{
  "best_metric": 0.7297297297297297,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1340",
  "epoch": 3.25,
  "global_step": 1340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.7313432835820893e-06,
      "loss": 2.4537,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.4626865671641785e-06,
      "loss": 2.4565,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.119402985074627e-05,
      "loss": 2.3771,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4925373134328357e-05,
      "loss": 2.3446,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.865671641791045e-05,
      "loss": 2.3192,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.238805970149254e-05,
      "loss": 2.3792,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.6119402985074626e-05,
      "loss": 2.4095,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9850746268656714e-05,
      "loss": 2.4641,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.358208955223881e-05,
      "loss": 2.2262,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.73134328358209e-05,
      "loss": 2.3417,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.104477611940299e-05,
      "loss": 2.2397,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.477611940298508e-05,
      "loss": 2.0114,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.850746268656717e-05,
      "loss": 2.349,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.975124378109453e-05,
      "loss": 2.058,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.933665008291874e-05,
      "loss": 2.0433,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8922056384742954e-05,
      "loss": 2.3097,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.850746268656717e-05,
      "loss": 1.9613,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8092868988391376e-05,
      "loss": 1.715,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.767827529021559e-05,
      "loss": 1.9524,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7263681592039805e-05,
      "loss": 2.4086,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.684908789386401e-05,
      "loss": 2.7159,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.643449419568823e-05,
      "loss": 2.1701,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.601990049751244e-05,
      "loss": 2.3041,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.560530679933665e-05,
      "loss": 2.2435,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5190713101160863e-05,
      "loss": 2.1136,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.477611940298508e-05,
      "loss": 1.3329,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4361525704809285e-05,
      "loss": 2.1726,
      "step": 270
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.39469320066335e-05,
      "loss": 1.7117,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.3532338308457714e-05,
      "loss": 2.1894,
      "step": 290
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.311774461028192e-05,
      "loss": 2.308,
      "step": 300
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.2703150912106136e-05,
      "loss": 2.2462,
      "step": 310
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.228855721393035e-05,
      "loss": 1.6541,
      "step": 320
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.187396351575456e-05,
      "loss": 1.2417,
      "step": 330
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.35135135135135137,
      "eval_loss": 1.5927890539169312,
      "eval_runtime": 21.5381,
      "eval_samples_per_second": 3.436,
      "eval_steps_per_second": 3.436,
      "step": 335
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.145936981757877e-05,
      "loss": 2.0567,
      "step": 340
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.104477611940299e-05,
      "loss": 1.7841,
      "step": 350
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.0630182421227194e-05,
      "loss": 1.2214,
      "step": 360
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.021558872305141e-05,
      "loss": 1.3657,
      "step": 370
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.980099502487562e-05,
      "loss": 1.3927,
      "step": 380
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.938640132669984e-05,
      "loss": 1.5291,
      "step": 390
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.8971807628524045e-05,
      "loss": 1.4722,
      "step": 400
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.855721393034826e-05,
      "loss": 1.024,
      "step": 410
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.8142620232172474e-05,
      "loss": 1.7965,
      "step": 420
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.772802653399669e-05,
      "loss": 1.5893,
      "step": 430
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.73134328358209e-05,
      "loss": 0.9593,
      "step": 440
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.689883913764511e-05,
      "loss": 1.4799,
      "step": 450
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.6484245439469325e-05,
      "loss": 0.7833,
      "step": 460
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.606965174129354e-05,
      "loss": 2.0512,
      "step": 470
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.565505804311775e-05,
      "loss": 1.063,
      "step": 480
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.524046434494196e-05,
      "loss": 1.4163,
      "step": 490
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.4825870646766175e-05,
      "loss": 1.9212,
      "step": 500
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.441127694859038e-05,
      "loss": 1.4935,
      "step": 510
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.39966832504146e-05,
      "loss": 0.5912,
      "step": 520
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.358208955223881e-05,
      "loss": 0.4764,
      "step": 530
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.316749585406302e-05,
      "loss": 1.0399,
      "step": 540
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.2752902155887234e-05,
      "loss": 1.4846,
      "step": 550
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.233830845771145e-05,
      "loss": 0.8735,
      "step": 560
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.1923714759535656e-05,
      "loss": 1.193,
      "step": 570
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.150912106135987e-05,
      "loss": 1.5802,
      "step": 580
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.109452736318408e-05,
      "loss": 1.5537,
      "step": 590
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.067993366500829e-05,
      "loss": 0.5706,
      "step": 600
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.0265339966832506e-05,
      "loss": 1.7501,
      "step": 610
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.9850746268656714e-05,
      "loss": 1.4373,
      "step": 620
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.943615257048093e-05,
      "loss": 1.1142,
      "step": 630
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.9021558872305143e-05,
      "loss": 1.596,
      "step": 640
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.8606965174129354e-05,
      "loss": 1.2776,
      "step": 650
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.8192371475953565e-05,
      "loss": 0.8291,
      "step": 660
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.7873,
      "step": 670
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.5,
      "eval_loss": 1.0956870317459106,
      "eval_runtime": 21.8938,
      "eval_samples_per_second": 3.38,
      "eval_steps_per_second": 3.38,
      "step": 670
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.736318407960199e-05,
      "loss": 0.4087,
      "step": 680
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.6948590381426204e-05,
      "loss": 0.6448,
      "step": 690
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.653399668325042e-05,
      "loss": 0.5034,
      "step": 700
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.6119402985074626e-05,
      "loss": 0.2098,
      "step": 710
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.570480928689884e-05,
      "loss": 0.792,
      "step": 720
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.5290215588723055e-05,
      "loss": 0.0555,
      "step": 730
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.4875621890547266e-05,
      "loss": 1.0835,
      "step": 740
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.4461028192371477e-05,
      "loss": 0.6056,
      "step": 750
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.4046434494195688e-05,
      "loss": 1.2307,
      "step": 760
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.3631840796019903e-05,
      "loss": 0.0849,
      "step": 770
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.3217247097844114e-05,
      "loss": 1.4995,
      "step": 780
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.2802653399668325e-05,
      "loss": 0.8404,
      "step": 790
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.238805970149254e-05,
      "loss": 0.7694,
      "step": 800
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.197346600331675e-05,
      "loss": 0.2,
      "step": 810
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.155887230514096e-05,
      "loss": 0.8996,
      "step": 820
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.1144278606965175e-05,
      "loss": 1.4479,
      "step": 830
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.0729684908789386e-05,
      "loss": 0.9172,
      "step": 840
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.0315091210613597e-05,
      "loss": 0.3513,
      "step": 850
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.990049751243781e-05,
      "loss": 0.8308,
      "step": 860
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.9485903814262023e-05,
      "loss": 0.177,
      "step": 870
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.9071310116086237e-05,
      "loss": 1.0408,
      "step": 880
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.865671641791045e-05,
      "loss": 0.7758,
      "step": 890
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8242122719734662e-05,
      "loss": 0.5689,
      "step": 900
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.7827529021558873e-05,
      "loss": 0.176,
      "step": 910
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.7412935323383088e-05,
      "loss": 0.7186,
      "step": 920
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.69983416252073e-05,
      "loss": 0.8592,
      "step": 930
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.658374792703151e-05,
      "loss": 0.6164,
      "step": 940
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.6169154228855724e-05,
      "loss": 0.6385,
      "step": 950
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.5754560530679935e-05,
      "loss": 0.5576,
      "step": 960
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.5339966832504146e-05,
      "loss": 0.2168,
      "step": 970
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.4925373134328357e-05,
      "loss": 0.7471,
      "step": 980
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4510779436152571e-05,
      "loss": 0.0901,
      "step": 990
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.4096185737976782e-05,
      "loss": 0.7945,
      "step": 1000
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.7027027027027027,
      "eval_loss": 1.0747544765472412,
      "eval_runtime": 23.049,
      "eval_samples_per_second": 3.211,
      "eval_steps_per_second": 3.211,
      "step": 1005
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.3681592039800995e-05,
      "loss": 0.1508,
      "step": 1010
    },
    {
      "epoch": 3.01,
      "learning_rate": 1.326699834162521e-05,
      "loss": 0.6429,
      "step": 1020
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.285240464344942e-05,
      "loss": 0.6257,
      "step": 1030
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2437810945273633e-05,
      "loss": 0.2605,
      "step": 1040
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2023217247097844e-05,
      "loss": 0.5422,
      "step": 1050
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.1608623548922057e-05,
      "loss": 0.1763,
      "step": 1060
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.119402985074627e-05,
      "loss": 0.2139,
      "step": 1070
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.077943615257048e-05,
      "loss": 1.1283,
      "step": 1080
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.0364842454394693e-05,
      "loss": 0.2503,
      "step": 1090
    },
    {
      "epoch": 3.07,
      "learning_rate": 9.950248756218906e-06,
      "loss": 0.0209,
      "step": 1100
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.535655058043118e-06,
      "loss": 0.286,
      "step": 1110
    },
    {
      "epoch": 3.09,
      "learning_rate": 9.121061359867331e-06,
      "loss": 0.4992,
      "step": 1120
    },
    {
      "epoch": 3.09,
      "learning_rate": 8.706467661691544e-06,
      "loss": 0.082,
      "step": 1130
    },
    {
      "epoch": 3.1,
      "learning_rate": 8.291873963515755e-06,
      "loss": 0.7033,
      "step": 1140
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.877280265339968e-06,
      "loss": 0.4956,
      "step": 1150
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.4626865671641785e-06,
      "loss": 0.02,
      "step": 1160
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.048092868988391e-06,
      "loss": 0.0545,
      "step": 1170
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.633499170812605e-06,
      "loss": 0.0159,
      "step": 1180
    },
    {
      "epoch": 3.14,
      "learning_rate": 6.2189054726368165e-06,
      "loss": 0.2031,
      "step": 1190
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.804311774461028e-06,
      "loss": 0.208,
      "step": 1200
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.38971807628524e-06,
      "loss": 0.4455,
      "step": 1210
    },
    {
      "epoch": 3.16,
      "learning_rate": 4.975124378109453e-06,
      "loss": 0.0516,
      "step": 1220
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.560530679933666e-06,
      "loss": 0.4953,
      "step": 1230
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.145936981757877e-06,
      "loss": 0.0238,
      "step": 1240
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.7313432835820893e-06,
      "loss": 0.3327,
      "step": 1250
    },
    {
      "epoch": 3.19,
      "learning_rate": 3.3167495854063024e-06,
      "loss": 0.7936,
      "step": 1260
    },
    {
      "epoch": 3.2,
      "learning_rate": 2.902155887230514e-06,
      "loss": 1.226,
      "step": 1270
    },
    {
      "epoch": 3.21,
      "learning_rate": 2.4875621890547264e-06,
      "loss": 0.0363,
      "step": 1280
    },
    {
      "epoch": 3.21,
      "learning_rate": 2.0729684908789387e-06,
      "loss": 0.2792,
      "step": 1290
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.6583747927031512e-06,
      "loss": 0.061,
      "step": 1300
    },
    {
      "epoch": 3.23,
      "learning_rate": 1.2437810945273632e-06,
      "loss": 0.1353,
      "step": 1310
    },
    {
      "epoch": 3.24,
      "learning_rate": 8.291873963515756e-07,
      "loss": 0.3527,
      "step": 1320
    },
    {
      "epoch": 3.24,
      "learning_rate": 4.145936981757878e-07,
      "loss": 0.0164,
      "step": 1330
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0,
      "loss": 0.0604,
      "step": 1340
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.7297297297297297,
      "eval_loss": 0.7424588799476624,
      "eval_runtime": 22.0218,
      "eval_samples_per_second": 3.36,
      "eval_steps_per_second": 3.36,
      "step": 1340
    },
    {
      "epoch": 3.25,
      "step": 1340,
      "total_flos": 1.6698605675957453e+18,
      "train_loss": 1.1046247358308798,
      "train_runtime": 1053.1884,
      "train_samples_per_second": 1.272,
      "train_steps_per_second": 1.272
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.7716049382716049,
      "eval_loss": 0.7548928260803223,
      "eval_runtime": 52.2864,
      "eval_samples_per_second": 3.098,
      "eval_steps_per_second": 3.098,
      "step": 1340
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.7716049382716049,
      "eval_loss": 0.7548928260803223,
      "eval_runtime": 46.747,
      "eval_samples_per_second": 3.465,
      "eval_steps_per_second": 3.465,
      "step": 1340
    }
  ],
  "max_steps": 1340,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.6698605675957453e+18,
  "trial_name": null,
  "trial_params": null
}