{
  "best_metric": 0.9759521484375,
  "best_model_checkpoint": "./beans_outputs_1/checkpoint-1295",
  "epoch": 5.0,
  "global_step": 1295,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.9845559845559848e-05,
      "loss": 1.106,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9691119691119695e-05,
      "loss": 1.1028,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9536679536679538e-05,
      "loss": 1.0825,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.938223938223938e-05,
      "loss": 1.1019,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9227799227799228e-05,
      "loss": 1.0847,
      "step": 50
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9073359073359075e-05,
      "loss": 1.0689,
      "step": 60
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.891891891891892e-05,
      "loss": 1.0911,
      "step": 70
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8764478764478768e-05,
      "loss": 1.0968,
      "step": 80
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.861003861003861e-05,
      "loss": 1.0731,
      "step": 90
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.8455598455598458e-05,
      "loss": 1.0753,
      "step": 100
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.83011583011583e-05,
      "loss": 1.0795,
      "step": 110
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8146718146718147e-05,
      "loss": 1.0757,
      "step": 120
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7992277992277994e-05,
      "loss": 1.0769,
      "step": 130
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.783783783783784e-05,
      "loss": 1.0742,
      "step": 140
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7683397683397684e-05,
      "loss": 1.0649,
      "step": 150
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.752895752895753e-05,
      "loss": 1.0669,
      "step": 160
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.7374517374517377e-05,
      "loss": 1.0599,
      "step": 170
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.722007722007722e-05,
      "loss": 1.057,
      "step": 180
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.7065637065637067e-05,
      "loss": 1.0733,
      "step": 190
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6911196911196913e-05,
      "loss": 1.0602,
      "step": 200
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6756756756756757e-05,
      "loss": 1.0651,
      "step": 210
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.6602316602316603e-05,
      "loss": 1.0482,
      "step": 220
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.644787644787645e-05,
      "loss": 1.0514,
      "step": 230
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6293436293436296e-05,
      "loss": 1.0653,
      "step": 240
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.613899613899614e-05,
      "loss": 1.0596,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7142857142857143,
      "eval_loss": 1.0507243871688843,
      "eval_runtime": 60.3908,
      "eval_samples_per_second": 2.202,
      "eval_steps_per_second": 0.563,
      "step": 259
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.5984555984555986e-05,
      "loss": 1.0574,
      "step": 260
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.583011583011583e-05,
      "loss": 1.0497,
      "step": 270
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.5675675675675676e-05,
      "loss": 1.0488,
      "step": 280
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.5521235521235523e-05,
      "loss": 1.0416,
      "step": 290
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.536679536679537e-05,
      "loss": 1.0478,
      "step": 300
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.5212355212355214e-05,
      "loss": 1.0349,
      "step": 310
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.5057915057915061e-05,
      "loss": 1.0518,
      "step": 320
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.4903474903474904e-05,
      "loss": 1.0354,
      "step": 330
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.4749034749034749e-05,
      "loss": 1.0478,
      "step": 340
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.4594594594594596e-05,
      "loss": 1.064,
      "step": 350
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.444015444015444e-05,
      "loss": 1.0362,
      "step": 360
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 1.0351,
      "step": 370
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.4131274131274134e-05,
      "loss": 1.0423,
      "step": 380
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.3976833976833979e-05,
      "loss": 1.0345,
      "step": 390
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.3822393822393822e-05,
      "loss": 1.0271,
      "step": 400
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.3667953667953668e-05,
      "loss": 1.0337,
      "step": 410
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 1.0158,
      "step": 420
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.335907335907336e-05,
      "loss": 1.0421,
      "step": 430
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.3204633204633207e-05,
      "loss": 1.0309,
      "step": 440
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.3050193050193052e-05,
      "loss": 1.0097,
      "step": 450
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.2895752895752898e-05,
      "loss": 1.0157,
      "step": 460
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.2741312741312741e-05,
      "loss": 1.0195,
      "step": 470
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.2586872586872588e-05,
      "loss": 1.0279,
      "step": 480
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.2432432432432433e-05,
      "loss": 1.0187,
      "step": 490
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.227799227799228e-05,
      "loss": 1.015,
      "step": 500
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.2123552123552124e-05,
      "loss": 1.0165,
      "step": 510
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7894736842105263,
      "eval_loss": 1.0165094137191772,
      "eval_runtime": 57.5347,
      "eval_samples_per_second": 2.312,
      "eval_steps_per_second": 0.591,
      "step": 518
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.1969111969111971e-05,
      "loss": 1.0331,
      "step": 520
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.1814671814671816e-05,
      "loss": 1.0241,
      "step": 530
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.166023166023166e-05,
      "loss": 1.0185,
      "step": 540
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1505791505791506e-05,
      "loss": 1.0257,
      "step": 550
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.1351351351351352e-05,
      "loss": 1.0213,
      "step": 560
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.1196911196911197e-05,
      "loss": 1.0278,
      "step": 570
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.1042471042471044e-05,
      "loss": 1.0307,
      "step": 580
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.0888030888030889e-05,
      "loss": 1.0054,
      "step": 590
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.0733590733590735e-05,
      "loss": 1.0094,
      "step": 600
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.057915057915058e-05,
      "loss": 0.9994,
      "step": 610
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0424710424710425e-05,
      "loss": 1.0235,
      "step": 620
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.027027027027027e-05,
      "loss": 1.0063,
      "step": 630
    },
    {
      "epoch": 2.47,
      "learning_rate": 1.0115830115830117e-05,
      "loss": 0.9763,
      "step": 640
    },
    {
      "epoch": 2.51,
      "learning_rate": 9.961389961389962e-06,
      "loss": 1.0209,
      "step": 650
    },
    {
      "epoch": 2.55,
      "learning_rate": 9.806949806949808e-06,
      "loss": 0.998,
      "step": 660
    },
    {
      "epoch": 2.59,
      "learning_rate": 9.652509652509653e-06,
      "loss": 1.0063,
      "step": 670
    },
    {
      "epoch": 2.63,
      "learning_rate": 9.498069498069498e-06,
      "loss": 1.0366,
      "step": 680
    },
    {
      "epoch": 2.66,
      "learning_rate": 9.343629343629345e-06,
      "loss": 1.0004,
      "step": 690
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.189189189189191e-06,
      "loss": 1.0212,
      "step": 700
    },
    {
      "epoch": 2.74,
      "learning_rate": 9.034749034749034e-06,
      "loss": 1.002,
      "step": 710
    },
    {
      "epoch": 2.78,
      "learning_rate": 8.880308880308881e-06,
      "loss": 0.9824,
      "step": 720
    },
    {
      "epoch": 2.82,
      "learning_rate": 8.725868725868728e-06,
      "loss": 1.0043,
      "step": 730
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.9829,
      "step": 740
    },
    {
      "epoch": 2.9,
      "learning_rate": 8.416988416988418e-06,
      "loss": 0.9977,
      "step": 750
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.262548262548264e-06,
      "loss": 0.9996,
      "step": 760
    },
    {
      "epoch": 2.97,
      "learning_rate": 8.108108108108109e-06,
      "loss": 1.0113,
      "step": 770
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8045112781954887,
      "eval_loss": 0.9941034317016602,
      "eval_runtime": 57.8525,
      "eval_samples_per_second": 2.299,
      "eval_steps_per_second": 0.588,
      "step": 777
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.953667953667954e-06,
      "loss": 0.9685,
      "step": 780
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.7992277992278e-06,
      "loss": 0.998,
      "step": 790
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.644787644787645e-06,
      "loss": 0.9931,
      "step": 800
    },
    {
      "epoch": 3.13,
      "learning_rate": 7.49034749034749e-06,
      "loss": 0.9845,
      "step": 810
    },
    {
      "epoch": 3.17,
      "learning_rate": 7.335907335907336e-06,
      "loss": 0.9952,
      "step": 820
    },
    {
      "epoch": 3.2,
      "learning_rate": 7.181467181467182e-06,
      "loss": 0.9726,
      "step": 830
    },
    {
      "epoch": 3.24,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.9986,
      "step": 840
    },
    {
      "epoch": 3.28,
      "learning_rate": 6.872586872586873e-06,
      "loss": 0.9956,
      "step": 850
    },
    {
      "epoch": 3.32,
      "learning_rate": 6.718146718146718e-06,
      "loss": 1.0021,
      "step": 860
    },
    {
      "epoch": 3.36,
      "learning_rate": 6.563706563706564e-06,
      "loss": 0.9785,
      "step": 870
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.409266409266411e-06,
      "loss": 1.0007,
      "step": 880
    },
    {
      "epoch": 3.44,
      "learning_rate": 6.254826254826255e-06,
      "loss": 0.9712,
      "step": 890
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.1003861003861005e-06,
      "loss": 0.988,
      "step": 900
    },
    {
      "epoch": 3.51,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.9954,
      "step": 910
    },
    {
      "epoch": 3.55,
      "learning_rate": 5.791505791505791e-06,
      "loss": 0.9693,
      "step": 920
    },
    {
      "epoch": 3.59,
      "learning_rate": 5.637065637065637e-06,
      "loss": 1.0062,
      "step": 930
    },
    {
      "epoch": 3.63,
      "learning_rate": 5.4826254826254836e-06,
      "loss": 0.9875,
      "step": 940
    },
    {
      "epoch": 3.67,
      "learning_rate": 5.328185328185329e-06,
      "loss": 1.0029,
      "step": 950
    },
    {
      "epoch": 3.71,
      "learning_rate": 5.173745173745173e-06,
      "loss": 0.9766,
      "step": 960
    },
    {
      "epoch": 3.75,
      "learning_rate": 5.01930501930502e-06,
      "loss": 0.9875,
      "step": 970
    },
    {
      "epoch": 3.78,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.9631,
      "step": 980
    },
    {
      "epoch": 3.82,
      "learning_rate": 4.710424710424711e-06,
      "loss": 0.9838,
      "step": 990
    },
    {
      "epoch": 3.86,
      "learning_rate": 4.5559845559845564e-06,
      "loss": 0.9694,
      "step": 1000
    },
    {
      "epoch": 3.9,
      "learning_rate": 4.401544401544402e-06,
      "loss": 1.0125,
      "step": 1010
    },
    {
      "epoch": 3.94,
      "learning_rate": 4.247104247104247e-06,
      "loss": 0.9848,
      "step": 1020
    },
    {
      "epoch": 3.98,
      "learning_rate": 4.092664092664093e-06,
      "loss": 1.0067,
      "step": 1030
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8195488721804511,
      "eval_loss": 0.9804362654685974,
      "eval_runtime": 57.6615,
      "eval_samples_per_second": 2.307,
      "eval_steps_per_second": 0.59,
      "step": 1036
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.938223938223939e-06,
      "loss": 0.9862,
      "step": 1040
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.968,
      "step": 1050
    },
    {
      "epoch": 4.09,
      "learning_rate": 3.6293436293436297e-06,
      "loss": 0.9788,
      "step": 1060
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.4749034749034755e-06,
      "loss": 0.9988,
      "step": 1070
    },
    {
      "epoch": 4.17,
      "learning_rate": 3.320463320463321e-06,
      "loss": 0.9927,
      "step": 1080
    },
    {
      "epoch": 4.21,
      "learning_rate": 3.166023166023166e-06,
      "loss": 0.9883,
      "step": 1090
    },
    {
      "epoch": 4.25,
      "learning_rate": 3.011583011583012e-06,
      "loss": 0.9859,
      "step": 1100
    },
    {
      "epoch": 4.29,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.9918,
      "step": 1110
    },
    {
      "epoch": 4.32,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.9805,
      "step": 1120
    },
    {
      "epoch": 4.36,
      "learning_rate": 2.5482625482625484e-06,
      "loss": 0.9869,
      "step": 1130
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.393822393822394e-06,
      "loss": 1.0008,
      "step": 1140
    },
    {
      "epoch": 4.44,
      "learning_rate": 2.2393822393822394e-06,
      "loss": 0.9577,
      "step": 1150
    },
    {
      "epoch": 4.48,
      "learning_rate": 2.084942084942085e-06,
      "loss": 0.9531,
      "step": 1160
    },
    {
      "epoch": 4.52,
      "learning_rate": 1.9305019305019305e-06,
      "loss": 0.9739,
      "step": 1170
    },
    {
      "epoch": 4.56,
      "learning_rate": 1.7760617760617763e-06,
      "loss": 0.9914,
      "step": 1180
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.9602,
      "step": 1190
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.4671814671814674e-06,
      "loss": 0.9821,
      "step": 1200
    },
    {
      "epoch": 4.67,
      "learning_rate": 1.3127413127413127e-06,
      "loss": 0.9576,
      "step": 1210
    },
    {
      "epoch": 4.71,
      "learning_rate": 1.1583011583011585e-06,
      "loss": 0.9677,
      "step": 1220
    },
    {
      "epoch": 4.75,
      "learning_rate": 1.0038610038610038e-06,
      "loss": 0.9838,
      "step": 1230
    },
    {
      "epoch": 4.79,
      "learning_rate": 8.494208494208495e-07,
      "loss": 0.9762,
      "step": 1240
    },
    {
      "epoch": 4.83,
      "learning_rate": 6.94980694980695e-07,
      "loss": 0.9833,
      "step": 1250
    },
    {
      "epoch": 4.86,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.9839,
      "step": 1260
    },
    {
      "epoch": 4.9,
      "learning_rate": 3.8610038610038613e-07,
      "loss": 0.9802,
      "step": 1270
    },
    {
      "epoch": 4.94,
      "learning_rate": 2.3166023166023168e-07,
      "loss": 0.991,
      "step": 1280
    },
    {
      "epoch": 4.98,
      "learning_rate": 7.722007722007723e-08,
      "loss": 0.9746,
      "step": 1290
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8195488721804511,
      "eval_loss": 0.9759521484375,
      "eval_runtime": 60.3048,
      "eval_samples_per_second": 2.205,
      "eval_steps_per_second": 0.564,
      "step": 1295
    },
    {
      "epoch": 5.0,
      "step": 1295,
      "total_flos": 2.945297577944494e+18,
      "train_loss": 1.017018985011863,
      "train_runtime": 3198.9902,
      "train_samples_per_second": 1.616,
      "train_steps_per_second": 0.405
    }
  ],
  "max_steps": 1295,
  "num_train_epochs": 5,
  "total_flos": 2.945297577944494e+18,
  "trial_name": null,
  "trial_params": null
}