{
  "best_metric": 0.5603644646924829,
  "best_model_checkpoint": "videomae-base-fatigue-detection-full/checkpoint-1800",
  "epoch": 2.3325193325193325,
  "eval_steps": 200,
  "global_step": 2457,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0325203252032523e-06,
      "loss": 1.0932,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.0650406504065046e-06,
      "loss": 1.071,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.0975609756097564e-06,
      "loss": 1.0823,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.130081300813009e-06,
      "loss": 1.065,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.016260162601626e-05,
      "loss": 0.9151,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2195121951219513e-05,
      "loss": 0.9317,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4227642276422764e-05,
      "loss": 0.7747,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6260162601626018e-05,
      "loss": 0.7065,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8292682926829268e-05,
      "loss": 0.6079,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.032520325203252e-05,
      "loss": 0.4306,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.2357723577235773e-05,
      "loss": 0.5325,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.2726,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.642276422764228e-05,
      "loss": 0.3247,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.8455284552845528e-05,
      "loss": 0.2971,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.048780487804878e-05,
      "loss": 0.2515,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.2520325203252037e-05,
      "loss": 0.2845,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.4552845528455286e-05,
      "loss": 0.1247,
      "step": 170
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.6585365853658535e-05,
      "loss": 0.0741,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.861788617886179e-05,
      "loss": 0.248,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.065040650406504e-05,
      "loss": 0.0402,
      "step": 200
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.4646924829157175,
      "eval_loss": 1.2843588590621948,
      "eval_runtime": 1127.5818,
      "eval_samples_per_second": 0.389,
      "eval_steps_per_second": 0.098,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.26829268292683e-05,
      "loss": 0.0652,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.4715447154471546e-05,
      "loss": 0.0827,
      "step": 220
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.6747967479674795e-05,
      "loss": 0.1339,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.0576,
      "step": 240
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9909543193125285e-05,
      "loss": 0.0135,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9683401175938496e-05,
      "loss": 0.0197,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.94572591587517e-05,
      "loss": 0.0287,
      "step": 270
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9231117141564905e-05,
      "loss": 0.0066,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.900497512437811e-05,
      "loss": 0.0256,
      "step": 290
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.877883310719132e-05,
      "loss": 0.0016,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8552691090004524e-05,
      "loss": 0.0036,
      "step": 310
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8326549072817735e-05,
      "loss": 0.0039,
      "step": 320
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.810040705563094e-05,
      "loss": 0.0014,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.787426503844414e-05,
      "loss": 0.0012,
      "step": 340
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7648123021257354e-05,
      "loss": 0.0007,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.742198100407056e-05,
      "loss": 0.0278,
      "step": 360
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.719583898688377e-05,
      "loss": 0.0004,
      "step": 370
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.696969696969697e-05,
      "loss": 0.0004,
      "step": 380
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.674355495251018e-05,
      "loss": 0.0004,
      "step": 390
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.651741293532338e-05,
      "loss": 0.0003,
      "step": 400
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.46924829157175396,
      "eval_loss": 1.65602445602417,
      "eval_runtime": 1082.8751,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.102,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.629127091813659e-05,
      "loss": 0.0003,
      "step": 410
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.60651289009498e-05,
      "loss": 0.0003,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.583898688376301e-05,
      "loss": 0.0003,
      "step": 430
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.561284486657621e-05,
      "loss": 0.0003,
      "step": 440
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.5386702849389416e-05,
      "loss": 0.0003,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.516056083220263e-05,
      "loss": 0.0003,
      "step": 460
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.493441881501583e-05,
      "loss": 0.0002,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.470827679782904e-05,
      "loss": 0.0002,
      "step": 480
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4482134780642246e-05,
      "loss": 0.0002,
      "step": 490
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.425599276345545e-05,
      "loss": 0.0002,
      "step": 500
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.402985074626866e-05,
      "loss": 0.0002,
      "step": 510
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.3803708729081865e-05,
      "loss": 0.0002,
      "step": 520
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.3577566711895076e-05,
      "loss": 0.0002,
      "step": 530
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.335142469470828e-05,
      "loss": 0.0002,
      "step": 540
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.3125282677521484e-05,
      "loss": 0.0001,
      "step": 550
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.289914066033469e-05,
      "loss": 0.0001,
      "step": 560
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.26729986431479e-05,
      "loss": 0.0001,
      "step": 570
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.2446856625961104e-05,
      "loss": 0.0001,
      "step": 580
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.2220714608774314e-05,
      "loss": 0.0002,
      "step": 590
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.199457259158752e-05,
      "loss": 0.0001,
      "step": 600
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.4510250569476082,
      "eval_loss": 2.0519042015075684,
      "eval_runtime": 1093.6378,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.101,
      "step": 600
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.176843057440072e-05,
      "loss": 0.0002,
      "step": 610
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.1542288557213934e-05,
      "loss": 0.0001,
      "step": 620
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.131614654002714e-05,
      "loss": 0.0001,
      "step": 630
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.109000452284035e-05,
      "loss": 0.0001,
      "step": 640
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.086386250565355e-05,
      "loss": 0.0001,
      "step": 650
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.063772048846676e-05,
      "loss": 0.0001,
      "step": 660
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.041157847127997e-05,
      "loss": 0.0001,
      "step": 670
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.018543645409317e-05,
      "loss": 0.0004,
      "step": 680
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.995929443690638e-05,
      "loss": 0.0002,
      "step": 690
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.973315241971959e-05,
      "loss": 0.0003,
      "step": 700
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.950701040253279e-05,
      "loss": 0.0001,
      "step": 710
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.9280868385345995e-05,
      "loss": 0.0001,
      "step": 720
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.9054726368159206e-05,
      "loss": 0.0002,
      "step": 730
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.882858435097241e-05,
      "loss": 0.0001,
      "step": 740
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.860244233378562e-05,
      "loss": 0.0001,
      "step": 750
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.8376300316598826e-05,
      "loss": 0.0001,
      "step": 760
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.815015829941203e-05,
      "loss": 0.0001,
      "step": 770
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.792401628222524e-05,
      "loss": 0.0001,
      "step": 780
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.7697874265038445e-05,
      "loss": 0.0001,
      "step": 790
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.7471732247851656e-05,
      "loss": 0.0001,
      "step": 800
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.4396355353075171,
      "eval_loss": 1.6676476001739502,
      "eval_runtime": 1094.6937,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.1,
      "step": 800
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.724559023066486e-05,
      "loss": 0.0001,
      "step": 810
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.7019448213478064e-05,
      "loss": 0.0001,
      "step": 820
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.6793306196291275e-05,
      "loss": 0.0001,
      "step": 830
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.656716417910448e-05,
      "loss": 0.0001,
      "step": 840
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.634102216191769e-05,
      "loss": 0.0001,
      "step": 850
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.6114880144730894e-05,
      "loss": 0.0001,
      "step": 860
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.58887381275441e-05,
      "loss": 0.0001,
      "step": 870
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.56625961103573e-05,
      "loss": 0.0001,
      "step": 880
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.543645409317051e-05,
      "loss": 0.0001,
      "step": 890
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.521031207598372e-05,
      "loss": 0.0001,
      "step": 900
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.498417005879693e-05,
      "loss": 0.0001,
      "step": 910
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.475802804161013e-05,
      "loss": 0.0001,
      "step": 920
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.453188602442334e-05,
      "loss": 0.0001,
      "step": 930
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.430574400723655e-05,
      "loss": 0.0001,
      "step": 940
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.407960199004975e-05,
      "loss": 0.0001,
      "step": 950
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.385345997286296e-05,
      "loss": 0.0001,
      "step": 960
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.362731795567617e-05,
      "loss": 0.0001,
      "step": 970
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.340117593848937e-05,
      "loss": 0.0001,
      "step": 980
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.3175033921302575e-05,
      "loss": 0.0001,
      "step": 990
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.2948891904115786e-05,
      "loss": 0.0001,
      "step": 1000
    },
    {
      "epoch": 1.07,
      "eval_accuracy": 0.4305239179954442,
      "eval_loss": 2.105757474899292,
      "eval_runtime": 1084.6609,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.101,
      "step": 1000
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.2722749886929e-05,
      "loss": 0.0001,
      "step": 1010
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.24966078697422e-05,
      "loss": 0.0001,
      "step": 1020
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.2270465852555405e-05,
      "loss": 0.0001,
      "step": 1030
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.204432383536861e-05,
      "loss": 0.0001,
      "step": 1040
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.181818181818182e-05,
      "loss": 0.0001,
      "step": 1050
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.1592039800995024e-05,
      "loss": 0.0001,
      "step": 1060
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.1365897783808235e-05,
      "loss": 0.0001,
      "step": 1070
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.113975576662144e-05,
      "loss": 0.0001,
      "step": 1080
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.0913613749434644e-05,
      "loss": 0.0001,
      "step": 1090
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.0687471732247855e-05,
      "loss": 0.0001,
      "step": 1100
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.046132971506106e-05,
      "loss": 0.0001,
      "step": 1110
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.0235187697874266e-05,
      "loss": 0.0001,
      "step": 1120
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.0009045680687474e-05,
      "loss": 0.0001,
      "step": 1130
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.9782903663500678e-05,
      "loss": 0.0001,
      "step": 1140
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.9556761646313885e-05,
      "loss": 0.0001,
      "step": 1150
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.9330619629127093e-05,
      "loss": 0.0001,
      "step": 1160
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.91044776119403e-05,
      "loss": 0.0,
      "step": 1170
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.8878335594753508e-05,
      "loss": 0.0001,
      "step": 1180
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.865219357756671e-05,
      "loss": 0.0,
      "step": 1190
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.842605156037992e-05,
      "loss": 0.0001,
      "step": 1200
    },
    {
      "epoch": 1.15,
      "eval_accuracy": 0.4419134396355353,
      "eval_loss": 2.165936231613159,
      "eval_runtime": 1107.6493,
      "eval_samples_per_second": 0.396,
      "eval_steps_per_second": 0.099,
      "step": 1200
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.8199909543193127e-05,
      "loss": 0.0001,
      "step": 1210
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.7973767526006335e-05,
      "loss": 0.0001,
      "step": 1220
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.7747625508819542e-05,
      "loss": 0.0001,
      "step": 1230
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.752148349163275e-05,
      "loss": 0.0,
      "step": 1240
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.729534147444595e-05,
      "loss": 0.0,
      "step": 1250
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.7069199457259158e-05,
      "loss": 0.0,
      "step": 1260
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.6843057440072366e-05,
      "loss": 0.0001,
      "step": 1270
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.6616915422885573e-05,
      "loss": 0.0,
      "step": 1280
    },
    {
      "epoch": 1.19,
      "learning_rate": 2.639077340569878e-05,
      "loss": 0.0,
      "step": 1290
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.6164631388511985e-05,
      "loss": 0.0,
      "step": 1300
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.5938489371325192e-05,
      "loss": 0.0001,
      "step": 1310
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.57123473541384e-05,
      "loss": 0.0001,
      "step": 1320
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.5486205336951608e-05,
      "loss": 0.0,
      "step": 1330
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.5260063319764815e-05,
      "loss": 0.0,
      "step": 1340
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.5033921302578023e-05,
      "loss": 0.0,
      "step": 1350
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.4807779285391227e-05,
      "loss": 0.0,
      "step": 1360
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.4581637268204434e-05,
      "loss": 0.0,
      "step": 1370
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.4355495251017642e-05,
      "loss": 0.0,
      "step": 1380
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.412935323383085e-05,
      "loss": 0.0,
      "step": 1390
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.3903211216644054e-05,
      "loss": 0.0,
      "step": 1400
    },
    {
      "epoch": 1.24,
      "eval_accuracy": 0.43735763097949887,
      "eval_loss": 2.219512939453125,
      "eval_runtime": 1089.3185,
      "eval_samples_per_second": 0.403,
      "eval_steps_per_second": 0.101,
      "step": 1400
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.367706919945726e-05,
      "loss": 0.0,
      "step": 1410
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.3450927182270465e-05,
      "loss": 0.0,
      "step": 1420
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.3224785165083673e-05,
      "loss": 0.0,
      "step": 1430
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.299864314789688e-05,
      "loss": 0.0,
      "step": 1440
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.2772501130710084e-05,
      "loss": 0.0,
      "step": 1450
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.2546359113523295e-05,
      "loss": 0.0,
      "step": 1460
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.2320217096336503e-05,
      "loss": 0.0,
      "step": 1470
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.2094075079149707e-05,
      "loss": 0.0,
      "step": 1480
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.1867933061962915e-05,
      "loss": 0.0,
      "step": 1490
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.164179104477612e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.1415649027589326e-05,
      "loss": 0.0,
      "step": 1510
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.1189507010402534e-05,
      "loss": 0.0,
      "step": 1520
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.0963364993215738e-05,
      "loss": 0.0,
      "step": 1530
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.073722297602895e-05,
      "loss": 0.0,
      "step": 1540
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.0511080958842156e-05,
      "loss": 0.0,
      "step": 1550
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.028493894165536e-05,
      "loss": 0.0,
      "step": 1560
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.0058796924468568e-05,
      "loss": 0.0,
      "step": 1570
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.9832654907281776e-05,
      "loss": 0.0,
      "step": 1580
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.960651289009498e-05,
      "loss": 0.0,
      "step": 1590
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.9380370872908187e-05,
      "loss": 0.0,
      "step": 1600
    },
    {
      "epoch": 1.32,
      "eval_accuracy": 0.43507972665148065,
      "eval_loss": 2.3093459606170654,
      "eval_runtime": 1108.3747,
      "eval_samples_per_second": 0.396,
      "eval_steps_per_second": 0.099,
      "step": 1600
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.915422885572139e-05,
      "loss": 0.0,
      "step": 1610
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.89280868385346e-05,
      "loss": 0.004,
      "step": 1620
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.870194482134781e-05,
      "loss": 0.0117,
      "step": 1630
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.8475802804161014e-05,
      "loss": 0.0001,
      "step": 1640
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.824966078697422e-05,
      "loss": 0.0002,
      "step": 1650
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.802351876978743e-05,
      "loss": 0.0001,
      "step": 1660
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.7797376752600633e-05,
      "loss": 0.0001,
      "step": 1670
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.757123473541384e-05,
      "loss": 0.0001,
      "step": 1680
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.7345092718227045e-05,
      "loss": 0.0001,
      "step": 1690
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.7118950701040252e-05,
      "loss": 0.0001,
      "step": 1700
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.689280868385346e-05,
      "loss": 0.0001,
      "step": 1710
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0,
      "step": 1720
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.6440524649479875e-05,
      "loss": 0.0,
      "step": 1730
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.6214382632293083e-05,
      "loss": 0.0,
      "step": 1740
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.5988240615106287e-05,
      "loss": 0.0002,
      "step": 1750
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.5762098597919494e-05,
      "loss": 0.0,
      "step": 1760
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.55359565807327e-05,
      "loss": 0.0001,
      "step": 1770
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.5309814563545906e-05,
      "loss": 0.0001,
      "step": 1780
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.5083672546359115e-05,
      "loss": 0.0,
      "step": 1790
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.485753052917232e-05,
      "loss": 0.0013,
      "step": 1800
    },
    {
      "epoch": 2.07,
      "eval_accuracy": 0.5603644646924829,
      "eval_loss": 2.1500625610351562,
      "eval_runtime": 1095.3897,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.1,
      "step": 1800
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.4631388511985527e-05,
      "loss": 0.0001,
      "step": 1810
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.4405246494798736e-05,
      "loss": 0.0001,
      "step": 1820
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.417910447761194e-05,
      "loss": 0.0001,
      "step": 1830
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.3952962460425148e-05,
      "loss": 0.0001,
      "step": 1840
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.3726820443238355e-05,
      "loss": 0.003,
      "step": 1850
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.3500678426051561e-05,
      "loss": 0.0002,
      "step": 1860
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.3274536408864769e-05,
      "loss": 0.0001,
      "step": 1870
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.3048394391677973e-05,
      "loss": 0.0001,
      "step": 1880
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.282225237449118e-05,
      "loss": 0.0001,
      "step": 1890
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.259611035730439e-05,
      "loss": 0.0001,
      "step": 1900
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.2369968340117595e-05,
      "loss": 0.0001,
      "step": 1910
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.2143826322930801e-05,
      "loss": 0.0001,
      "step": 1920
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1917684305744007e-05,
      "loss": 0.0001,
      "step": 1930
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1691542288557215e-05,
      "loss": 0.0001,
      "step": 1940
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.1465400271370422e-05,
      "loss": 0.0001,
      "step": 1950
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.1239258254183628e-05,
      "loss": 0.0001,
      "step": 1960
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.1013116236996834e-05,
      "loss": 0.0,
      "step": 1970
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.0786974219810041e-05,
      "loss": 0.0001,
      "step": 1980
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.0560832202623249e-05,
      "loss": 0.0001,
      "step": 1990
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.0334690185436455e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 2.15,
      "eval_accuracy": 0.5148063781321185,
      "eval_loss": 2.2250020503997803,
      "eval_runtime": 1087.2971,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.101,
      "step": 2000
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.010854816824966e-05,
      "loss": 0.0,
      "step": 2010
    },
    {
      "epoch": 2.15,
      "learning_rate": 9.882406151062868e-06,
      "loss": 0.0,
      "step": 2020
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.656264133876076e-06,
      "loss": 0.0,
      "step": 2030
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.430122116689281e-06,
      "loss": 0.0,
      "step": 2040
    },
    {
      "epoch": 2.17,
      "learning_rate": 9.203980099502487e-06,
      "loss": 0.0,
      "step": 2050
    },
    {
      "epoch": 2.17,
      "learning_rate": 8.977838082315695e-06,
      "loss": 0.0,
      "step": 2060
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.751696065128902e-06,
      "loss": 0.0,
      "step": 2070
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.525554047942108e-06,
      "loss": 0.0,
      "step": 2080
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.299412030755314e-06,
      "loss": 0.0003,
      "step": 2090
    },
    {
      "epoch": 2.19,
      "learning_rate": 8.073270013568522e-06,
      "loss": 0.0,
      "step": 2100
    },
    {
      "epoch": 2.19,
      "learning_rate": 7.847127996381729e-06,
      "loss": 0.0001,
      "step": 2110
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.620985979194935e-06,
      "loss": 0.0001,
      "step": 2120
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.394843962008141e-06,
      "loss": 0.0,
      "step": 2130
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.168701944821349e-06,
      "loss": 0.0,
      "step": 2140
    },
    {
      "epoch": 2.21,
      "learning_rate": 6.942559927634555e-06,
      "loss": 0.0,
      "step": 2150
    },
    {
      "epoch": 2.21,
      "learning_rate": 6.716417910447762e-06,
      "loss": 0.0004,
      "step": 2160
    },
    {
      "epoch": 2.22,
      "learning_rate": 6.4902758932609675e-06,
      "loss": 0.0,
      "step": 2170
    },
    {
      "epoch": 2.22,
      "learning_rate": 6.264133876074176e-06,
      "loss": 0.0002,
      "step": 2180
    },
    {
      "epoch": 2.22,
      "learning_rate": 6.037991858887382e-06,
      "loss": 0.0,
      "step": 2190
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.811849841700588e-06,
      "loss": 0.0,
      "step": 2200
    },
    {
      "epoch": 2.23,
      "eval_accuracy": 0.5330296127562643,
      "eval_loss": 2.6677799224853516,
      "eval_runtime": 1087.0337,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.101,
      "step": 2200
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.585707824513795e-06,
      "loss": 0.0,
      "step": 2210
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.359565807327002e-06,
      "loss": 0.0002,
      "step": 2220
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.1334237901402085e-06,
      "loss": 0.0,
      "step": 2230
    },
    {
      "epoch": 2.24,
      "learning_rate": 4.907281772953415e-06,
      "loss": 0.0,
      "step": 2240
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.681139755766622e-06,
      "loss": 0.0,
      "step": 2250
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.4549977385798285e-06,
      "loss": 0.0,
      "step": 2260
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.228855721393035e-06,
      "loss": 0.0,
      "step": 2270
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.002713704206242e-06,
      "loss": 0.0,
      "step": 2280
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.7765716870194486e-06,
      "loss": 0.0,
      "step": 2290
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.550429669832655e-06,
      "loss": 0.0,
      "step": 2300
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.324287652645862e-06,
      "loss": 0.0,
      "step": 2310
    },
    {
      "epoch": 2.28,
      "learning_rate": 3.0981456354590687e-06,
      "loss": 0.0,
      "step": 2320
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.8720036182722753e-06,
      "loss": 0.0,
      "step": 2330
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.645861601085482e-06,
      "loss": 0.0,
      "step": 2340
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.4197195838986887e-06,
      "loss": 0.0,
      "step": 2350
    },
    {
      "epoch": 2.29,
      "learning_rate": 2.1935775667118954e-06,
      "loss": 0.0,
      "step": 2360
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.967435549525102e-06,
      "loss": 0.0,
      "step": 2370
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.7412935323383086e-06,
      "loss": 0.0,
      "step": 2380
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.0,
      "step": 2390
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.289009497964722e-06,
      "loss": 0.0,
      "step": 2400
    },
    {
      "epoch": 2.31,
      "eval_accuracy": 0.5079726651480638,
      "eval_loss": 2.713104724884033,
      "eval_runtime": 1085.6923,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.101,
      "step": 2400
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.0628674807779286e-06,
      "loss": 0.0,
      "step": 2410
    },
    {
      "epoch": 2.32,
      "learning_rate": 8.367254635911353e-07,
      "loss": 0.0,
      "step": 2420
    },
    {
      "epoch": 2.32,
      "learning_rate": 6.10583446404342e-07,
      "loss": 0.0,
      "step": 2430
    },
    {
      "epoch": 2.33,
      "learning_rate": 3.844414292175486e-07,
      "loss": 0.0,
      "step": 2440
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.582994120307553e-07,
      "loss": 0.0,
      "step": 2450
    },
    {
      "epoch": 2.33,
      "step": 2457,
      "total_flos": 1.2241447696947216e+19,
      "train_loss": 0.047377249488086234,
      "train_runtime": 41549.3568,
      "train_samples_per_second": 0.237,
      "train_steps_per_second": 0.059
    }
  ],
  "logging_steps": 10,
  "max_steps": 2457.0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "total_flos": 1.2241447696947216e+19,
  "trial_name": null,
  "trial_params": null
}