{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.6807713911252575,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 4.995319228608875e-05,
      "loss": 3.2415,
      "step": 500
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9906384572177495e-05,
      "loss": 3.1877,
      "step": 1000
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.9859576858266244e-05,
      "loss": 3.16,
      "step": 1500
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.9812769144354994e-05,
      "loss": 3.106,
      "step": 2000
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.9766055045871565e-05,
      "loss": 3.1023,
      "step": 2500
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.971924733196031e-05,
      "loss": 3.0976,
      "step": 3000
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.967243961804906e-05,
      "loss": 3.0841,
      "step": 3500
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.96256319041378e-05,
      "loss": 3.0686,
      "step": 4000
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.957882419022655e-05,
      "loss": 3.0504,
      "step": 4500
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.953211009174312e-05,
      "loss": 3.0647,
      "step": 5000
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.948530237783187e-05,
      "loss": 2.9605,
      "step": 5500
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.9438494663920614e-05,
      "loss": 2.83,
      "step": 6000
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.9391686950009364e-05,
      "loss": 2.8551,
      "step": 6500
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.9344972851525935e-05,
      "loss": 2.8582,
      "step": 7000
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.9298165137614684e-05,
      "loss": 2.8605,
      "step": 7500
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.9251357423703434e-05,
      "loss": 2.8591,
      "step": 8000
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.920454970979218e-05,
      "loss": 2.8611,
      "step": 8500
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.9157741995880926e-05,
      "loss": 2.8545,
      "step": 9000
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.9110934281969676e-05,
      "loss": 2.8659,
      "step": 9500
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.906412656805842e-05,
      "loss": 2.8525,
      "step": 10000
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.901741246957498e-05,
      "loss": 2.868,
      "step": 10500
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.897060475566373e-05,
      "loss": 2.7281,
      "step": 11000
    },
    {
      "epoch": 2.15,
      "learning_rate": 4.892379704175248e-05,
      "loss": 2.6595,
      "step": 11500
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.887698932784123e-05,
      "loss": 2.6782,
      "step": 12000
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.8830181613929975e-05,
      "loss": 2.6556,
      "step": 12500
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.8783373900018725e-05,
      "loss": 2.6926,
      "step": 13000
    },
    {
      "epoch": 2.53,
      "learning_rate": 4.8736566186107474e-05,
      "loss": 2.6984,
      "step": 13500
    },
    {
      "epoch": 2.62,
      "learning_rate": 4.8689758472196224e-05,
      "loss": 2.6981,
      "step": 14000
    },
    {
      "epoch": 2.71,
      "learning_rate": 4.8643044373712795e-05,
      "loss": 2.702,
      "step": 14500
    },
    {
      "epoch": 2.81,
      "learning_rate": 4.859623665980154e-05,
      "loss": 2.689,
      "step": 15000
    },
    {
      "epoch": 2.9,
      "learning_rate": 4.854942894589029e-05,
      "loss": 2.6981,
      "step": 15500
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.850262123197904e-05,
      "loss": 2.7248,
      "step": 16000
    },
    {
      "epoch": 3.09,
      "learning_rate": 4.845581351806778e-05,
      "loss": 2.5182,
      "step": 16500
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.840900580415653e-05,
      "loss": 2.5234,
      "step": 17000
    },
    {
      "epoch": 3.28,
      "learning_rate": 4.8362291705673094e-05,
      "loss": 2.5263,
      "step": 17500
    },
    {
      "epoch": 3.37,
      "learning_rate": 4.8315483991761844e-05,
      "loss": 2.5354,
      "step": 18000
    },
    {
      "epoch": 3.46,
      "learning_rate": 4.826867627785059e-05,
      "loss": 2.5474,
      "step": 18500
    },
    {
      "epoch": 3.56,
      "learning_rate": 4.8221868563939336e-05,
      "loss": 2.5553,
      "step": 19000
    },
    {
      "epoch": 3.65,
      "learning_rate": 4.8175060850028086e-05,
      "loss": 2.5713,
      "step": 19500
    },
    {
      "epoch": 3.74,
      "learning_rate": 4.812834675154466e-05,
      "loss": 2.5589,
      "step": 20000
    },
    {
      "epoch": 3.84,
      "learning_rate": 4.8081539037633407e-05,
      "loss": 2.5645,
      "step": 20500
    },
    {
      "epoch": 3.93,
      "learning_rate": 4.8034731323722156e-05,
      "loss": 2.5756,
      "step": 21000
    },
    {
      "epoch": 4.03,
      "learning_rate": 4.79879236098109e-05,
      "loss": 2.5252,
      "step": 21500
    },
    {
      "epoch": 4.12,
      "learning_rate": 4.794120951132747e-05,
      "loss": 2.3718,
      "step": 22000
    },
    {
      "epoch": 4.21,
      "learning_rate": 4.789440179741621e-05,
      "loss": 2.3778,
      "step": 22500
    },
    {
      "epoch": 4.31,
      "learning_rate": 4.784759408350496e-05,
      "loss": 2.3979,
      "step": 23000
    },
    {
      "epoch": 4.4,
      "learning_rate": 4.7800786369593706e-05,
      "loss": 2.4116,
      "step": 23500
    },
    {
      "epoch": 4.49,
      "learning_rate": 4.7753978655682455e-05,
      "loss": 2.4175,
      "step": 24000
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.7707264557199026e-05,
      "loss": 2.441,
      "step": 24500
    },
    {
      "epoch": 4.68,
      "learning_rate": 4.7660456843287776e-05,
      "loss": 2.4519,
      "step": 25000
    }
  ],
  "max_steps": 534100,
  "num_train_epochs": 100,
  "total_flos": 1.30646016e+16,
  "trial_name": null,
  "trial_params": null
}