{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12358882947118241,
  "eval_steps": 62,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030897207367795603,
      "grad_norm": 60.04155349731445,
      "learning_rate": 4e-07,
      "loss": 23.0268,
      "step": 1
    },
    {
      "epoch": 0.006179441473559121,
      "grad_norm": 58.97097396850586,
      "learning_rate": 8e-07,
      "loss": 22.9042,
      "step": 2
    },
    {
      "epoch": 0.009269162210338681,
      "grad_norm": 59.939247131347656,
      "learning_rate": 1.2e-06,
      "loss": 22.4922,
      "step": 3
    },
    {
      "epoch": 0.012358882947118241,
      "grad_norm": 60.71556091308594,
      "learning_rate": 1.6e-06,
      "loss": 23.6818,
      "step": 4
    },
    {
      "epoch": 0.015448603683897801,
      "grad_norm": 60.084556579589844,
      "learning_rate": 2e-06,
      "loss": 22.6323,
      "step": 5
    },
    {
      "epoch": 0.018538324420677363,
      "grad_norm": 58.05175018310547,
      "learning_rate": 1.998481516433316e-06,
      "loss": 21.7936,
      "step": 6
    },
    {
      "epoch": 0.02162804515745692,
      "grad_norm": 59.613494873046875,
      "learning_rate": 1.9939306773179494e-06,
      "loss": 22.5545,
      "step": 7
    },
    {
      "epoch": 0.024717765894236483,
      "grad_norm": 60.87885284423828,
      "learning_rate": 1.9863613034027223e-06,
      "loss": 22.6495,
      "step": 8
    },
    {
      "epoch": 0.027807486631016044,
      "grad_norm": 59.92291259765625,
      "learning_rate": 1.9757963826274354e-06,
      "loss": 22.562,
      "step": 9
    },
    {
      "epoch": 0.030897207367795602,
      "grad_norm": 59.16581344604492,
      "learning_rate": 1.9622680003092503e-06,
      "loss": 20.2875,
      "step": 10
    },
    {
      "epoch": 0.03398692810457516,
      "grad_norm": 59.31634521484375,
      "learning_rate": 1.9458172417006346e-06,
      "loss": 21.7414,
      "step": 11
    },
    {
      "epoch": 0.037076648841354726,
      "grad_norm": 59.62112045288086,
      "learning_rate": 1.9264940672148015e-06,
      "loss": 24.1894,
      "step": 12
    },
    {
      "epoch": 0.040166369578134284,
      "grad_norm": 59.239402770996094,
      "learning_rate": 1.9043571606975775e-06,
      "loss": 21.5377,
      "step": 13
    },
    {
      "epoch": 0.04325609031491384,
      "grad_norm": 61.078468322753906,
      "learning_rate": 1.8794737512064888e-06,
      "loss": 22.3836,
      "step": 14
    },
    {
      "epoch": 0.04634581105169341,
      "grad_norm": 60.2807502746582,
      "learning_rate": 1.851919408838327e-06,
      "loss": 22.8097,
      "step": 15
    },
    {
      "epoch": 0.049435531788472965,
      "grad_norm": 60.678627014160156,
      "learning_rate": 1.821777815225245e-06,
      "loss": 21.4694,
      "step": 16
    },
    {
      "epoch": 0.052525252525252523,
      "grad_norm": 61.19229507446289,
      "learning_rate": 1.7891405093963937e-06,
      "loss": 21.6569,
      "step": 17
    },
    {
      "epoch": 0.05561497326203209,
      "grad_norm": 60.128238677978516,
      "learning_rate": 1.754106609776896e-06,
      "loss": 23.511,
      "step": 18
    },
    {
      "epoch": 0.05870469399881165,
      "grad_norm": 59.77021408081055,
      "learning_rate": 1.7167825131684511e-06,
      "loss": 22.5047,
      "step": 19
    },
    {
      "epoch": 0.061794414735591205,
      "grad_norm": 61.9268684387207,
      "learning_rate": 1.6772815716257411e-06,
      "loss": 22.4478,
      "step": 20
    },
    {
      "epoch": 0.06488413547237076,
      "grad_norm": 59.85469436645508,
      "learning_rate": 1.6357237482099683e-06,
      "loss": 22.8151,
      "step": 21
    },
    {
      "epoch": 0.06797385620915032,
      "grad_norm": 60.153926849365234,
      "learning_rate": 1.5922352526649801e-06,
      "loss": 22.5061,
      "step": 22
    },
    {
      "epoch": 0.0710635769459299,
      "grad_norm": 59.1512565612793,
      "learning_rate": 1.5469481581224271e-06,
      "loss": 22.5223,
      "step": 23
    },
    {
      "epoch": 0.07415329768270945,
      "grad_norm": 59.45036697387695,
      "learning_rate": 1.5e-06,
      "loss": 22.095,
      "step": 24
    },
    {
      "epoch": 0.07724301841948901,
      "grad_norm": 59.37210464477539,
      "learning_rate": 1.4515333583108893e-06,
      "loss": 21.9364,
      "step": 25
    },
    {
      "epoch": 0.08033273915626857,
      "grad_norm": 60.37602996826172,
      "learning_rate": 1.4016954246529694e-06,
      "loss": 22.7162,
      "step": 26
    },
    {
      "epoch": 0.08342245989304813,
      "grad_norm": 59.79236602783203,
      "learning_rate": 1.3506375551927544e-06,
      "loss": 22.3541,
      "step": 27
    },
    {
      "epoch": 0.08651218062982768,
      "grad_norm": 59.140647888183594,
      "learning_rate": 1.2985148110016947e-06,
      "loss": 22.8465,
      "step": 28
    },
    {
      "epoch": 0.08960190136660724,
      "grad_norm": 59.66078567504883,
      "learning_rate": 1.245485487140799e-06,
      "loss": 22.3047,
      "step": 29
    },
    {
      "epoch": 0.09269162210338681,
      "grad_norm": 58.10475158691406,
      "learning_rate": 1.1917106319237384e-06,
      "loss": 23.073,
      "step": 30
    },
    {
      "epoch": 0.09578134284016637,
      "grad_norm": 60.376319885253906,
      "learning_rate": 1.1373535578184082e-06,
      "loss": 22.5172,
      "step": 31
    },
    {
      "epoch": 0.09887106357694593,
      "grad_norm": 61.557090759277344,
      "learning_rate": 1.0825793454723324e-06,
      "loss": 22.0322,
      "step": 32
    },
    {
      "epoch": 0.10196078431372549,
      "grad_norm": 58.49174118041992,
      "learning_rate": 1.0275543423681621e-06,
      "loss": 23.4697,
      "step": 33
    },
    {
      "epoch": 0.10505050505050505,
      "grad_norm": 59.54422378540039,
      "learning_rate": 9.72445657631838e-07,
      "loss": 22.6532,
      "step": 34
    },
    {
      "epoch": 0.1081402257872846,
      "grad_norm": 59.265708923339844,
      "learning_rate": 9.174206545276677e-07,
      "loss": 23.3989,
      "step": 35
    },
    {
      "epoch": 0.11122994652406418,
      "grad_norm": 60.273563385009766,
      "learning_rate": 8.626464421815918e-07,
      "loss": 23.3648,
      "step": 36
    },
    {
      "epoch": 0.11431966726084374,
      "grad_norm": 60.52754592895508,
      "learning_rate": 8.082893680762618e-07,
      "loss": 22.2345,
      "step": 37
    },
    {
      "epoch": 0.1174093879976233,
      "grad_norm": 60.50078582763672,
      "learning_rate": 7.545145128592008e-07,
      "loss": 21.6119,
      "step": 38
    },
    {
      "epoch": 0.12049910873440285,
      "grad_norm": 59.05815505981445,
      "learning_rate": 7.014851889983057e-07,
      "loss": 22.5614,
      "step": 39
    },
    {
      "epoch": 0.12358882947118241,
      "grad_norm": 61.67491149902344,
      "learning_rate": 6.493624448072457e-07,
      "loss": 23.6093,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.637517228998656e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}