{
  "best_metric": 0.8191489361702128,
  "best_model_checkpoint": "videomae-base-finetuned-movienet-take2/checkpoint-1302",
  "epoch": 9.010135135135135,
  "global_step": 1704,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.6891891891891894e-06,
      "loss": 1.6719,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.3783783783783788e-06,
      "loss": 1.6396,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.067567567567568e-06,
      "loss": 1.5972,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 1.598,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.445945945945946e-06,
      "loss": 1.596,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0135135135135136e-05,
      "loss": 1.568,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1824324324324325e-05,
      "loss": 1.5668,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 1.5481,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5202702702702704e-05,
      "loss": 1.5096,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6891891891891892e-05,
      "loss": 1.5268,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8581081081081082e-05,
      "loss": 1.5309,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0270270270270273e-05,
      "loss": 1.4613,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.195945945945946e-05,
      "loss": 1.4655,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.364864864864865e-05,
      "loss": 1.1861,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.533783783783784e-05,
      "loss": 1.2159,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.702702702702703e-05,
      "loss": 1.0353,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.8716216216216217e-05,
      "loss": 1.0126,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.0405405405405407e-05,
      "loss": 1.0917,
      "step": 180
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5425531914893617,
      "eval_loss": 1.008441686630249,
      "eval_runtime": 325.3141,
      "eval_samples_per_second": 0.578,
      "eval_steps_per_second": 0.074,
      "step": 186
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.20945945945946e-05,
      "loss": 0.9827,
      "step": 190
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.9337,
      "step": 200
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.547297297297297e-05,
      "loss": 0.9799,
      "step": 210
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.7162162162162165e-05,
      "loss": 0.8158,
      "step": 220
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.885135135135135e-05,
      "loss": 0.791,
      "step": 230
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 1.0988,
      "step": 240
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.222972972972973e-05,
      "loss": 0.934,
      "step": 250
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.391891891891892e-05,
      "loss": 0.8967,
      "step": 260
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.560810810810811e-05,
      "loss": 0.9449,
      "step": 270
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.72972972972973e-05,
      "loss": 0.7262,
      "step": 280
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.8986486486486486e-05,
      "loss": 0.8733,
      "step": 290
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.9924924924924924e-05,
      "loss": 0.7646,
      "step": 300
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.973723723723724e-05,
      "loss": 0.6704,
      "step": 310
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.954954954954955e-05,
      "loss": 0.8049,
      "step": 320
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.9361861861861864e-05,
      "loss": 0.6962,
      "step": 330
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.9174174174174175e-05,
      "loss": 0.6775,
      "step": 340
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.8986486486486486e-05,
      "loss": 0.6874,
      "step": 350
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.87987987987988e-05,
      "loss": 0.7424,
      "step": 360
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.7221,
      "step": 370
    },
    {
      "epoch": 1.06,
      "eval_accuracy": 0.7180851063829787,
      "eval_loss": 0.6874406933784485,
      "eval_runtime": 140.1323,
      "eval_samples_per_second": 1.342,
      "eval_steps_per_second": 0.171,
      "step": 372
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8423423423423426e-05,
      "loss": 0.4945,
      "step": 380
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.823573573573574e-05,
      "loss": 0.493,
      "step": 390
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.804804804804805e-05,
      "loss": 0.7461,
      "step": 400
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.786036036036036e-05,
      "loss": 0.4885,
      "step": 410
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.767267267267268e-05,
      "loss": 0.6439,
      "step": 420
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.748498498498499e-05,
      "loss": 0.6739,
      "step": 430
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.72972972972973e-05,
      "loss": 0.5467,
      "step": 440
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.710960960960961e-05,
      "loss": 0.6623,
      "step": 450
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.692192192192192e-05,
      "loss": 0.4457,
      "step": 460
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.673423423423424e-05,
      "loss": 0.4094,
      "step": 470
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.654654654654655e-05,
      "loss": 0.5707,
      "step": 480
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.635885885885886e-05,
      "loss": 0.5932,
      "step": 490
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.617117117117117e-05,
      "loss": 0.5556,
      "step": 500
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.5983483483483484e-05,
      "loss": 0.6922,
      "step": 510
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.57957957957958e-05,
      "loss": 0.5235,
      "step": 520
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.560810810810811e-05,
      "loss": 0.5206,
      "step": 530
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.5420420420420424e-05,
      "loss": 0.5925,
      "step": 540
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.5232732732732735e-05,
      "loss": 0.5015,
      "step": 550
    },
    {
      "epoch": 2.06,
      "eval_accuracy": 0.675531914893617,
      "eval_loss": 0.8818714022636414,
      "eval_runtime": 139.1461,
      "eval_samples_per_second": 1.351,
      "eval_steps_per_second": 0.172,
      "step": 558
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 0.9722,
      "step": 560
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.4857357357357364e-05,
      "loss": 0.3877,
      "step": 570
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.4669669669669675e-05,
      "loss": 0.4829,
      "step": 580
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.4481981981981986e-05,
      "loss": 0.4713,
      "step": 590
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.42942942942943e-05,
      "loss": 0.3729,
      "step": 600
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.410660660660661e-05,
      "loss": 0.3128,
      "step": 610
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.391891891891892e-05,
      "loss": 0.553,
      "step": 620
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.373123123123124e-05,
      "loss": 0.4738,
      "step": 630
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.354354354354355e-05,
      "loss": 0.3917,
      "step": 640
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.335585585585586e-05,
      "loss": 0.3353,
      "step": 650
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.316816816816817e-05,
      "loss": 0.4164,
      "step": 660
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.298048048048048e-05,
      "loss": 0.4818,
      "step": 670
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.27927927927928e-05,
      "loss": 0.4163,
      "step": 680
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.260510510510511e-05,
      "loss": 0.338,
      "step": 690
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.241741741741742e-05,
      "loss": 0.3834,
      "step": 700
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.222972972972973e-05,
      "loss": 0.3242,
      "step": 710
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.204204204204204e-05,
      "loss": 0.3029,
      "step": 720
    },
    {
      "epoch": 3.06,
      "learning_rate": 4.185435435435436e-05,
      "loss": 0.483,
      "step": 730
    },
    {
      "epoch": 3.06,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.3678,
      "step": 740
    },
    {
      "epoch": 3.06,
      "eval_accuracy": 0.7553191489361702,
      "eval_loss": 0.6245753765106201,
      "eval_runtime": 110.5708,
      "eval_samples_per_second": 1.7,
      "eval_steps_per_second": 0.217,
      "step": 744
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.147897897897898e-05,
      "loss": 0.4088,
      "step": 750
    },
    {
      "epoch": 4.01,
      "learning_rate": 4.1291291291291294e-05,
      "loss": 0.2268,
      "step": 760
    },
    {
      "epoch": 4.01,
      "learning_rate": 4.1103603603603605e-05,
      "loss": 0.2889,
      "step": 770
    },
    {
      "epoch": 4.01,
      "learning_rate": 4.091591591591592e-05,
      "loss": 0.3062,
      "step": 780
    },
    {
      "epoch": 4.02,
      "learning_rate": 4.0728228228228234e-05,
      "loss": 0.2331,
      "step": 790
    },
    {
      "epoch": 4.02,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 0.2727,
      "step": 800
    },
    {
      "epoch": 4.02,
      "learning_rate": 4.0352852852852856e-05,
      "loss": 0.0624,
      "step": 810
    },
    {
      "epoch": 4.03,
      "learning_rate": 4.016516516516517e-05,
      "loss": 0.2055,
      "step": 820
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.9977477477477485e-05,
      "loss": 0.389,
      "step": 830
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.9789789789789796e-05,
      "loss": 0.3561,
      "step": 840
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.960210210210211e-05,
      "loss": 0.1887,
      "step": 850
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.941441441441442e-05,
      "loss": 0.3762,
      "step": 860
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.922672672672673e-05,
      "loss": 0.3079,
      "step": 870
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.903903903903904e-05,
      "loss": 0.3228,
      "step": 880
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.885135135135135e-05,
      "loss": 0.3692,
      "step": 890
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.866366366366366e-05,
      "loss": 0.2801,
      "step": 900
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.8475975975975974e-05,
      "loss": 0.1766,
      "step": 910
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.8288288288288285e-05,
      "loss": 0.1004,
      "step": 920
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.81006006006006e-05,
      "loss": 0.2759,
      "step": 930
    },
    {
      "epoch": 4.06,
      "eval_accuracy": 0.7606382978723404,
      "eval_loss": 0.9069157242774963,
      "eval_runtime": 111.6385,
      "eval_samples_per_second": 1.684,
      "eval_steps_per_second": 0.215,
      "step": 930
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.7912912912912914e-05,
      "loss": 0.0877,
      "step": 940
    },
    {
      "epoch": 5.01,
      "learning_rate": 3.7725225225225225e-05,
      "loss": 0.2627,
      "step": 950
    },
    {
      "epoch": 5.01,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.1291,
      "step": 960
    },
    {
      "epoch": 5.01,
      "learning_rate": 3.734984984984985e-05,
      "loss": 0.2871,
      "step": 970
    },
    {
      "epoch": 5.02,
      "learning_rate": 3.7162162162162165e-05,
      "loss": 0.4653,
      "step": 980
    },
    {
      "epoch": 5.02,
      "learning_rate": 3.6974474474474476e-05,
      "loss": 0.2982,
      "step": 990
    },
    {
      "epoch": 5.02,
      "learning_rate": 3.678678678678679e-05,
      "loss": 0.2621,
      "step": 1000
    },
    {
      "epoch": 5.03,
      "learning_rate": 3.65990990990991e-05,
      "loss": 0.1349,
      "step": 1010
    },
    {
      "epoch": 5.03,
      "learning_rate": 3.641141141141141e-05,
      "loss": 0.1245,
      "step": 1020
    },
    {
      "epoch": 5.03,
      "learning_rate": 3.622372372372373e-05,
      "loss": 0.1143,
      "step": 1030
    },
    {
      "epoch": 5.04,
      "learning_rate": 3.603603603603604e-05,
      "loss": 0.2005,
      "step": 1040
    },
    {
      "epoch": 5.04,
      "learning_rate": 3.584834834834835e-05,
      "loss": 0.1979,
      "step": 1050
    },
    {
      "epoch": 5.04,
      "learning_rate": 3.566066066066066e-05,
      "loss": 0.3614,
      "step": 1060
    },
    {
      "epoch": 5.05,
      "learning_rate": 3.547297297297297e-05,
      "loss": 0.217,
      "step": 1070
    },
    {
      "epoch": 5.05,
      "learning_rate": 3.528528528528528e-05,
      "loss": 0.3563,
      "step": 1080
    },
    {
      "epoch": 5.05,
      "learning_rate": 3.50975975975976e-05,
      "loss": 0.355,
      "step": 1090
    },
    {
      "epoch": 5.06,
      "learning_rate": 3.490990990990991e-05,
      "loss": 0.239,
      "step": 1100
    },
    {
      "epoch": 5.06,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.3954,
      "step": 1110
    },
    {
      "epoch": 5.06,
      "eval_accuracy": 0.7659574468085106,
      "eval_loss": 0.8444852828979492,
      "eval_runtime": 128.1344,
      "eval_samples_per_second": 1.467,
      "eval_steps_per_second": 0.187,
      "step": 1116
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.453453453453453e-05,
      "loss": 0.279,
      "step": 1120
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.4346846846846844e-05,
      "loss": 0.0194,
      "step": 1130
    },
    {
      "epoch": 6.01,
      "learning_rate": 3.415915915915916e-05,
      "loss": 0.0181,
      "step": 1140
    },
    {
      "epoch": 6.01,
      "learning_rate": 3.397147147147147e-05,
      "loss": 0.0482,
      "step": 1150
    },
    {
      "epoch": 6.01,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.1143,
      "step": 1160
    },
    {
      "epoch": 6.02,
      "learning_rate": 3.3596096096096095e-05,
      "loss": 0.0299,
      "step": 1170
    },
    {
      "epoch": 6.02,
      "learning_rate": 3.3408408408408406e-05,
      "loss": 0.0741,
      "step": 1180
    },
    {
      "epoch": 6.03,
      "learning_rate": 3.3220720720720724e-05,
      "loss": 0.2265,
      "step": 1190
    },
    {
      "epoch": 6.03,
      "learning_rate": 3.3033033033033035e-05,
      "loss": 0.1181,
      "step": 1200
    },
    {
      "epoch": 6.03,
      "learning_rate": 3.2845345345345346e-05,
      "loss": 0.2526,
      "step": 1210
    },
    {
      "epoch": 6.04,
      "learning_rate": 3.265765765765766e-05,
      "loss": 0.206,
      "step": 1220
    },
    {
      "epoch": 6.04,
      "learning_rate": 3.246996996996997e-05,
      "loss": 0.2485,
      "step": 1230
    },
    {
      "epoch": 6.04,
      "learning_rate": 3.2282282282282286e-05,
      "loss": 0.0098,
      "step": 1240
    },
    {
      "epoch": 6.05,
      "learning_rate": 3.20945945945946e-05,
      "loss": 0.0529,
      "step": 1250
    },
    {
      "epoch": 6.05,
      "learning_rate": 3.190690690690691e-05,
      "loss": 0.3244,
      "step": 1260
    },
    {
      "epoch": 6.05,
      "learning_rate": 3.171921921921922e-05,
      "loss": 0.3008,
      "step": 1270
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.153153153153153e-05,
      "loss": 0.2757,
      "step": 1280
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.134384384384385e-05,
      "loss": 0.2518,
      "step": 1290
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.115615615615616e-05,
      "loss": 0.0327,
      "step": 1300
    },
    {
      "epoch": 6.06,
      "eval_accuracy": 0.8191489361702128,
      "eval_loss": 0.8311583995819092,
      "eval_runtime": 149.5054,
      "eval_samples_per_second": 1.257,
      "eval_steps_per_second": 0.161,
      "step": 1302
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.096846846846847e-05,
      "loss": 0.1377,
      "step": 1310
    },
    {
      "epoch": 7.01,
      "learning_rate": 3.078078078078078e-05,
      "loss": 0.191,
      "step": 1320
    },
    {
      "epoch": 7.01,
      "learning_rate": 3.059309309309309e-05,
      "loss": 0.085,
      "step": 1330
    },
    {
      "epoch": 7.01,
      "learning_rate": 3.0405405405405407e-05,
      "loss": 0.0236,
      "step": 1340
    },
    {
      "epoch": 7.02,
      "learning_rate": 3.0217717717717718e-05,
      "loss": 0.0419,
      "step": 1350
    },
    {
      "epoch": 7.02,
      "learning_rate": 3.0030030030030033e-05,
      "loss": 0.1571,
      "step": 1360
    },
    {
      "epoch": 7.02,
      "learning_rate": 2.9842342342342344e-05,
      "loss": 0.0076,
      "step": 1370
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.9654654654654658e-05,
      "loss": 0.0132,
      "step": 1380
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.946696696696697e-05,
      "loss": 0.1189,
      "step": 1390
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.927927927927928e-05,
      "loss": 0.0322,
      "step": 1400
    },
    {
      "epoch": 7.04,
      "learning_rate": 2.9091591591591595e-05,
      "loss": 0.0019,
      "step": 1410
    },
    {
      "epoch": 7.04,
      "learning_rate": 2.8903903903903906e-05,
      "loss": 0.0816,
      "step": 1420
    },
    {
      "epoch": 7.04,
      "learning_rate": 2.8716216216216217e-05,
      "loss": 0.1199,
      "step": 1430
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.852852852852853e-05,
      "loss": 0.1295,
      "step": 1440
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.8340840840840843e-05,
      "loss": 0.0567,
      "step": 1450
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.8153153153153157e-05,
      "loss": 0.0828,
      "step": 1460
    },
    {
      "epoch": 7.06,
      "learning_rate": 2.7965465465465468e-05,
      "loss": 0.0826,
      "step": 1470
    },
    {
      "epoch": 7.06,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.059,
      "step": 1480
    },
    {
      "epoch": 7.06,
      "eval_accuracy": 0.7872340425531915,
      "eval_loss": 1.1619175672531128,
      "eval_runtime": 117.2087,
      "eval_samples_per_second": 1.604,
      "eval_steps_per_second": 0.205,
      "step": 1488
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.7590090090090094e-05,
      "loss": 0.0026,
      "step": 1490
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.7402402402402405e-05,
      "loss": 0.1052,
      "step": 1500
    },
    {
      "epoch": 8.01,
      "learning_rate": 2.721471471471472e-05,
      "loss": 0.0362,
      "step": 1510
    },
    {
      "epoch": 8.01,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.0663,
      "step": 1520
    },
    {
      "epoch": 8.01,
      "learning_rate": 2.683933933933934e-05,
      "loss": 0.0092,
      "step": 1530
    },
    {
      "epoch": 8.02,
      "learning_rate": 2.6651651651651656e-05,
      "loss": 0.0325,
      "step": 1540
    },
    {
      "epoch": 8.02,
      "learning_rate": 2.6463963963963967e-05,
      "loss": 0.0014,
      "step": 1550
    },
    {
      "epoch": 8.02,
      "learning_rate": 2.6276276276276278e-05,
      "loss": 0.2578,
      "step": 1560
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.6088588588588592e-05,
      "loss": 0.0899,
      "step": 1570
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.5900900900900903e-05,
      "loss": 0.154,
      "step": 1580
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.5713213213213218e-05,
      "loss": 0.0036,
      "step": 1590
    },
    {
      "epoch": 8.04,
      "learning_rate": 2.552552552552553e-05,
      "loss": 0.0216,
      "step": 1600
    },
    {
      "epoch": 8.04,
      "learning_rate": 2.533783783783784e-05,
      "loss": 0.0871,
      "step": 1610
    },
    {
      "epoch": 8.04,
      "learning_rate": 2.5150150150150154e-05,
      "loss": 0.0168,
      "step": 1620
    },
    {
      "epoch": 8.05,
      "learning_rate": 2.4962462462462462e-05,
      "loss": 0.0016,
      "step": 1630
    },
    {
      "epoch": 8.05,
      "learning_rate": 2.4774774774774777e-05,
      "loss": 0.0011,
      "step": 1640
    },
    {
      "epoch": 8.05,
      "learning_rate": 2.4587087087087088e-05,
      "loss": 0.0011,
      "step": 1650
    },
    {
      "epoch": 8.06,
      "learning_rate": 2.43993993993994e-05,
      "loss": 0.0504,
      "step": 1660
    },
    {
      "epoch": 8.06,
      "learning_rate": 2.4211711711711713e-05,
      "loss": 0.0032,
      "step": 1670
    },
    {
      "epoch": 8.06,
      "eval_accuracy": 0.8031914893617021,
      "eval_loss": 1.1739730834960938,
      "eval_runtime": 123.2699,
      "eval_samples_per_second": 1.525,
      "eval_steps_per_second": 0.195,
      "step": 1674
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.4024024024024024e-05,
      "loss": 0.001,
      "step": 1680
    },
    {
      "epoch": 9.01,
      "learning_rate": 2.383633633633634e-05,
      "loss": 0.0105,
      "step": 1690
    },
    {
      "epoch": 9.01,
      "learning_rate": 2.364864864864865e-05,
      "loss": 0.1208,
      "step": 1700
    },
    {
      "epoch": 9.01,
      "eval_accuracy": 0.796875,
      "eval_loss": 1.0793333053588867,
      "eval_runtime": 292.2482,
      "eval_samples_per_second": 0.657,
      "eval_steps_per_second": 0.082,
      "step": 1704
    },
    {
      "epoch": 9.01,
      "eval_accuracy": 0.796875,
      "eval_loss": 1.0793333053588867,
      "eval_runtime": 131.1948,
      "eval_samples_per_second": 1.463,
      "eval_steps_per_second": 0.183,
      "step": 1704
    }
  ],
  "max_steps": 2960,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.6868427640627692e+19,
  "trial_name": null,
  "trial_params": null
}