{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 0,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 102.1269760131836,
      "learning_rate": 9.696969696969698e-06,
      "loss": 1.3339,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 32.059940338134766,
      "learning_rate": 9.393939393939396e-06,
      "loss": 0.8949,
      "step": 2
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 24.139785766601562,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.8498,
      "step": 3
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 4.718374729156494,
      "learning_rate": 8.787878787878788e-06,
      "loss": 0.6128,
      "step": 4
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 4.824295997619629,
      "learning_rate": 8.484848484848486e-06,
      "loss": 0.4623,
      "step": 5
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.600407361984253,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.3631,
      "step": 6
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.3101181983947754,
      "learning_rate": 7.87878787878788e-06,
      "loss": 0.2783,
      "step": 7
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.6703295707702637,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.2201,
      "step": 8
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.6509493589401245,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.1772,
      "step": 9
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.1594750881195068,
      "learning_rate": 6.969696969696971e-06,
      "loss": 0.15,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1056914329528809,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1294,
      "step": 11
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.7135591506958008,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.1173,
      "step": 12
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.8880245089530945,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.1027,
      "step": 13
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.7149422764778137,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 0.0999,
      "step": 14
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4583257734775543,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.0929,
      "step": 15
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.4339885115623474,
      "learning_rate": 5.151515151515152e-06,
      "loss": 0.0897,
      "step": 16
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.418163001537323,
      "learning_rate": 4.848484848484849e-06,
      "loss": 0.0882,
      "step": 17
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.3970937728881836,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.0862,
      "step": 18
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.300276517868042,
      "learning_rate": 4.242424242424243e-06,
      "loss": 0.0838,
      "step": 19
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.3120823800563812,
      "learning_rate": 3.93939393939394e-06,
      "loss": 0.0842,
      "step": 20
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.3221524953842163,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.0843,
      "step": 21
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2994186580181122,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0869,
      "step": 22
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.2431754171848297,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.08,
      "step": 23
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.3260601758956909,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.0792,
      "step": 24
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.25717467069625854,
      "learning_rate": 2.4242424242424244e-06,
      "loss": 0.0788,
      "step": 25
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.2379615604877472,
      "learning_rate": 2.1212121212121216e-06,
      "loss": 0.0792,
      "step": 26
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.22090616822242737,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.077,
      "step": 27
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.2328050285577774,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.0801,
      "step": 28
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.24620036780834198,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 0.0815,
      "step": 29
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.2227202206850052,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.0753,
      "step": 30
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.1897324025630951,
      "learning_rate": 6.060606060606061e-07,
      "loss": 0.078,
      "step": 31
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.20983684062957764,
      "learning_rate": 3.0303030303030305e-07,
      "loss": 0.0771,
      "step": 32
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.22096428275108337,
      "learning_rate": 0.0,
      "loss": 0.0774,
      "step": 33
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.651932147574374e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}