{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9989637305699481,
  "eval_steps": 500,
  "global_step": 482,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 4.99941873550415,
      "learning_rate": 2e-05,
      "loss": 9.9329,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.741065502166748,
      "learning_rate": 4e-05,
      "loss": 11.0746,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.4727320671081543,
      "learning_rate": 6e-05,
      "loss": 2.7159,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.1335960477590561,
      "learning_rate": 8e-05,
      "loss": 0.3969,
      "step": 40
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0014472692273557186,
      "learning_rate": 0.0001,
      "loss": 0.0032,
      "step": 50
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0010780546581372619,
      "learning_rate": 0.0001,
      "loss": 0.0002,
      "step": 60
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.03132963180542,
      "learning_rate": 0.0001,
      "loss": 0.0002,
      "step": 70
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.008827299810945988,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.0002956670359708369,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 90
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0003419867134653032,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.0003681881644297391,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0002884200366679579,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.00011985149467363954,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.0003195986500941217,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.00010149635636480525,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.00010508792183827609,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.00011793687008321285,
      "learning_rate": 0.0001,
      "loss": 0.006,
      "step": 170
    },
    {
      "epoch": 0.37,
      "grad_norm": 8.076676749624312e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.0007808339432813227,
      "learning_rate": 0.0001,
      "loss": 0.006,
      "step": 190
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.11711683869361877,
      "learning_rate": 0.0001,
      "loss": 0.003,
      "step": 200
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0002039404644165188,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 210
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.00873592495918274,
      "learning_rate": 0.0001,
      "loss": 0.0209,
      "step": 220
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.0506539344787598,
      "learning_rate": 0.0001,
      "loss": 0.0201,
      "step": 230
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.05903371796011925,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 240
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0002484666183590889,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 250
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0003493047261144966,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 260
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0008058947860263288,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 270
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.0004198936221655458,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 280
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0002983050071634352,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 290
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0002279053587699309,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 300
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.00015332824841607362,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.00011723622446879745,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0001235378731507808,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.00010625163122313097,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 340
    },
    {
      "epoch": 0.73,
      "grad_norm": 7.50239341869019e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.00010148331784876063,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.77,
      "grad_norm": 7.368126534856856e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.00012744461128022522,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 0.81,
      "grad_norm": 5.87971335335169e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.83,
      "grad_norm": 6.405858584912494e-05,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 400
    },
    {
      "epoch": 0.85,
      "grad_norm": 9.752299229148775e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.87,
      "grad_norm": 4.5175151171861216e-05,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.00013234459038358182,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 430
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.00013048920664004982,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0004233328509144485,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 450
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.00019652876653708518,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.000157060450874269,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.00014773521979805082,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 1.0,
      "step": 482,
      "total_flos": 7.979272829443277e+17,
      "train_loss": 0.5017403132133569,
      "train_runtime": 75900.5046,
      "train_samples_per_second": 0.102,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 10,
  "max_steps": 482,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7.979272829443277e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}