{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 121.21212121212122,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.848484848484849,
      "grad_norm": 0.5543263554573059,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.7902,
      "step": 10
    },
    {
      "epoch": 9.696969696969697,
      "grad_norm": 0.6367977857589722,
      "learning_rate": 0.0001968583161128631,
      "loss": 2.3062,
      "step": 20
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 0.479856014251709,
      "learning_rate": 0.00019297764858882514,
      "loss": 1.7416,
      "step": 30
    },
    {
      "epoch": 19.393939393939394,
      "grad_norm": 0.29826533794403076,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.4342,
      "step": 40
    },
    {
      "epoch": 24.242424242424242,
      "grad_norm": 0.27084779739379883,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3399,
      "step": 50
    },
    {
      "epoch": 29.09090909090909,
      "grad_norm": 0.2398836314678192,
      "learning_rate": 0.00017289686274214118,
      "loss": 1.2648,
      "step": 60
    },
    {
      "epoch": 33.93939393939394,
      "grad_norm": 0.22510196268558502,
      "learning_rate": 0.000163742398974869,
      "loss": 1.2083,
      "step": 70
    },
    {
      "epoch": 38.78787878787879,
      "grad_norm": 0.2365349531173706,
      "learning_rate": 0.00015358267949789966,
      "loss": 1.1641,
      "step": 80
    },
    {
      "epoch": 43.63636363636363,
      "grad_norm": 0.270672082901001,
      "learning_rate": 0.00014257792915650728,
      "loss": 1.1283,
      "step": 90
    },
    {
      "epoch": 48.484848484848484,
      "grad_norm": 0.2681578993797302,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0801,
      "step": 100
    },
    {
      "epoch": 53.333333333333336,
      "grad_norm": 0.31493374705314636,
      "learning_rate": 0.00011873813145857249,
      "loss": 1.0366,
      "step": 110
    },
    {
      "epoch": 58.18181818181818,
      "grad_norm": 0.3526628315448761,
      "learning_rate": 0.00010627905195293135,
      "loss": 1.0097,
      "step": 120
    },
    {
      "epoch": 63.03030303030303,
      "grad_norm": 0.31481245160102844,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.9806,
      "step": 130
    },
    {
      "epoch": 67.87878787878788,
      "grad_norm": 0.3324221074581146,
      "learning_rate": 8.126186854142752e-05,
      "loss": 0.9474,
      "step": 140
    },
    {
      "epoch": 72.72727272727273,
      "grad_norm": 0.32580453157424927,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.9228,
      "step": 150
    },
    {
      "epoch": 77.57575757575758,
      "grad_norm": 0.3470986485481262,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.9007,
      "step": 160
    },
    {
      "epoch": 82.42424242424242,
      "grad_norm": 0.4177663326263428,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 0.8839,
      "step": 170
    },
    {
      "epoch": 87.27272727272727,
      "grad_norm": 0.4714958965778351,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 0.8706,
      "step": 180
    },
    {
      "epoch": 92.12121212121212,
      "grad_norm": 0.4196126163005829,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.8541,
      "step": 190
    },
    {
      "epoch": 96.96969696969697,
      "grad_norm": 0.35907700657844543,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.8503,
      "step": 200
    },
    {
      "epoch": 101.81818181818181,
      "grad_norm": 0.40164825320243835,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 0.8449,
      "step": 210
    },
    {
      "epoch": 106.66666666666667,
      "grad_norm": 0.37763774394989014,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.8384,
      "step": 220
    },
    {
      "epoch": 111.51515151515152,
      "grad_norm": 0.3757176101207733,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 0.8405,
      "step": 230
    },
    {
      "epoch": 116.36363636363636,
      "grad_norm": 0.4176121950149536,
      "learning_rate": 7.885298685522235e-07,
      "loss": 0.8299,
      "step": 240
    },
    {
      "epoch": 121.21212121212122,
      "grad_norm": 0.47404736280441284,
      "learning_rate": 0.0,
      "loss": 0.8342,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 125,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6950976392371200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}