{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3453518094981838,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.9990073706856164e-05,
      "loss": 2.3809,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.99603027099283e-05,
      "loss": 0.1075,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.991071065046783e-05,
      "loss": 0.0487,
      "step": 300
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.984133690970033e-05,
      "loss": 0.0357,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.975223657755279e-05,
      "loss": 0.0271,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9643480408906496e-05,
      "loss": 0.0257,
      "step": 600
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.951515476741036e-05,
      "loss": 0.0231,
      "step": 700
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.936736155689918e-05,
      "loss": 0.0176,
      "step": 800
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.920021814047156e-05,
      "loss": 0.018,
      "step": 900
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.901385724729137e-05,
      "loss": 0.0184,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.880842686718711e-05,
      "loss": 0.0181,
      "step": 1100
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.858409013313266e-05,
      "loss": 0.016,
      "step": 1200
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.834354792422293e-05,
      "loss": 0.0171,
      "step": 1300
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.8082132142108465e-05,
      "loss": 0.0141,
      "step": 1400
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.780238675919182e-05,
      "loss": 0.0137,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.75045339222471e-05,
      "loss": 0.0156,
      "step": 1600
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.718881015724017e-05,
      "loss": 0.0136,
      "step": 1700
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.6855466181502544e-05,
      "loss": 0.0134,
      "step": 1800
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.65047667046359e-05,
      "loss": 0.0101,
      "step": 1900
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.613699021830524e-05,
      "loss": 0.0126,
      "step": 2000
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.575635648326851e-05,
      "loss": 0.0138,
      "step": 2100
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.5355478705672265e-05,
      "loss": 0.0125,
      "step": 2200
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.4938436572178774e-05,
      "loss": 0.0097,
      "step": 2300
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.450556125738566e-05,
      "loss": 0.0157,
      "step": 2400
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.4057196509074484e-05,
      "loss": 0.0091,
      "step": 2500
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.359369837523941e-05,
      "loss": 0.0131,
      "step": 2600
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.311543492134827e-05,
      "loss": 0.0094,
      "step": 2700
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.2622785938060536e-05,
      "loss": 0.0139,
      "step": 2800
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.211614263963423e-05,
      "loss": 0.0089,
      "step": 2900
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.1595907353261296e-05,
      "loss": 0.009,
      "step": 3000
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.106249319957826e-05,
      "loss": 0.0103,
      "step": 3100
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.051632376460562e-05,
      "loss": 0.0115,
      "step": 3200
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.9957832763376815e-05,
      "loss": 0.0106,
      "step": 3300
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.9387463695523555e-05,
      "loss": 0.0098,
      "step": 3400
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.880566949309125e-05,
      "loss": 0.0087,
      "step": 3500
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.82129121608641e-05,
      "loss": 0.0081,
      "step": 3600
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.7609662409485565e-05,
      "loss": 0.0082,
      "step": 3700
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.699639928166532e-05,
      "loss": 0.0067,
      "step": 3800
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.6373609771769846e-05,
      "loss": 0.0071,
      "step": 3900
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.574178843909851e-05,
      "loss": 0.0081,
      "step": 4000
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5101437015152346e-05,
      "loss": 0.0075,
      "step": 4100
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.445306400520726e-05,
      "loss": 0.0088,
      "step": 4200
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.379718428450832e-05,
      "loss": 0.0066,
      "step": 4300
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.313431868940551e-05,
      "loss": 0.0057,
      "step": 4400
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.24649936037558e-05,
      "loss": 0.0072,
      "step": 4500
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.1789740540919856e-05,
      "loss": 0.0068,
      "step": 4600
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.1109095721685525e-05,
      "loss": 0.0068,
      "step": 4700
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.0423599648453037e-05,
      "loss": 0.008,
      "step": 4800
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.9733796676020104e-05,
      "loss": 0.0076,
      "step": 4900
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.9040234579308025e-05,
      "loss": 0.0071,
      "step": 5000
    }
  ],
  "logging_steps": 100,
  "max_steps": 11148,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "total_flos": 2.416609239309877e+18,
  "trial_name": null,
  "trial_params": null
}