{
  "best_metric": 0.8278950452804565,
  "best_model_checkpoint": "beto-SemcorSDS-esp-mchoice/checkpoint-49572",
  "epoch": 2.0,
  "global_step": 49572,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.949568304688131e-05,
      "loss": 1.0107,
      "step": 500
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.899136609376261e-05,
      "loss": 0.8723,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.848704914064391e-05,
      "loss": 0.8684,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.798273218752522e-05,
      "loss": 0.8193,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.747841523440652e-05,
      "loss": 0.8183,
      "step": 2500
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.697409828128783e-05,
      "loss": 0.7922,
      "step": 3000
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.6469781328169134e-05,
      "loss": 0.7736,
      "step": 3500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.5965464375050435e-05,
      "loss": 0.7731,
      "step": 4000
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.5461147421931735e-05,
      "loss": 0.7645,
      "step": 4500
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.495683046881304e-05,
      "loss": 0.747,
      "step": 5000
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.4452513515694343e-05,
      "loss": 0.7296,
      "step": 5500
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.394819656257565e-05,
      "loss": 0.6894,
      "step": 6000
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.344387960945696e-05,
      "loss": 0.7093,
      "step": 6500
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.293956265633826e-05,
      "loss": 0.7082,
      "step": 7000
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.243524570321956e-05,
      "loss": 0.7191,
      "step": 7500
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.193092875010087e-05,
      "loss": 0.7172,
      "step": 8000
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.142661179698217e-05,
      "loss": 0.6845,
      "step": 8500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.0922294843863475e-05,
      "loss": 0.6957,
      "step": 9000
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.041797789074478e-05,
      "loss": 0.6726,
      "step": 9500
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.9913660937626076e-05,
      "loss": 0.6653,
      "step": 10000
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.9409343984507384e-05,
      "loss": 0.6952,
      "step": 10500
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.890502703138869e-05,
      "loss": 0.6757,
      "step": 11000
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.840071007826999e-05,
      "loss": 0.7029,
      "step": 11500
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.78963931251513e-05,
      "loss": 0.657,
      "step": 12000
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.73920761720326e-05,
      "loss": 0.6924,
      "step": 12500
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.68877592189139e-05,
      "loss": 0.6466,
      "step": 13000
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.638344226579521e-05,
      "loss": 0.6479,
      "step": 13500
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.5879125312676515e-05,
      "loss": 0.6381,
      "step": 14000
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.5374808359557816e-05,
      "loss": 0.659,
      "step": 14500
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.4870491406439124e-05,
      "loss": 0.6862,
      "step": 15000
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.4366174453320424e-05,
      "loss": 0.6493,
      "step": 15500
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.3861857500201725e-05,
      "loss": 0.6541,
      "step": 16000
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.335754054708303e-05,
      "loss": 0.6269,
      "step": 16500
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.285322359396434e-05,
      "loss": 0.6667,
      "step": 17000
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.234890664084564e-05,
      "loss": 0.639,
      "step": 17500
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.184458968772695e-05,
      "loss": 0.6136,
      "step": 18000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.134027273460825e-05,
      "loss": 0.6126,
      "step": 18500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.083595578148955e-05,
      "loss": 0.6108,
      "step": 19000
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.0331638828370857e-05,
      "loss": 0.6087,
      "step": 19500
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.982732187525216e-05,
      "loss": 0.6155,
      "step": 20000
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.932300492213346e-05,
      "loss": 0.6204,
      "step": 20500
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.881868796901477e-05,
      "loss": 0.6014,
      "step": 21000
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.8314371015896073e-05,
      "loss": 0.5979,
      "step": 21500
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.7810054062777373e-05,
      "loss": 0.6329,
      "step": 22000
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.730573710965868e-05,
      "loss": 0.5963,
      "step": 22500
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6801420156539985e-05,
      "loss": 0.6109,
      "step": 23000
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.6297103203421285e-05,
      "loss": 0.6187,
      "step": 23500
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.5792786250302593e-05,
      "loss": 0.5924,
      "step": 24000
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5288469297183897e-05,
      "loss": 0.5883,
      "step": 24500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8021398186683655,
      "eval_loss": 0.5718119144439697,
      "eval_runtime": 299.0287,
      "eval_samples_per_second": 69.077,
      "eval_steps_per_second": 11.514,
      "step": 24786
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.4784152344065198e-05,
      "loss": 0.5161,
      "step": 25000
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.4279835390946505e-05,
      "loss": 0.3989,
      "step": 25500
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.3775518437827806e-05,
      "loss": 0.4255,
      "step": 26000
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.327120148470911e-05,
      "loss": 0.4015,
      "step": 26500
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.2766884531590417e-05,
      "loss": 0.4222,
      "step": 27000
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.2262567578471718e-05,
      "loss": 0.4449,
      "step": 27500
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.1758250625353022e-05,
      "loss": 0.4148,
      "step": 28000
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.1253933672234326e-05,
      "loss": 0.4286,
      "step": 28500
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.074961671911563e-05,
      "loss": 0.4623,
      "step": 29000
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.0245299765996934e-05,
      "loss": 0.4258,
      "step": 29500
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.9740982812878238e-05,
      "loss": 0.4439,
      "step": 30000
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.9236665859759542e-05,
      "loss": 0.4485,
      "step": 30500
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.8732348906640846e-05,
      "loss": 0.4374,
      "step": 31000
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.822803195352215e-05,
      "loss": 0.4199,
      "step": 31500
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.7723715000403454e-05,
      "loss": 0.4585,
      "step": 32000
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.7219398047284758e-05,
      "loss": 0.4371,
      "step": 32500
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.6715081094166062e-05,
      "loss": 0.4205,
      "step": 33000
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.6210764141047366e-05,
      "loss": 0.4491,
      "step": 33500
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.570644718792867e-05,
      "loss": 0.4186,
      "step": 34000
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.5202130234809974e-05,
      "loss": 0.4236,
      "step": 34500
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.4697813281691278e-05,
      "loss": 0.4114,
      "step": 35000
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.419349632857258e-05,
      "loss": 0.4206,
      "step": 35500
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.3689179375453886e-05,
      "loss": 0.4212,
      "step": 36000
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.318486242233519e-05,
      "loss": 0.4327,
      "step": 36500
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.2680545469216493e-05,
      "loss": 0.4082,
      "step": 37000
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.2176228516097797e-05,
      "loss": 0.4307,
      "step": 37500
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.1671911562979101e-05,
      "loss": 0.4021,
      "step": 38000
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.1167594609860407e-05,
      "loss": 0.4307,
      "step": 38500
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.0663277656741709e-05,
      "loss": 0.4307,
      "step": 39000
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.0158960703623013e-05,
      "loss": 0.3856,
      "step": 39500
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.654643750504317e-06,
      "loss": 0.4156,
      "step": 40000
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.150326797385621e-06,
      "loss": 0.398,
      "step": 40500
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.646009844266925e-06,
      "loss": 0.4467,
      "step": 41000
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.141692891148229e-06,
      "loss": 0.3962,
      "step": 41500
    },
    {
      "epoch": 1.69,
      "learning_rate": 7.637375938029533e-06,
      "loss": 0.405,
      "step": 42000
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.133058984910837e-06,
      "loss": 0.4219,
      "step": 42500
    },
    {
      "epoch": 1.73,
      "learning_rate": 6.628742031792141e-06,
      "loss": 0.4234,
      "step": 43000
    },
    {
      "epoch": 1.76,
      "learning_rate": 6.124425078673445e-06,
      "loss": 0.3794,
      "step": 43500
    },
    {
      "epoch": 1.78,
      "learning_rate": 5.6201081255547485e-06,
      "loss": 0.3924,
      "step": 44000
    },
    {
      "epoch": 1.8,
      "learning_rate": 5.1157911724360525e-06,
      "loss": 0.4233,
      "step": 44500
    },
    {
      "epoch": 1.82,
      "learning_rate": 4.611474219317357e-06,
      "loss": 0.3938,
      "step": 45000
    },
    {
      "epoch": 1.84,
      "learning_rate": 4.107157266198661e-06,
      "loss": 0.378,
      "step": 45500
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.602840313079964e-06,
      "loss": 0.3797,
      "step": 46000
    },
    {
      "epoch": 1.88,
      "learning_rate": 3.0985233599612687e-06,
      "loss": 0.3882,
      "step": 46500
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.5942064068425727e-06,
      "loss": 0.3475,
      "step": 47000
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.0898894537238767e-06,
      "loss": 0.4292,
      "step": 47500
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.5855725006051804e-06,
      "loss": 0.3869,
      "step": 48000
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.0812555474864844e-06,
      "loss": 0.3847,
      "step": 48500
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.769385943677882e-07,
      "loss": 0.3832,
      "step": 49000
    },
    {
      "epoch": 2.0,
      "learning_rate": 7.262164124909223e-08,
      "loss": 0.4131,
      "step": 49500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8278950452804565,
      "eval_loss": 0.6946226954460144,
      "eval_runtime": 292.3668,
      "eval_samples_per_second": 70.651,
      "eval_steps_per_second": 11.776,
      "step": 49572
    }
  ],
  "max_steps": 49572,
  "num_train_epochs": 2,
  "total_flos": 6.135635110010184e+16,
  "trial_name": null,
  "trial_params": null
}