{
  "best_metric": 0.0682438537478447,
  "best_model_checkpoint": "finetune-apple-leaf/checkpoint-1045",
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 1045,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 68452.109375,
      "learning_rate": 1.980861244019139e-05,
      "loss": 1.5577,
      "step": 10
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 81296.0546875,
      "learning_rate": 1.9617224880382777e-05,
      "loss": 1.4263,
      "step": 20
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 91526.734375,
      "learning_rate": 1.9425837320574165e-05,
      "loss": 1.2775,
      "step": 30
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 82238.640625,
      "learning_rate": 1.9234449760765553e-05,
      "loss": 1.144,
      "step": 40
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 93808.3671875,
      "learning_rate": 1.904306220095694e-05,
      "loss": 0.9826,
      "step": 50
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 92552.0625,
      "learning_rate": 1.8851674641148328e-05,
      "loss": 0.834,
      "step": 60
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 97152.6953125,
      "learning_rate": 1.8660287081339713e-05,
      "loss": 0.7036,
      "step": 70
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 72807.1796875,
      "learning_rate": 1.8468899521531104e-05,
      "loss": 0.5867,
      "step": 80
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 80641.046875,
      "learning_rate": 1.8277511961722488e-05,
      "loss": 0.5116,
      "step": 90
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 88719.7265625,
      "learning_rate": 1.8086124401913876e-05,
      "loss": 0.4345,
      "step": 100
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 87248.7109375,
      "learning_rate": 1.7894736842105264e-05,
      "loss": 0.3765,
      "step": 110
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 74184.46875,
      "learning_rate": 1.770334928229665e-05,
      "loss": 0.3363,
      "step": 120
    },
    {
      "epoch": 0.6220095693779905,
      "grad_norm": 76457.8125,
      "learning_rate": 1.751196172248804e-05,
      "loss": 0.3341,
      "step": 130
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 59443.3984375,
      "learning_rate": 1.7320574162679427e-05,
      "loss": 0.2943,
      "step": 140
    },
    {
      "epoch": 0.7177033492822966,
      "grad_norm": 98078.953125,
      "learning_rate": 1.7129186602870815e-05,
      "loss": 0.2792,
      "step": 150
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 68582.828125,
      "learning_rate": 1.6937799043062203e-05,
      "loss": 0.2567,
      "step": 160
    },
    {
      "epoch": 0.8133971291866029,
      "grad_norm": 60306.1328125,
      "learning_rate": 1.674641148325359e-05,
      "loss": 0.2431,
      "step": 170
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 72700.328125,
      "learning_rate": 1.6555023923444978e-05,
      "loss": 0.2115,
      "step": 180
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 152611.125,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.222,
      "step": 190
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 61888.64453125,
      "learning_rate": 1.6172248803827754e-05,
      "loss": 0.1988,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9957482993197279,
      "eval_loss": 0.18814513087272644,
      "eval_runtime": 39.0452,
      "eval_samples_per_second": 60.238,
      "eval_steps_per_second": 0.948,
      "step": 209
    },
    {
      "epoch": 1.0047846889952152,
      "grad_norm": 93927.0234375,
      "learning_rate": 1.5980861244019138e-05,
      "loss": 0.215,
      "step": 210
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 50695.28125,
      "learning_rate": 1.578947368421053e-05,
      "loss": 0.1936,
      "step": 220
    },
    {
      "epoch": 1.1004784688995215,
      "grad_norm": 150133.75,
      "learning_rate": 1.5598086124401914e-05,
      "loss": 0.1818,
      "step": 230
    },
    {
      "epoch": 1.1483253588516746,
      "grad_norm": 91581.5078125,
      "learning_rate": 1.5406698564593305e-05,
      "loss": 0.1819,
      "step": 240
    },
    {
      "epoch": 1.1961722488038278,
      "grad_norm": 53073.0234375,
      "learning_rate": 1.5215311004784689e-05,
      "loss": 0.1618,
      "step": 250
    },
    {
      "epoch": 1.244019138755981,
      "grad_norm": 112323.625,
      "learning_rate": 1.5023923444976079e-05,
      "loss": 0.165,
      "step": 260
    },
    {
      "epoch": 1.291866028708134,
      "grad_norm": 97414.734375,
      "learning_rate": 1.4832535885167465e-05,
      "loss": 0.2017,
      "step": 270
    },
    {
      "epoch": 1.339712918660287,
      "grad_norm": 162907.59375,
      "learning_rate": 1.4641148325358854e-05,
      "loss": 0.1762,
      "step": 280
    },
    {
      "epoch": 1.38755980861244,
      "grad_norm": 27552.251953125,
      "learning_rate": 1.444976076555024e-05,
      "loss": 0.1715,
      "step": 290
    },
    {
      "epoch": 1.4354066985645932,
      "grad_norm": 108859.3671875,
      "learning_rate": 1.4258373205741626e-05,
      "loss": 0.153,
      "step": 300
    },
    {
      "epoch": 1.4832535885167464,
      "grad_norm": 73719.96875,
      "learning_rate": 1.4066985645933016e-05,
      "loss": 0.14,
      "step": 310
    },
    {
      "epoch": 1.5311004784688995,
      "grad_norm": 21314.03125,
      "learning_rate": 1.3875598086124402e-05,
      "loss": 0.1354,
      "step": 320
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 58937.32421875,
      "learning_rate": 1.3684210526315791e-05,
      "loss": 0.1389,
      "step": 330
    },
    {
      "epoch": 1.6267942583732058,
      "grad_norm": 56629.7578125,
      "learning_rate": 1.3492822966507177e-05,
      "loss": 0.1402,
      "step": 340
    },
    {
      "epoch": 1.674641148325359,
      "grad_norm": 59540.6953125,
      "learning_rate": 1.3301435406698567e-05,
      "loss": 0.1347,
      "step": 350
    },
    {
      "epoch": 1.722488038277512,
      "grad_norm": 81783.2421875,
      "learning_rate": 1.3110047846889953e-05,
      "loss": 0.1448,
      "step": 360
    },
    {
      "epoch": 1.7703349282296652,
      "grad_norm": 90950.421875,
      "learning_rate": 1.2918660287081342e-05,
      "loss": 0.1503,
      "step": 370
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 149309.421875,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.1464,
      "step": 380
    },
    {
      "epoch": 1.8660287081339713,
      "grad_norm": 83194.9375,
      "learning_rate": 1.2535885167464116e-05,
      "loss": 0.1394,
      "step": 390
    },
    {
      "epoch": 1.9138755980861244,
      "grad_norm": 124922.578125,
      "learning_rate": 1.2344497607655504e-05,
      "loss": 0.1245,
      "step": 400
    },
    {
      "epoch": 1.9617224880382775,
      "grad_norm": 52044.2578125,
      "learning_rate": 1.215311004784689e-05,
      "loss": 0.1012,
      "step": 410
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9953231292517006,
      "eval_loss": 0.1110498234629631,
      "eval_runtime": 39.4692,
      "eval_samples_per_second": 59.591,
      "eval_steps_per_second": 0.937,
      "step": 418
    },
    {
      "epoch": 2.0095693779904304,
      "grad_norm": 78857.1328125,
      "learning_rate": 1.196172248803828e-05,
      "loss": 0.1258,
      "step": 420
    },
    {
      "epoch": 2.0574162679425836,
      "grad_norm": 74979.1796875,
      "learning_rate": 1.1770334928229666e-05,
      "loss": 0.1325,
      "step": 430
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 85820.78125,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 0.1231,
      "step": 440
    },
    {
      "epoch": 2.15311004784689,
      "grad_norm": 58782.41015625,
      "learning_rate": 1.1387559808612441e-05,
      "loss": 0.1282,
      "step": 450
    },
    {
      "epoch": 2.200956937799043,
      "grad_norm": 21210.45703125,
      "learning_rate": 1.1196172248803829e-05,
      "loss": 0.1087,
      "step": 460
    },
    {
      "epoch": 2.248803827751196,
      "grad_norm": 80271.7265625,
      "learning_rate": 1.1004784688995217e-05,
      "loss": 0.1192,
      "step": 470
    },
    {
      "epoch": 2.2966507177033493,
      "grad_norm": 32322.310546875,
      "learning_rate": 1.0813397129186604e-05,
      "loss": 0.1098,
      "step": 480
    },
    {
      "epoch": 2.3444976076555024,
      "grad_norm": 113407.7578125,
      "learning_rate": 1.062200956937799e-05,
      "loss": 0.1216,
      "step": 490
    },
    {
      "epoch": 2.3923444976076556,
      "grad_norm": 194755.9375,
      "learning_rate": 1.0430622009569378e-05,
      "loss": 0.116,
      "step": 500
    },
    {
      "epoch": 2.4401913875598087,
      "grad_norm": 23810.296875,
      "learning_rate": 1.0239234449760766e-05,
      "loss": 0.1026,
      "step": 510
    },
    {
      "epoch": 2.488038277511962,
      "grad_norm": 49451.3125,
      "learning_rate": 1.0047846889952154e-05,
      "loss": 0.1217,
      "step": 520
    },
    {
      "epoch": 2.535885167464115,
      "grad_norm": 85535.9609375,
      "learning_rate": 9.856459330143542e-06,
      "loss": 0.1324,
      "step": 530
    },
    {
      "epoch": 2.583732057416268,
      "grad_norm": 77596.9453125,
      "learning_rate": 9.66507177033493e-06,
      "loss": 0.1154,
      "step": 540
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 196213.265625,
      "learning_rate": 9.473684210526315e-06,
      "loss": 0.1234,
      "step": 550
    },
    {
      "epoch": 2.679425837320574,
      "grad_norm": 129738.171875,
      "learning_rate": 9.282296650717703e-06,
      "loss": 0.0983,
      "step": 560
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 123404.078125,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.1187,
      "step": 570
    },
    {
      "epoch": 2.77511961722488,
      "grad_norm": 163260.46875,
      "learning_rate": 8.899521531100479e-06,
      "loss": 0.1145,
      "step": 580
    },
    {
      "epoch": 2.8229665071770333,
      "grad_norm": 92286.703125,
      "learning_rate": 8.708133971291867e-06,
      "loss": 0.1001,
      "step": 590
    },
    {
      "epoch": 2.8708133971291865,
      "grad_norm": 107133.9375,
      "learning_rate": 8.516746411483254e-06,
      "loss": 0.0953,
      "step": 600
    },
    {
      "epoch": 2.9186602870813396,
      "grad_norm": 52350.8359375,
      "learning_rate": 8.325358851674642e-06,
      "loss": 0.0981,
      "step": 610
    },
    {
      "epoch": 2.9665071770334928,
      "grad_norm": 33242.46875,
      "learning_rate": 8.13397129186603e-06,
      "loss": 0.1171,
      "step": 620
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9927721088435374,
      "eval_loss": 0.0925019159913063,
      "eval_runtime": 39.5447,
      "eval_samples_per_second": 59.477,
      "eval_steps_per_second": 0.936,
      "step": 627
    },
    {
      "epoch": 3.014354066985646,
      "grad_norm": 24220.681640625,
      "learning_rate": 7.942583732057418e-06,
      "loss": 0.0879,
      "step": 630
    },
    {
      "epoch": 3.062200956937799,
      "grad_norm": 161409.765625,
      "learning_rate": 7.751196172248805e-06,
      "loss": 0.098,
      "step": 640
    },
    {
      "epoch": 3.110047846889952,
      "grad_norm": 137376.515625,
      "learning_rate": 7.5598086124401915e-06,
      "loss": 0.0991,
      "step": 650
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 17668.015625,
      "learning_rate": 7.368421052631579e-06,
      "loss": 0.0898,
      "step": 660
    },
    {
      "epoch": 3.2057416267942584,
      "grad_norm": 168850.53125,
      "learning_rate": 7.177033492822967e-06,
      "loss": 0.0787,
      "step": 670
    },
    {
      "epoch": 3.2535885167464116,
      "grad_norm": 24098.3203125,
      "learning_rate": 6.985645933014355e-06,
      "loss": 0.1136,
      "step": 680
    },
    {
      "epoch": 3.3014354066985647,
      "grad_norm": 184889.9375,
      "learning_rate": 6.794258373205742e-06,
      "loss": 0.0899,
      "step": 690
    },
    {
      "epoch": 3.349282296650718,
      "grad_norm": 154068.140625,
      "learning_rate": 6.6028708133971295e-06,
      "loss": 0.072,
      "step": 700
    },
    {
      "epoch": 3.397129186602871,
      "grad_norm": 213492.796875,
      "learning_rate": 6.411483253588517e-06,
      "loss": 0.095,
      "step": 710
    },
    {
      "epoch": 3.444976076555024,
      "grad_norm": 79102.0859375,
      "learning_rate": 6.220095693779905e-06,
      "loss": 0.0852,
      "step": 720
    },
    {
      "epoch": 3.492822966507177,
      "grad_norm": 158182.59375,
      "learning_rate": 6.028708133971293e-06,
      "loss": 0.079,
      "step": 730
    },
    {
      "epoch": 3.5406698564593304,
      "grad_norm": 12833.8759765625,
      "learning_rate": 5.837320574162681e-06,
      "loss": 0.0881,
      "step": 740
    },
    {
      "epoch": 3.588516746411483,
      "grad_norm": 124951.265625,
      "learning_rate": 5.645933014354067e-06,
      "loss": 0.0963,
      "step": 750
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 207838.703125,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.0967,
      "step": 760
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 15068.2353515625,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.081,
      "step": 770
    },
    {
      "epoch": 3.7320574162679425,
      "grad_norm": 20366.380859375,
      "learning_rate": 5.07177033492823e-06,
      "loss": 0.0824,
      "step": 780
    },
    {
      "epoch": 3.7799043062200957,
      "grad_norm": 11184.1630859375,
      "learning_rate": 4.880382775119618e-06,
      "loss": 0.1021,
      "step": 790
    },
    {
      "epoch": 3.827751196172249,
      "grad_norm": 41858.83203125,
      "learning_rate": 4.6889952153110055e-06,
      "loss": 0.071,
      "step": 800
    },
    {
      "epoch": 3.875598086124402,
      "grad_norm": 11330.4501953125,
      "learning_rate": 4.4976076555023925e-06,
      "loss": 0.0725,
      "step": 810
    },
    {
      "epoch": 3.923444976076555,
      "grad_norm": 143718.625,
      "learning_rate": 4.30622009569378e-06,
      "loss": 0.0938,
      "step": 820
    },
    {
      "epoch": 3.971291866028708,
      "grad_norm": 89987.9453125,
      "learning_rate": 4.114832535885168e-06,
      "loss": 0.0766,
      "step": 830
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9965986394557823,
      "eval_loss": 0.07070581614971161,
      "eval_runtime": 39.4603,
      "eval_samples_per_second": 59.604,
      "eval_steps_per_second": 0.938,
      "step": 836
    },
    {
      "epoch": 4.019138755980861,
      "grad_norm": 57436.94140625,
      "learning_rate": 3.923444976076555e-06,
      "loss": 0.0945,
      "step": 840
    },
    {
      "epoch": 4.0669856459330145,
      "grad_norm": 40826.1953125,
      "learning_rate": 3.732057416267943e-06,
      "loss": 0.0743,
      "step": 850
    },
    {
      "epoch": 4.114832535885167,
      "grad_norm": 29963.001953125,
      "learning_rate": 3.5406698564593305e-06,
      "loss": 0.0962,
      "step": 860
    },
    {
      "epoch": 4.162679425837321,
      "grad_norm": 32081.44921875,
      "learning_rate": 3.3492822966507182e-06,
      "loss": 0.0883,
      "step": 870
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 65598.9375,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.0753,
      "step": 880
    },
    {
      "epoch": 4.258373205741627,
      "grad_norm": 72391.234375,
      "learning_rate": 2.966507177033493e-06,
      "loss": 0.0764,
      "step": 890
    },
    {
      "epoch": 4.30622009569378,
      "grad_norm": 82336.0625,
      "learning_rate": 2.7751196172248807e-06,
      "loss": 0.0594,
      "step": 900
    },
    {
      "epoch": 4.354066985645933,
      "grad_norm": 126016.4609375,
      "learning_rate": 2.5837320574162685e-06,
      "loss": 0.0782,
      "step": 910
    },
    {
      "epoch": 4.401913875598086,
      "grad_norm": 10192.6044921875,
      "learning_rate": 2.392344497607656e-06,
      "loss": 0.0705,
      "step": 920
    },
    {
      "epoch": 4.44976076555024,
      "grad_norm": 226228.453125,
      "learning_rate": 2.200956937799043e-06,
      "loss": 0.0793,
      "step": 930
    },
    {
      "epoch": 4.497607655502392,
      "grad_norm": 11644.4921875,
      "learning_rate": 2.0095693779904305e-06,
      "loss": 0.0687,
      "step": 940
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 71224.4609375,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.0626,
      "step": 950
    },
    {
      "epoch": 4.5933014354066986,
      "grad_norm": 15732.5244140625,
      "learning_rate": 1.6267942583732059e-06,
      "loss": 0.0764,
      "step": 960
    },
    {
      "epoch": 4.641148325358852,
      "grad_norm": 49954.69921875,
      "learning_rate": 1.4354066985645934e-06,
      "loss": 0.0941,
      "step": 970
    },
    {
      "epoch": 4.688995215311005,
      "grad_norm": 196565.375,
      "learning_rate": 1.244019138755981e-06,
      "loss": 0.0802,
      "step": 980
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 29685.708984375,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.0656,
      "step": 990
    },
    {
      "epoch": 4.784688995215311,
      "grad_norm": 31311.546875,
      "learning_rate": 8.612440191387561e-07,
      "loss": 0.0908,
      "step": 1000
    },
    {
      "epoch": 4.832535885167464,
      "grad_norm": 75467.4765625,
      "learning_rate": 6.698564593301436e-07,
      "loss": 0.0755,
      "step": 1010
    },
    {
      "epoch": 4.880382775119617,
      "grad_norm": 51163.75390625,
      "learning_rate": 4.784688995215311e-07,
      "loss": 0.0836,
      "step": 1020
    },
    {
      "epoch": 4.92822966507177,
      "grad_norm": 180410.21875,
      "learning_rate": 2.870813397129187e-07,
      "loss": 0.0815,
      "step": 1030
    },
    {
      "epoch": 4.976076555023924,
      "grad_norm": 187452.96875,
      "learning_rate": 9.569377990430622e-08,
      "loss": 0.0723,
      "step": 1040
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9957482993197279,
      "eval_loss": 0.0682438537478447,
      "eval_runtime": 38.7752,
      "eval_samples_per_second": 60.657,
      "eval_steps_per_second": 0.954,
      "step": 1045
    },
    {
      "epoch": 5.0,
      "step": 1045,
      "total_flos": 5.1638175692258e+18,
      "train_loss": 0.20529093819371821,
      "train_runtime": 2500.4647,
      "train_samples_per_second": 26.649,
      "train_steps_per_second": 0.418
    }
  ],
  "logging_steps": 10,
  "max_steps": 1045,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1638175692258e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}