{
  "best_metric": 0.855072463768116,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1080",
  "epoch": 4.2,
  "eval_steps": 500,
  "global_step": 1350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 2.3221,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 2.5211,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.2885,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 2.2464,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 2.1272,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.2088,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 2.1,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.962962962962963e-05,
      "loss": 2.2068,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0292,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 2.0693,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.074074074074074e-05,
      "loss": 2.2566,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.0376,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.814814814814815e-05,
      "loss": 2.0765,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9794238683127575e-05,
      "loss": 2.1693,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.938271604938271e-05,
      "loss": 2.1702,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8971193415637865e-05,
      "loss": 1.6641,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.855967078189301e-05,
      "loss": 1.9802,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.814814814814815e-05,
      "loss": 2.1454,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.773662551440329e-05,
      "loss": 1.879,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.732510288065844e-05,
      "loss": 2.3546,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.691358024691358e-05,
      "loss": 2.4823,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.650205761316873e-05,
      "loss": 1.5895,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.609053497942387e-05,
      "loss": 2.0294,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.567901234567901e-05,
      "loss": 1.8332,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5267489711934157e-05,
      "loss": 2.0615,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.48559670781893e-05,
      "loss": 2.2003,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.7873,
      "step": 270
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.4927536231884058,
      "eval_loss": 1.5797250270843506,
      "eval_runtime": 22.9519,
      "eval_samples_per_second": 9.019,
      "eval_steps_per_second": 9.019,
      "step": 270
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.403292181069959e-05,
      "loss": 1.655,
      "step": 280
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.3621399176954737e-05,
      "loss": 1.7651,
      "step": 290
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 1.9236,
      "step": 300
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.279835390946502e-05,
      "loss": 1.5829,
      "step": 310
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.2386831275720165e-05,
      "loss": 1.8236,
      "step": 320
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.197530864197531e-05,
      "loss": 1.6459,
      "step": 330
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.1563786008230455e-05,
      "loss": 1.8179,
      "step": 340
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.11522633744856e-05,
      "loss": 1.8987,
      "step": 350
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.4019,
      "step": 360
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.032921810699588e-05,
      "loss": 1.9101,
      "step": 370
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.9917695473251035e-05,
      "loss": 1.3061,
      "step": 380
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.950617283950617e-05,
      "loss": 1.715,
      "step": 390
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.909465020576132e-05,
      "loss": 1.7822,
      "step": 400
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.868312757201646e-05,
      "loss": 1.7078,
      "step": 410
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.82716049382716e-05,
      "loss": 1.7544,
      "step": 420
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.786008230452675e-05,
      "loss": 1.5281,
      "step": 430
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.74485596707819e-05,
      "loss": 1.3543,
      "step": 440
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.0257,
      "step": 450
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.662551440329218e-05,
      "loss": 1.4273,
      "step": 460
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.6213991769547327e-05,
      "loss": 1.7747,
      "step": 470
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.580246913580247e-05,
      "loss": 1.3631,
      "step": 480
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.539094650205762e-05,
      "loss": 1.4453,
      "step": 490
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.497942386831276e-05,
      "loss": 1.2782,
      "step": 500
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.45679012345679e-05,
      "loss": 4.8334,
      "step": 510
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.4156378600823045e-05,
      "loss": 2.3039,
      "step": 520
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.374485596707819e-05,
      "loss": 2.1338,
      "step": 530
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.5618,
      "step": 540
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.6038647342995169,
      "eval_loss": 1.1127229928970337,
      "eval_runtime": 23.2911,
      "eval_samples_per_second": 8.888,
      "eval_steps_per_second": 8.888,
      "step": 540
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.292181069958848e-05,
      "loss": 1.11,
      "step": 550
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.2510288065843625e-05,
      "loss": 0.5159,
      "step": 560
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.209876543209876e-05,
      "loss": 1.3914,
      "step": 570
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.168724279835391e-05,
      "loss": 0.6359,
      "step": 580
    },
    {
      "epoch": 2.04,
      "learning_rate": 3.127572016460906e-05,
      "loss": 1.3793,
      "step": 590
    },
    {
      "epoch": 2.04,
      "learning_rate": 3.08641975308642e-05,
      "loss": 1.1747,
      "step": 600
    },
    {
      "epoch": 2.05,
      "learning_rate": 3.0452674897119343e-05,
      "loss": 1.4827,
      "step": 610
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.0041152263374488e-05,
      "loss": 1.0893,
      "step": 620
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.5242,
      "step": 630
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.9218106995884775e-05,
      "loss": 1.2997,
      "step": 640
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.880658436213992e-05,
      "loss": 1.2575,
      "step": 650
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.4275,
      "step": 660
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.7983539094650207e-05,
      "loss": 0.6559,
      "step": 670
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.757201646090535e-05,
      "loss": 0.3606,
      "step": 680
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.8187,
      "step": 690
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.6748971193415638e-05,
      "loss": 0.9589,
      "step": 700
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.6337448559670787e-05,
      "loss": 0.3948,
      "step": 710
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.1526,
      "step": 720
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.551440329218107e-05,
      "loss": 0.525,
      "step": 730
    },
    {
      "epoch": 2.15,
      "learning_rate": 2.510288065843622e-05,
      "loss": 1.4803,
      "step": 740
    },
    {
      "epoch": 2.16,
      "learning_rate": 2.4691358024691357e-05,
      "loss": 0.8134,
      "step": 750
    },
    {
      "epoch": 2.16,
      "learning_rate": 2.4279835390946505e-05,
      "loss": 1.0397,
      "step": 760
    },
    {
      "epoch": 2.17,
      "learning_rate": 2.3868312757201647e-05,
      "loss": 0.8543,
      "step": 770
    },
    {
      "epoch": 2.18,
      "learning_rate": 2.345679012345679e-05,
      "loss": 1.1528,
      "step": 780
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.3045267489711937e-05,
      "loss": 0.2724,
      "step": 790
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.2633744855967078e-05,
      "loss": 0.4115,
      "step": 800
    },
    {
      "epoch": 2.2,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6551,
      "step": 810
    },
    {
      "epoch": 2.2,
      "eval_accuracy": 0.6811594202898551,
      "eval_loss": 1.0396733283996582,
      "eval_runtime": 23.4381,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 8.832,
      "step": 810
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.1810699588477368e-05,
      "loss": 0.2593,
      "step": 820
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.139917695473251e-05,
      "loss": 0.4806,
      "step": 830
    },
    {
      "epoch": 3.02,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.1263,
      "step": 840
    },
    {
      "epoch": 3.03,
      "learning_rate": 2.05761316872428e-05,
      "loss": 0.9648,
      "step": 850
    },
    {
      "epoch": 3.04,
      "learning_rate": 2.016460905349794e-05,
      "loss": 0.317,
      "step": 860
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.7032,
      "step": 870
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.934156378600823e-05,
      "loss": 0.4669,
      "step": 880
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.8930041152263377e-05,
      "loss": 1.2327,
      "step": 890
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.3478,
      "step": 900
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.8106995884773663e-05,
      "loss": 0.0172,
      "step": 910
    },
    {
      "epoch": 3.08,
      "learning_rate": 1.769547325102881e-05,
      "loss": 0.2312,
      "step": 920
    },
    {
      "epoch": 3.09,
      "learning_rate": 1.728395061728395e-05,
      "loss": 0.2194,
      "step": 930
    },
    {
      "epoch": 3.1,
      "learning_rate": 1.6872427983539095e-05,
      "loss": 0.0099,
      "step": 940
    },
    {
      "epoch": 3.1,
      "learning_rate": 1.646090534979424e-05,
      "loss": 0.8937,
      "step": 950
    },
    {
      "epoch": 3.11,
      "learning_rate": 1.604938271604938e-05,
      "loss": 0.9387,
      "step": 960
    },
    {
      "epoch": 3.12,
      "learning_rate": 1.563786008230453e-05,
      "loss": 0.5917,
      "step": 970
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.5226337448559672e-05,
      "loss": 0.765,
      "step": 980
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.2671,
      "step": 990
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.440329218106996e-05,
      "loss": 0.6623,
      "step": 1000
    },
    {
      "epoch": 3.15,
      "learning_rate": 1.3991769547325103e-05,
      "loss": 0.8418,
      "step": 1010
    },
    {
      "epoch": 3.16,
      "learning_rate": 1.3580246913580247e-05,
      "loss": 0.579,
      "step": 1020
    },
    {
      "epoch": 3.16,
      "learning_rate": 1.3168724279835393e-05,
      "loss": 0.5901,
      "step": 1030
    },
    {
      "epoch": 3.17,
      "learning_rate": 1.2757201646090535e-05,
      "loss": 0.6065,
      "step": 1040
    },
    {
      "epoch": 3.18,
      "learning_rate": 1.2345679012345678e-05,
      "loss": 0.4892,
      "step": 1050
    },
    {
      "epoch": 3.19,
      "learning_rate": 1.1934156378600823e-05,
      "loss": 0.5454,
      "step": 1060
    },
    {
      "epoch": 3.19,
      "learning_rate": 1.1522633744855968e-05,
      "loss": 0.3136,
      "step": 1070
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0093,
      "step": 1080
    },
    {
      "epoch": 3.2,
      "eval_accuracy": 0.855072463768116,
      "eval_loss": 0.535359263420105,
      "eval_runtime": 23.1,
      "eval_samples_per_second": 8.961,
      "eval_steps_per_second": 8.961,
      "step": 1080
    },
    {
      "epoch": 4.01,
      "learning_rate": 1.0699588477366255e-05,
      "loss": 0.1891,
      "step": 1090
    },
    {
      "epoch": 4.01,
      "learning_rate": 1.02880658436214e-05,
      "loss": 0.5171,
      "step": 1100
    },
    {
      "epoch": 4.02,
      "learning_rate": 9.876543209876543e-06,
      "loss": 0.7706,
      "step": 1110
    },
    {
      "epoch": 4.03,
      "learning_rate": 9.465020576131688e-06,
      "loss": 0.0302,
      "step": 1120
    },
    {
      "epoch": 4.04,
      "learning_rate": 9.053497942386832e-06,
      "loss": 0.2731,
      "step": 1130
    },
    {
      "epoch": 4.04,
      "learning_rate": 8.641975308641975e-06,
      "loss": 0.1557,
      "step": 1140
    },
    {
      "epoch": 4.05,
      "learning_rate": 8.23045267489712e-06,
      "loss": 0.8335,
      "step": 1150
    },
    {
      "epoch": 4.06,
      "learning_rate": 7.818930041152265e-06,
      "loss": 0.0061,
      "step": 1160
    },
    {
      "epoch": 4.07,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0213,
      "step": 1170
    },
    {
      "epoch": 4.07,
      "learning_rate": 6.995884773662552e-06,
      "loss": 0.0132,
      "step": 1180
    },
    {
      "epoch": 4.08,
      "learning_rate": 6.584362139917697e-06,
      "loss": 0.7131,
      "step": 1190
    },
    {
      "epoch": 4.09,
      "learning_rate": 6.172839506172839e-06,
      "loss": 0.2163,
      "step": 1200
    },
    {
      "epoch": 4.1,
      "learning_rate": 5.761316872427984e-06,
      "loss": 0.0835,
      "step": 1210
    },
    {
      "epoch": 4.1,
      "learning_rate": 5.3497942386831275e-06,
      "loss": 0.1773,
      "step": 1220
    },
    {
      "epoch": 4.11,
      "learning_rate": 4.938271604938272e-06,
      "loss": 0.4539,
      "step": 1230
    },
    {
      "epoch": 4.12,
      "learning_rate": 4.526748971193416e-06,
      "loss": 0.4743,
      "step": 1240
    },
    {
      "epoch": 4.13,
      "learning_rate": 4.11522633744856e-06,
      "loss": 1.0935,
      "step": 1250
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.4259,
      "step": 1260
    },
    {
      "epoch": 4.14,
      "learning_rate": 3.2921810699588483e-06,
      "loss": 0.0187,
      "step": 1270
    },
    {
      "epoch": 4.15,
      "learning_rate": 2.880658436213992e-06,
      "loss": 0.0101,
      "step": 1280
    },
    {
      "epoch": 4.16,
      "learning_rate": 2.469135802469136e-06,
      "loss": 0.0073,
      "step": 1290
    },
    {
      "epoch": 4.16,
      "learning_rate": 2.05761316872428e-06,
      "loss": 1.1336,
      "step": 1300
    },
    {
      "epoch": 4.17,
      "learning_rate": 1.6460905349794242e-06,
      "loss": 0.0194,
      "step": 1310
    },
    {
      "epoch": 4.18,
      "learning_rate": 1.234567901234568e-06,
      "loss": 0.2058,
      "step": 1320
    },
    {
      "epoch": 4.19,
      "learning_rate": 8.230452674897121e-07,
      "loss": 0.0268,
      "step": 1330
    },
    {
      "epoch": 4.19,
      "learning_rate": 4.1152263374485604e-07,
      "loss": 0.1909,
      "step": 1340
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0,
      "loss": 0.0434,
      "step": 1350
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.8357487922705314,
      "eval_loss": 0.6645320653915405,
      "eval_runtime": 22.8287,
      "eval_samples_per_second": 9.068,
      "eval_steps_per_second": 9.068,
      "step": 1350
    },
    {
      "epoch": 4.2,
      "step": 1350,
      "total_flos": 1.6822922096590848e+18,
      "train_loss": 1.1034327039619287,
      "train_runtime": 414.0045,
      "train_samples_per_second": 3.261,
      "train_steps_per_second": 3.261
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.8497409326424871,
      "eval_loss": 0.49719980359077454,
      "eval_runtime": 21.5367,
      "eval_samples_per_second": 8.961,
      "eval_steps_per_second": 8.961,
      "step": 1350
    },
    {
      "epoch": 4.2,
      "eval_accuracy": 0.8497409326424871,
      "eval_loss": 0.49719980359077454,
      "eval_runtime": 21.7543,
      "eval_samples_per_second": 8.872,
      "eval_steps_per_second": 8.872,
      "step": 1350
    }
  ],
  "logging_steps": 10,
  "max_steps": 1350,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.6822922096590848e+18,
  "trial_name": null,
  "trial_params": null
}