,
      "learning_rate": 1.6825531432186545e-05,
      "loss": 2.1074,
      "step": 35
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 4.326565265655518,
      "learning_rate": 1.5484518712493188e-05,
      "loss": 1.9132,
      "step": 40
    },
    {
      "epoch": 0.43373493975903615,
      "grad_norm": 4.591472625732422,
      "learning_rate": 1.3984010898462417e-05,
      "loss": 1.819,
      "step": 45
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 4.667574405670166,
      "learning_rate": 1.2367644204664468e-05,
      "loss": 1.7638,
      "step": 50
    },
    {
      "epoch": 0.5301204819277109,
      "grad_norm": 3.1131222248077393,
      "learning_rate": 1.0682424133646712e-05,
      "loss": 1.7303,
      "step": 55
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 2.3192598819732666,
      "learning_rate": 8.977358510579658e-06,
      "loss": 1.6781,
      "step": 60
    },
    {
      "epoch": 0.6265060240963856,
      "grad_norm": 2.1515562534332275,
      "learning_rate": 7.3020322884297565e-06,
      "loss": 1.6642,
      "step": 65
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 2.2130627632141113,
      "learning_rate": 5.7051655696991825e-06,
      "loss": 1.6445,
      "step": 70
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 2.1814661026000977,
      "learning_rate": 4.2331967788513295e-06,
      "loss": 1.6173,
      "step": 75
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 2.0850536823272705,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 1.5971,
      "step": 80
    },
    {
      "epoch": 0.8192771084337349,
      "grad_norm": 2.2434961795806885,
      "learning_rate": 1.8303010698955803e-06,
      "loss": 1.5907,
      "step": 85
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 1.420127511024475,
      "learning_rate": 9.692526767546727e-07,
      "loss": 1.5897,
      "step": 90
    },
    {
      "epoch": 0.9156626506024096,
      "grad_norm": 1.3640261888504028,
      "learning_rate": 3.708271265220087e-07,
      "loss": 1.5803,
      "step": 95
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 1.352455496788025,
      "learning_rate": 5.2427211419051605e-08,
      "loss": 1.5745,
      "step": 100
    },
    {
      "epoch": 0.9927710843373494,
      "step": 103,
      "total_flos": 7.598970625641677e+16,
      "train_loss": 2.118080861360124,
      "train_runtime": 272.0741,
      "train_samples_per_second": 48.781,
      "train_steps_per_second": 0.379
    }
  ],
  "logging_steps": 5,
  "max_steps": 103,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.598970625641677e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}