{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.549520766773163,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06389776357827476,
      "grad_norm": 20.377737713693822,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 2.5741,
      "step": 10
    },
    {
      "epoch": 0.12779552715654952,
      "grad_norm": 4.615055699717414,
      "learning_rate": 3.958333333333333e-06,
      "loss": 1.8858,
      "step": 20
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 2.7878960752665805,
      "learning_rate": 6.041666666666667e-06,
      "loss": 1.3172,
      "step": 30
    },
    {
      "epoch": 0.25559105431309903,
      "grad_norm": 2.1443618886066678,
      "learning_rate": 8.125000000000001e-06,
      "loss": 1.0762,
      "step": 40
    },
    {
      "epoch": 0.3194888178913738,
      "grad_norm": 2.083564361550629,
      "learning_rate": 9.999862102299874e-06,
      "loss": 0.9691,
      "step": 50
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 2.027770037241651,
      "learning_rate": 9.983323579940351e-06,
      "loss": 0.9239,
      "step": 60
    },
    {
      "epoch": 0.4472843450479233,
      "grad_norm": 1.8790492807169699,
      "learning_rate": 9.939310009499348e-06,
      "loss": 0.8883,
      "step": 70
    },
    {
      "epoch": 0.5111821086261981,
      "grad_norm": 1.7919483636147056,
      "learning_rate": 9.868064055324204e-06,
      "loss": 0.8785,
      "step": 80
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 1.97998264662781,
      "learning_rate": 9.76997852474223e-06,
      "loss": 0.8606,
      "step": 90
    },
    {
      "epoch": 0.6389776357827476,
      "grad_norm": 1.7621305607359916,
      "learning_rate": 9.645594202357438e-06,
      "loss": 0.8499,
      "step": 100
    },
    {
      "epoch": 0.7028753993610224,
      "grad_norm": 1.7524493187730084,
      "learning_rate": 9.495596868489588e-06,
      "loss": 0.8322,
      "step": 110
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 1.8949002802030435,
      "learning_rate": 9.320813518194084e-06,
      "loss": 0.8225,
      "step": 120
    },
    {
      "epoch": 0.8306709265175719,
      "grad_norm": 1.896682860936547,
      "learning_rate": 9.122207801708802e-06,
      "loss": 0.8242,
      "step": 130
    },
    {
      "epoch": 0.8945686900958466,
      "grad_norm": 1.9529011844472832,
      "learning_rate": 8.900874711466436e-06,
      "loss": 0.8026,
      "step": 140
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 1.8816098587424452,
      "learning_rate": 8.658034544965003e-06,
      "loss": 0.8046,
      "step": 150
    },
    {
      "epoch": 1.0191693290734825,
      "grad_norm": 1.7513144878089228,
      "learning_rate": 8.395026176781627e-06,
      "loss": 0.7811,
      "step": 160
    },
    {
      "epoch": 1.0830670926517572,
      "grad_norm": 1.6927871553024794,
      "learning_rate": 8.113299676823614e-06,
      "loss": 0.7099,
      "step": 170
    },
    {
      "epoch": 1.1469648562300319,
      "grad_norm": 1.8501286355982487,
      "learning_rate": 7.814408315515419e-06,
      "loss": 0.716,
      "step": 180
    },
    {
      "epoch": 1.2108626198083068,
      "grad_norm": 1.898746762667725,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.6966,
      "step": 190
    },
    {
      "epoch": 1.2747603833865815,
      "grad_norm": 2.0376095953208186,
      "learning_rate": 7.1718081885702905e-06,
      "loss": 0.6988,
      "step": 200
    },
    {
      "epoch": 1.3386581469648562,
      "grad_norm": 2.0679265754168097,
      "learning_rate": 6.831642333423068e-06,
      "loss": 0.6995,
      "step": 210
    },
    {
      "epoch": 1.4025559105431311,
      "grad_norm": 1.7425470695615182,
      "learning_rate": 6.481377904428171e-06,
      "loss": 0.6849,
      "step": 220
    },
    {
      "epoch": 1.4664536741214058,
      "grad_norm": 1.7480874168585598,
      "learning_rate": 6.122946048915991e-06,
      "loss": 0.6797,
      "step": 230
    },
    {
      "epoch": 1.5303514376996805,
      "grad_norm": 1.932258961098815,
      "learning_rate": 5.75832294449293e-06,
      "loss": 0.6826,
      "step": 240
    },
    {
      "epoch": 1.5942492012779552,
      "grad_norm": 1.795120951075422,
      "learning_rate": 5.389518903587016e-06,
      "loss": 0.6794,
      "step": 250
    },
    {
      "epoch": 1.65814696485623,
      "grad_norm": 2.102611176384133,
      "learning_rate": 5.0185672897946515e-06,
      "loss": 0.6609,
      "step": 260
    },
    {
      "epoch": 1.7220447284345048,
      "grad_norm": 1.866705749251324,
      "learning_rate": 4.647513307137076e-06,
      "loss": 0.6741,
      "step": 270
    },
    {
      "epoch": 1.7859424920127795,
      "grad_norm": 1.7566750001867661,
      "learning_rate": 4.278402724035868e-06,
      "loss": 0.6619,
      "step": 280
    },
    {
      "epoch": 1.8498402555910545,
      "grad_norm": 1.814186513384251,
      "learning_rate": 3.913270594176665e-06,
      "loss": 0.6529,
      "step": 290
    },
    {
      "epoch": 1.9137380191693292,
      "grad_norm": 1.8183647565801306,
      "learning_rate": 3.5541300364475067e-06,
      "loss": 0.6406,
      "step": 300
    },
    {
      "epoch": 1.9776357827476039,
      "grad_norm": 1.9111185282349554,
      "learning_rate": 3.202961135812437e-06,
      "loss": 0.6302,
      "step": 310
    },
    {
      "epoch": 2.038338658146965,
      "grad_norm": 1.940940094549139,
      "learning_rate": 2.861700026314308e-06,
      "loss": 0.5852,
      "step": 320
    },
    {
      "epoch": 2.1022364217252396,
      "grad_norm": 1.812424693455716,
      "learning_rate": 2.5322282163965096e-06,
      "loss": 0.554,
      "step": 330
    },
    {
      "epoch": 2.1661341853035143,
      "grad_norm": 1.9758944605649846,
      "learning_rate": 2.216362215397393e-06,
      "loss": 0.5457,
      "step": 340
    },
    {
      "epoch": 2.230031948881789,
      "grad_norm": 1.846108330503614,
      "learning_rate": 1.91584351841065e-06,
      "loss": 0.537,
      "step": 350
    },
    {
      "epoch": 2.2939297124600637,
      "grad_norm": 1.9713773985567047,
      "learning_rate": 1.6323290047291196e-06,
      "loss": 0.5249,
      "step": 360
    },
    {
      "epoch": 2.357827476038339,
      "grad_norm": 1.96920367350381,
      "learning_rate": 1.367381802809185e-06,
      "loss": 0.521,
      "step": 370
    },
    {
      "epoch": 2.4217252396166136,
      "grad_norm": 1.8545979654793228,
      "learning_rate": 1.1224626721209141e-06,
      "loss": 0.5263,
      "step": 380
    },
    {
      "epoch": 2.4856230031948883,
      "grad_norm": 1.8666939617951708,
      "learning_rate": 8.989219493991791e-07,
      "loss": 0.5183,
      "step": 390
    },
    {
      "epoch": 2.549520766773163,
      "grad_norm": 1.976527350667108,
      "learning_rate": 6.979921036993042e-07,
      "loss": 0.5214,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 471,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 31500009209856.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}