{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.112676056338028,
  "eval_steps": 500,
  "global_step": 2400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0880281690140845,
      "grad_norm": 1643.14404296875,
      "learning_rate": 4.166666666666667e-06,
      "loss": 136.5152,
      "step": 100
    },
    {
      "epoch": 0.176056338028169,
      "grad_norm": 1259.6392822265625,
      "learning_rate": 8.333333333333334e-06,
      "loss": 127.3215,
      "step": 200
    },
    {
      "epoch": 0.2640845070422535,
      "grad_norm": 1478.6107177734375,
      "learning_rate": 9.980973490458728e-06,
      "loss": 137.0093,
      "step": 300
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 586.53076171875,
      "learning_rate": 9.86522435289912e-06,
      "loss": 136.2538,
      "step": 400
    },
    {
      "epoch": 0.44014084507042256,
      "grad_norm": 748.0945434570312,
      "learning_rate": 9.646737621134112e-06,
      "loss": 110.4259,
      "step": 500
    },
    {
      "epoch": 0.528169014084507,
      "grad_norm": 1178.682373046875,
      "learning_rate": 9.330127018922195e-06,
      "loss": 99.7847,
      "step": 600
    },
    {
      "epoch": 0.6161971830985915,
      "grad_norm": 890.4047241210938,
      "learning_rate": 8.92207832459788e-06,
      "loss": 111.7352,
      "step": 700
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 333.7227783203125,
      "learning_rate": 8.43120818934367e-06,
      "loss": 104.0762,
      "step": 800
    },
    {
      "epoch": 0.7922535211267606,
      "grad_norm": 1009.5026245117188,
      "learning_rate": 7.86788218175523e-06,
      "loss": 103.2902,
      "step": 900
    },
    {
      "epoch": 0.8802816901408451,
      "grad_norm": 542.9478759765625,
      "learning_rate": 7.243995901002312e-06,
      "loss": 107.7297,
      "step": 1000
    },
    {
      "epoch": 0.9683098591549296,
      "grad_norm": 864.6980590820312,
      "learning_rate": 6.572723780758069e-06,
      "loss": 88.3369,
      "step": 1100
    },
    {
      "epoch": 1.0,
      "eval_loss": 200.542236328125,
      "eval_runtime": 31.8227,
      "eval_samples_per_second": 31.738,
      "eval_steps_per_second": 3.991,
      "step": 1136
    },
    {
      "epoch": 1.056338028169014,
      "grad_norm": 1790.6683349609375,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 91.1943,
      "step": 1200
    },
    {
      "epoch": 1.1443661971830985,
      "grad_norm": 1222.1258544921875,
      "learning_rate": 5.145423593715558e-06,
      "loss": 101.148,
      "step": 1300
    },
    {
      "epoch": 1.232394366197183,
      "grad_norm": 352.8750915527344,
      "learning_rate": 4.4195354293738484e-06,
      "loss": 74.3622,
      "step": 1400
    },
    {
      "epoch": 1.3204225352112675,
      "grad_norm": 2005.60986328125,
      "learning_rate": 3.705904774487396e-06,
      "loss": 85.063,
      "step": 1500
    },
    {
      "epoch": 1.408450704225352,
      "grad_norm": 680.5648193359375,
      "learning_rate": 3.019601169804216e-06,
      "loss": 81.2217,
      "step": 1600
    },
    {
      "epoch": 1.4964788732394365,
      "grad_norm": 394.0007629394531,
      "learning_rate": 2.3751170983272e-06,
      "loss": 83.0847,
      "step": 1700
    },
    {
      "epoch": 1.584507042253521,
      "grad_norm": 868.7428588867188,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 68.1166,
      "step": 1800
    },
    {
      "epoch": 1.6725352112676055,
      "grad_norm": 275.2021179199219,
      "learning_rate": 1.264874643795021e-06,
      "loss": 88.6323,
      "step": 1900
    },
    {
      "epoch": 1.76056338028169,
      "grad_norm": 370.32763671875,
      "learning_rate": 8.225609429353187e-07,
      "loss": 75.0886,
      "step": 2000
    },
    {
      "epoch": 1.8485915492957745,
      "grad_norm": 514.0765380859375,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 70.9229,
      "step": 2100
    },
    {
      "epoch": 1.936619718309859,
      "grad_norm": 687.5501708984375,
      "learning_rate": 2.1005243842255552e-07,
      "loss": 77.3133,
      "step": 2200
    },
    {
      "epoch": 2.0,
      "eval_loss": 195.50889587402344,
      "eval_runtime": 32.1653,
      "eval_samples_per_second": 31.4,
      "eval_steps_per_second": 3.948,
      "step": 2272
    },
    {
      "epoch": 2.0246478873239435,
      "grad_norm": 885.4177856445312,
      "learning_rate": 5.279180709527765e-08,
      "loss": 76.5441,
      "step": 2300
    },
    {
      "epoch": 2.112676056338028,
      "grad_norm": 815.9951782226562,
      "learning_rate": 0.0,
      "loss": 72.9512,
      "step": 2400
    }
  ],
  "logging_steps": 100,
  "max_steps": 2400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 600,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}