{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9968051118210862,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025559105431309903,
      "grad_norm": 0.2702205580538704,
      "learning_rate": 0.0,
      "loss": 0.3535,
      "step": 1
    },
    {
      "epoch": 0.051118210862619806,
      "grad_norm": 0.28684583415847476,
      "learning_rate": 5e-06,
      "loss": 0.3609,
      "step": 2
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 0.26679237950106627,
      "learning_rate": 1e-05,
      "loss": 0.3629,
      "step": 3
    },
    {
      "epoch": 0.10223642172523961,
      "grad_norm": 0.29404758323358765,
      "learning_rate": 9.981987442712634e-06,
      "loss": 0.3579,
      "step": 4
    },
    {
      "epoch": 0.12779552715654952,
      "grad_norm": 0.27382491912877804,
      "learning_rate": 9.928079551738542e-06,
      "loss": 0.3669,
      "step": 5
    },
    {
      "epoch": 0.15335463258785942,
      "grad_norm": 0.27863044831238126,
      "learning_rate": 9.838664734667496e-06,
      "loss": 0.351,
      "step": 6
    },
    {
      "epoch": 0.17891373801916932,
      "grad_norm": 0.2887255020211231,
      "learning_rate": 9.714387227305422e-06,
      "loss": 0.3562,
      "step": 7
    },
    {
      "epoch": 0.20447284345047922,
      "grad_norm": 0.294454678267451,
      "learning_rate": 9.55614245194068e-06,
      "loss": 0.3581,
      "step": 8
    },
    {
      "epoch": 0.23003194888178913,
      "grad_norm": 0.2609467109885083,
      "learning_rate": 9.365070565805941e-06,
      "loss": 0.3503,
      "step": 9
    },
    {
      "epoch": 0.25559105431309903,
      "grad_norm": 0.26941865715930563,
      "learning_rate": 9.142548246219212e-06,
      "loss": 0.3554,
      "step": 10
    },
    {
      "epoch": 0.28115015974440893,
      "grad_norm": 0.2986126638492072,
      "learning_rate": 8.890178771592198e-06,
      "loss": 0.3574,
      "step": 11
    },
    {
      "epoch": 0.30670926517571884,
      "grad_norm": 0.2877856445800662,
      "learning_rate": 8.609780469772623e-06,
      "loss": 0.3548,
      "step": 12
    },
    {
      "epoch": 0.33226837060702874,
      "grad_norm": 0.2694511486845226,
      "learning_rate": 8.303373616950408e-06,
      "loss": 0.3508,
      "step": 13
    },
    {
      "epoch": 0.35782747603833864,
      "grad_norm": 0.2559023823542533,
      "learning_rate": 7.973165881521435e-06,
      "loss": 0.354,
      "step": 14
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 0.29055130455186523,
      "learning_rate": 7.621536417786159e-06,
      "loss": 0.3543,
      "step": 15
    },
    {
      "epoch": 0.40894568690095845,
      "grad_norm": 0.26214018335874595,
      "learning_rate": 7.251018724088367e-06,
      "loss": 0.3584,
      "step": 16
    },
    {
      "epoch": 0.43450479233226835,
      "grad_norm": 0.2956146254798679,
      "learning_rate": 6.864282388901544e-06,
      "loss": 0.3564,
      "step": 17
    },
    {
      "epoch": 0.46006389776357826,
      "grad_norm": 0.26196605321409216,
      "learning_rate": 6.464113856382752e-06,
      "loss": 0.3551,
      "step": 18
    },
    {
      "epoch": 0.48562300319488816,
      "grad_norm": 0.2642640092390301,
      "learning_rate": 6.053396349978632e-06,
      "loss": 0.3564,
      "step": 19
    },
    {
      "epoch": 0.5111821086261981,
      "grad_norm": 0.2679189215560827,
      "learning_rate": 5.635089098734394e-06,
      "loss": 0.3502,
      "step": 20
    },
    {
      "epoch": 0.536741214057508,
      "grad_norm": 0.26748149169965235,
      "learning_rate": 5.212206015980742e-06,
      "loss": 0.347,
      "step": 21
    },
    {
      "epoch": 0.5623003194888179,
      "grad_norm": 0.2649623650289123,
      "learning_rate": 4.78779398401926e-06,
      "loss": 0.3537,
      "step": 22
    },
    {
      "epoch": 0.5878594249201278,
      "grad_norm": 0.26068573056009575,
      "learning_rate": 4.364910901265607e-06,
      "loss": 0.3475,
      "step": 23
    },
    {
      "epoch": 0.6134185303514377,
      "grad_norm": 0.28398923088906114,
      "learning_rate": 3.94660365002137e-06,
      "loss": 0.3584,
      "step": 24
    },
    {
      "epoch": 0.6389776357827476,
      "grad_norm": 0.24569806228235233,
      "learning_rate": 3.5358861436172487e-06,
      "loss": 0.3416,
      "step": 25
    },
    {
      "epoch": 0.6645367412140575,
      "grad_norm": 0.2603389001057077,
      "learning_rate": 3.1357176110984578e-06,
      "loss": 0.3444,
      "step": 26
    },
    {
      "epoch": 0.6900958466453674,
      "grad_norm": 0.2605981872635286,
      "learning_rate": 2.748981275911633e-06,
      "loss": 0.3528,
      "step": 27
    },
    {
      "epoch": 0.7156549520766773,
      "grad_norm": 0.260052555853406,
      "learning_rate": 2.3784635822138424e-06,
      "loss": 0.3518,
      "step": 28
    },
    {
      "epoch": 0.7412140575079872,
      "grad_norm": 0.2770744022287001,
      "learning_rate": 2.0268341184785674e-06,
      "loss": 0.3606,
      "step": 29
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 0.3105909584820928,
      "learning_rate": 1.6966263830495939e-06,
      "loss": 0.3531,
      "step": 30
    },
    {
      "epoch": 0.792332268370607,
      "grad_norm": 0.2686433300859331,
      "learning_rate": 1.390219530227378e-06,
      "loss": 0.3488,
      "step": 31
    },
    {
      "epoch": 0.8178913738019169,
      "grad_norm": 0.24550390235488143,
      "learning_rate": 1.1098212284078037e-06,
      "loss": 0.3535,
      "step": 32
    },
    {
      "epoch": 0.8434504792332268,
      "grad_norm": 0.24931550171886188,
      "learning_rate": 8.574517537807897e-07,
      "loss": 0.3489,
      "step": 33
    },
    {
      "epoch": 0.8690095846645367,
      "grad_norm": 0.24486541381545082,
      "learning_rate": 6.349294341940593e-07,
      "loss": 0.3567,
      "step": 34
    },
    {
      "epoch": 0.8945686900958466,
      "grad_norm": 0.2654084354760567,
      "learning_rate": 4.43857548059321e-07,
      "loss": 0.3485,
      "step": 35
    },
    {
      "epoch": 0.9201277955271565,
      "grad_norm": 0.27892004029327283,
      "learning_rate": 2.85612772694579e-07,
      "loss": 0.3554,
      "step": 36
    },
    {
      "epoch": 0.9456869009584664,
      "grad_norm": 0.2747818646370577,
      "learning_rate": 1.6133526533250566e-07,
      "loss": 0.3497,
      "step": 37
    },
    {
      "epoch": 0.9712460063897763,
      "grad_norm": 0.26593275387066134,
      "learning_rate": 7.192044826145772e-08,
      "loss": 0.3414,
      "step": 38
    },
    {
      "epoch": 0.9968051118210862,
      "grad_norm": 0.25641425675691765,
      "learning_rate": 1.8012557287367394e-08,
      "loss": 0.3454,
      "step": 39
    },
    {
      "epoch": 0.9968051118210862,
      "step": 39,
      "total_flos": 115417776128000.0,
      "train_loss": 0.3533387298767383,
      "train_runtime": 478.6351,
      "train_samples_per_second": 20.893,
      "train_steps_per_second": 0.081
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 115417776128000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}