{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6907036189963676,
  "eval_steps": 500,
  "global_step": 10000,
  "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": 2.2244,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.99603027099283e-05,
      "loss": 0.0286,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.991071065046783e-05,
      "loss": 0.0144,
      "step": 300
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.984133690970033e-05,
      "loss": 0.0223,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.975223657755279e-05,
      "loss": 0.0179,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9643480408906496e-05,
      "loss": 0.0246,
      "step": 600
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.951515476741036e-05,
      "loss": 0.0181,
      "step": 700
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.936736155689918e-05,
      "loss": 0.0155,
      "step": 800
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.920021814047156e-05,
      "loss": 0.0122,
      "step": 900
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.901385724729137e-05,
      "loss": 0.0128,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.880842686718711e-05,
      "loss": 0.016,
      "step": 1100
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.858409013313266e-05,
      "loss": 0.0134,
      "step": 1200
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8341025191702847e-05,
      "loss": 0.0099,
      "step": 1300
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.80794250616066e-05,
      "loss": 0.0102,
      "step": 1400
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.7799497480410125e-05,
      "loss": 0.0109,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.7501464739571836e-05,
      "loss": 0.0117,
      "step": 1600
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.7185563507919895e-05,
      "loss": 0.0154,
      "step": 1700
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.685204464371269e-05,
      "loss": 0.0107,
      "step": 1800
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6501172995431424e-05,
      "loss": 0.0133,
      "step": 1900
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6133227191463044e-05,
      "loss": 0.0157,
      "step": 2000
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.574849941884044e-05,
      "loss": 0.0115,
      "step": 2100
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.534729519121574e-05,
      "loss": 0.0135,
      "step": 2200
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.492993310625088e-05,
      "loss": 0.0104,
      "step": 2300
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.449674459261804e-05,
      "loss": 0.0113,
      "step": 2400
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.404807364681105e-05,
      "loss": 0.0075,
      "step": 2500
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.358427655997657e-05,
      "loss": 0.011,
      "step": 2600
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.310572163498205e-05,
      "loss": 0.0103,
      "step": 2700
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.2612788893945176e-05,
      "loss": 0.0126,
      "step": 2800
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.2105869776456944e-05,
      "loss": 0.0084,
      "step": 2900
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.158536682873821e-05,
      "loss": 0.0069,
      "step": 3000
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.1051693383976264e-05,
      "loss": 0.0089,
      "step": 3100
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.050527323409557e-05,
      "loss": 0.0103,
      "step": 3200
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.994654029322313e-05,
      "loss": 0.011,
      "step": 3300
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.937593825311575e-05,
      "loss": 0.0063,
      "step": 3400
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.8793920230822925e-05,
      "loss": 0.0091,
      "step": 3500
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.8200948408864986e-05,
      "loss": 0.0072,
      "step": 3600
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.759749366821241e-05,
      "loss": 0.007,
      "step": 3700
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.698403521435756e-05,
      "loss": 0.0067,
      "step": 3800
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.636106019677602e-05,
      "loss": 0.0055,
      "step": 3900
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.572906332207943e-05,
      "loss": 0.0071,
      "step": 4000
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5088546461167346e-05,
      "loss": 0.0056,
      "step": 4100
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.4440018250689767e-05,
      "loss": 0.0074,
      "step": 4200
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.3783993689137015e-05,
      "loss": 0.0061,
      "step": 4300
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.312099372787772e-05,
      "loss": 0.0051,
      "step": 4400
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.2451544857469436e-05,
      "loss": 0.0078,
      "step": 4500
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.177617868957078e-05,
      "loss": 0.0064,
      "step": 4600
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.109543153478671e-05,
      "loss": 0.0064,
      "step": 4700
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.040984397678245e-05,
      "loss": 0.0064,
      "step": 4800
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.9719960443004107e-05,
      "loss": 0.0062,
      "step": 4900
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.9026328772347e-05,
      "loss": 0.0056,
      "step": 5000
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.8329499780114865e-05,
      "loss": 0.0096,
      "step": 5100
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.763002682061555e-05,
      "loss": 0.0054,
      "step": 5200
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.6928465347740434e-05,
      "loss": 0.0049,
      "step": 5300
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6225372473876565e-05,
      "loss": 0.0023,
      "step": 5400
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.552835016828629e-05,
      "loss": 0.0065,
      "step": 5500
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.4823871621313255e-05,
      "loss": 0.0032,
      "step": 5600
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.411953293849365e-05,
      "loss": 0.0043,
      "step": 5700
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.341589343760652e-05,
      "loss": 0.0038,
      "step": 5800
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.271351188120813e-05,
      "loss": 0.0048,
      "step": 5900
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.2012946032916717e-05,
      "loss": 0.0082,
      "step": 6000
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.1314752214490396e-05,
      "loss": 0.0046,
      "step": 6100
    },
    {
      "epoch": 1.67,
      "learning_rate": 2.061948486405021e-05,
      "loss": 0.0063,
      "step": 6200
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.992769609579885e-05,
      "loss": 0.0052,
      "step": 6300
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.9239935261584917e-05,
      "loss": 0.0041,
      "step": 6400
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.8556748514660664e-05,
      "loss": 0.004,
      "step": 6500
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.7878678375979845e-05,
      "loss": 0.0035,
      "step": 6600
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.7206263303379948e-05,
      "loss": 0.0066,
      "step": 6700
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.654003726399097e-05,
      "loss": 0.0047,
      "step": 6800
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.5880529310210283e-05,
      "loss": 0.005,
      "step": 6900
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.5228263159580275e-05,
      "loss": 0.0033,
      "step": 7000
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.4583756778902463e-05,
      "loss": 0.0059,
      "step": 7100
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.3947521972918251e-05,
      "loss": 0.0051,
      "step": 7200
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.3320063977883046e-05,
      "loss": 0.0041,
      "step": 7300
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.2701881060356396e-05,
      "loss": 0.0049,
      "step": 7400
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.209346412152676e-05,
      "loss": 0.0024,
      "step": 7500
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.149529630738521e-05,
      "loss": 0.0035,
      "step": 7600
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.0907852625057538e-05,
      "loss": 0.0013,
      "step": 7700
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.0331599565599464e-05,
      "loss": 0.0014,
      "step": 7800
    },
    {
      "epoch": 2.13,
      "learning_rate": 9.766994733554432e-06,
      "loss": 0.004,
      "step": 7900
    },
    {
      "epoch": 2.15,
      "learning_rate": 9.214486483568307e-06,
      "loss": 0.0021,
      "step": 8000
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.674513564349376e-06,
      "loss": 0.0025,
      "step": 8100
    },
    {
      "epoch": 2.21,
      "learning_rate": 8.147504770256536e-06,
      "loss": 0.0026,
      "step": 8200
    },
    {
      "epoch": 2.23,
      "learning_rate": 7.633878600792143e-06,
      "loss": 0.0018,
      "step": 8300
    },
    {
      "epoch": 2.26,
      "learning_rate": 7.138971709507527e-06,
      "loss": 0.0016,
      "step": 8400
    },
    {
      "epoch": 2.29,
      "learning_rate": 6.653179652954706e-06,
      "loss": 0.003,
      "step": 8500
    },
    {
      "epoch": 2.31,
      "learning_rate": 6.181956869763645e-06,
      "loss": 0.0011,
      "step": 8600
    },
    {
      "epoch": 2.34,
      "learning_rate": 5.725677559572909e-06,
      "loss": 0.0024,
      "step": 8700
    },
    {
      "epoch": 2.37,
      "learning_rate": 5.284704055357578e-06,
      "loss": 0.0007,
      "step": 8800
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.859386535699373e-06,
      "loss": 0.0017,
      "step": 8900
    },
    {
      "epoch": 2.42,
      "learning_rate": 4.4500627467086245e-06,
      "loss": 0.0021,
      "step": 9000
    },
    {
      "epoch": 2.45,
      "learning_rate": 4.057057733818967e-06,
      "loss": 0.0016,
      "step": 9100
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.680683583667599e-06,
      "loss": 0.0013,
      "step": 9200
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.321239176266211e-06,
      "loss": 0.0028,
      "step": 9300
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.9790099476593393e-06,
      "loss": 0.0007,
      "step": 9400
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.654267663258628e-06,
      "loss": 0.0026,
      "step": 9500
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.3472702020329696e-06,
      "loss": 0.0013,
      "step": 9600
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.0582613517259377e-06,
      "loss": 0.0014,
      "step": 9700
    },
    {
      "epoch": 2.64,
      "learning_rate": 1.7874706152630705e-06,
      "loss": 0.0011,
      "step": 9800
    },
    {
      "epoch": 2.66,
      "learning_rate": 1.5351130285028214e-06,
      "loss": 0.0022,
      "step": 9900
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.3036333720407912e-06,
      "loss": 0.0012,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 11148,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "total_flos": 2.0893490293152154e+18,
  "trial_name": null,
  "trial_params": null
}