{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 2.067296788002129,
      "learning_rate": 0.0,
      "loss": 0.866,
      "step": 1
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.290485750060095,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.043,
      "step": 2
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.8761831403153433,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9406,
      "step": 3
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.5348726385452636,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.9753,
      "step": 4
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.451336617862282,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.9902,
      "step": 5
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3.321340013917274,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.9761,
      "step": 6
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 2.813148280382836,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.9736,
      "step": 7
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.5924965375006837,
      "learning_rate": 5e-05,
      "loss": 0.9838,
      "step": 8
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.5690611350244767,
      "learning_rate": 4.9993025930300686e-05,
      "loss": 0.9958,
      "step": 9
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.3166502579359358,
      "learning_rate": 4.99721076122146e-05,
      "loss": 0.9588,
      "step": 10
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 1.136691779583638,
      "learning_rate": 4.9937256716606394e-05,
      "loss": 0.8503,
      "step": 11
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.8350469358137226,
      "learning_rate": 4.9888492687682096e-05,
      "loss": 0.8724,
      "step": 12
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.7872759895415901,
      "learning_rate": 4.982584273214061e-05,
      "loss": 0.9391,
      "step": 13
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7631657638189762,
      "learning_rate": 4.9749341803994465e-05,
      "loss": 0.8446,
      "step": 14
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.6807894928709346,
      "learning_rate": 4.965903258506806e-05,
      "loss": 0.8727,
      "step": 15
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5683155258085846,
      "learning_rate": 4.955496546118439e-05,
      "loss": 0.8189,
      "step": 16
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.7801939464768173,
      "learning_rate": 4.9437198494053464e-05,
      "loss": 0.9303,
      "step": 17
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.5867664533954665,
      "learning_rate": 4.9305797388878264e-05,
      "loss": 0.83,
      "step": 18
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5567512617299766,
      "learning_rate": 4.916083545769607e-05,
      "loss": 0.8938,
      "step": 19
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.5135799351938194,
      "learning_rate": 4.9002393578475816e-05,
      "loss": 0.8907,
      "step": 20
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5604879970565443,
      "learning_rate": 4.883056014999423e-05,
      "loss": 0.8582,
      "step": 21
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5008974828940795,
      "learning_rate": 4.864543104251587e-05,
      "loss": 0.8132,
      "step": 22
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5351207184045396,
      "learning_rate": 4.8447109544304636e-05,
      "loss": 0.8775,
      "step": 23
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.48534815393327974,
      "learning_rate": 4.823570630399665e-05,
      "loss": 0.8478,
      "step": 24
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.4766396695563186,
      "learning_rate": 4.8011339268866505e-05,
      "loss": 0.8363,
      "step": 25
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.4856803005330466,
      "learning_rate": 4.7774133619021514e-05,
      "loss": 0.9035,
      "step": 26
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.3964013618666619,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.8033,
      "step": 27
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.48912255110703906,
      "learning_rate": 4.726174293673612e-05,
      "loss": 0.8316,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.48912255110703906,
      "learning_rate": 4.698684378016222e-05,
      "loss": 0.6913,
      "step": 29
    }
  ],
  "logging_steps": 1,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 12946871943168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}