{
  "best_metric": 0.09375,
  "best_model_checkpoint": "videomae-base-finetuned-NOSTRO-Nuovo-subset/checkpoint-140",
  "epoch": 3.0625,
  "eval_steps": 500,
  "global_step": 448,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022321428571428572,
      "grad_norm": 2.8510043621063232,
      "learning_rate": 0.004888392857142857,
      "loss": 3.4291,
      "step": 10
    },
    {
      "epoch": 0.044642857142857144,
      "grad_norm": 3.645416021347046,
      "learning_rate": 0.004776785714285714,
      "loss": 2.9155,
      "step": 20
    },
    {
      "epoch": 0.06696428571428571,
      "grad_norm": 2.4148318767547607,
      "learning_rate": 0.004665178571428572,
      "loss": 2.9151,
      "step": 30
    },
    {
      "epoch": 0.08928571428571429,
      "grad_norm": 1.8130139112472534,
      "learning_rate": 0.0045535714285714285,
      "loss": 2.8817,
      "step": 40
    },
    {
      "epoch": 0.11160714285714286,
      "grad_norm": 1.6304864883422852,
      "learning_rate": 0.004441964285714285,
      "loss": 2.6704,
      "step": 50
    },
    {
      "epoch": 0.13392857142857142,
      "grad_norm": 1.9342577457427979,
      "learning_rate": 0.004330357142857143,
      "loss": 2.2677,
      "step": 60
    },
    {
      "epoch": 0.15625,
      "grad_norm": 2.3716800212860107,
      "learning_rate": 0.00421875,
      "loss": 2.7221,
      "step": 70
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.262819766998291,
      "learning_rate": 0.004107142857142857,
      "loss": 2.7701,
      "step": 80
    },
    {
      "epoch": 0.20089285714285715,
      "grad_norm": 1.4354780912399292,
      "learning_rate": 0.0039955357142857145,
      "loss": 2.7488,
      "step": 90
    },
    {
      "epoch": 0.22321428571428573,
      "grad_norm": 1.7690075635910034,
      "learning_rate": 0.0038839285714285716,
      "loss": 2.6539,
      "step": 100
    },
    {
      "epoch": 0.24553571428571427,
      "grad_norm": 1.1364132165908813,
      "learning_rate": 0.0037723214285714287,
      "loss": 2.7443,
      "step": 110
    },
    {
      "epoch": 0.26785714285714285,
      "grad_norm": 1.049050211906433,
      "learning_rate": 0.0036607142857142854,
      "loss": 2.8178,
      "step": 120
    },
    {
      "epoch": 0.29017857142857145,
      "grad_norm": 1.1659719944000244,
      "learning_rate": 0.003549107142857143,
      "loss": 2.7022,
      "step": 130
    },
    {
      "epoch": 0.3125,
      "grad_norm": 1.7436045408248901,
      "learning_rate": 0.0034375,
      "loss": 2.6364,
      "step": 140
    },
    {
      "epoch": 0.3125,
      "eval_accuracy": 0.09375,
      "eval_loss": 2.716905355453491,
      "eval_runtime": 46.1618,
      "eval_samples_per_second": 1.386,
      "eval_steps_per_second": 0.347,
      "step": 140
    },
    {
      "epoch": 1.0223214285714286,
      "grad_norm": 0.9514412879943848,
      "learning_rate": 0.003325892857142857,
      "loss": 2.6498,
      "step": 150
    },
    {
      "epoch": 1.0446428571428572,
      "grad_norm": 0.8252668976783752,
      "learning_rate": 0.0032142857142857147,
      "loss": 2.7494,
      "step": 160
    },
    {
      "epoch": 1.0669642857142858,
      "grad_norm": 1.0420445203781128,
      "learning_rate": 0.0031026785714285718,
      "loss": 2.611,
      "step": 170
    },
    {
      "epoch": 1.0892857142857142,
      "grad_norm": 1.1212177276611328,
      "learning_rate": 0.0029910714285714284,
      "loss": 2.5799,
      "step": 180
    },
    {
      "epoch": 1.1116071428571428,
      "grad_norm": 0.9177935123443604,
      "learning_rate": 0.0028794642857142855,
      "loss": 2.7091,
      "step": 190
    },
    {
      "epoch": 1.1339285714285714,
      "grad_norm": 6.132950782775879,
      "learning_rate": 0.002767857142857143,
      "loss": 2.7558,
      "step": 200
    },
    {
      "epoch": 1.15625,
      "grad_norm": 1.1796364784240723,
      "learning_rate": 0.00265625,
      "loss": 2.7146,
      "step": 210
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 1.0622265338897705,
      "learning_rate": 0.002544642857142857,
      "loss": 2.6695,
      "step": 220
    },
    {
      "epoch": 1.2008928571428572,
      "grad_norm": 0.9800061583518982,
      "learning_rate": 0.0024330357142857144,
      "loss": 2.6584,
      "step": 230
    },
    {
      "epoch": 1.2232142857142858,
      "grad_norm": 1.505244255065918,
      "learning_rate": 0.0023214285714285715,
      "loss": 2.5511,
      "step": 240
    },
    {
      "epoch": 1.2455357142857142,
      "grad_norm": 1.490077018737793,
      "learning_rate": 0.0022098214285714286,
      "loss": 2.4467,
      "step": 250
    },
    {
      "epoch": 1.2678571428571428,
      "grad_norm": 1.0019323825836182,
      "learning_rate": 0.0020982142857142857,
      "loss": 2.8359,
      "step": 260
    },
    {
      "epoch": 1.2901785714285714,
      "grad_norm": 1.1663577556610107,
      "learning_rate": 0.001986607142857143,
      "loss": 2.6158,
      "step": 270
    },
    {
      "epoch": 1.3125,
      "grad_norm": 1.264772891998291,
      "learning_rate": 0.001875,
      "loss": 2.7081,
      "step": 280
    },
    {
      "epoch": 1.3125,
      "eval_accuracy": 0.09375,
      "eval_loss": 2.628089427947998,
      "eval_runtime": 47.2221,
      "eval_samples_per_second": 1.355,
      "eval_steps_per_second": 0.339,
      "step": 280
    },
    {
      "epoch": 2.0223214285714284,
      "grad_norm": 0.7295708060264587,
      "learning_rate": 0.0017633928571428573,
      "loss": 2.5085,
      "step": 290
    },
    {
      "epoch": 2.044642857142857,
      "grad_norm": 0.9577257037162781,
      "learning_rate": 0.0016517857142857144,
      "loss": 2.6441,
      "step": 300
    },
    {
      "epoch": 2.0669642857142856,
      "grad_norm": 0.8992665410041809,
      "learning_rate": 0.0015401785714285715,
      "loss": 2.6752,
      "step": 310
    },
    {
      "epoch": 2.0892857142857144,
      "grad_norm": 0.9659096598625183,
      "learning_rate": 0.0014285714285714286,
      "loss": 2.5191,
      "step": 320
    },
    {
      "epoch": 2.111607142857143,
      "grad_norm": 0.9776839017868042,
      "learning_rate": 0.0013169642857142857,
      "loss": 2.5218,
      "step": 330
    },
    {
      "epoch": 2.1339285714285716,
      "grad_norm": 1.1775952577590942,
      "learning_rate": 0.001205357142857143,
      "loss": 2.6112,
      "step": 340
    },
    {
      "epoch": 2.15625,
      "grad_norm": 1.1614340543746948,
      "learning_rate": 0.00109375,
      "loss": 2.8098,
      "step": 350
    },
    {
      "epoch": 2.1785714285714284,
      "grad_norm": 1.5740162134170532,
      "learning_rate": 0.0009821428571428572,
      "loss": 2.5155,
      "step": 360
    },
    {
      "epoch": 2.200892857142857,
      "grad_norm": 0.8294963240623474,
      "learning_rate": 0.0008705357142857143,
      "loss": 2.6925,
      "step": 370
    },
    {
      "epoch": 2.2232142857142856,
      "grad_norm": 0.6589123010635376,
      "learning_rate": 0.0007589285714285714,
      "loss": 2.6367,
      "step": 380
    },
    {
      "epoch": 2.2455357142857144,
      "grad_norm": 1.022390604019165,
      "learning_rate": 0.0006473214285714286,
      "loss": 2.6994,
      "step": 390
    },
    {
      "epoch": 2.267857142857143,
      "grad_norm": 0.9776459336280823,
      "learning_rate": 0.0005357142857142857,
      "loss": 2.6655,
      "step": 400
    },
    {
      "epoch": 2.2901785714285716,
      "grad_norm": 0.6604984402656555,
      "learning_rate": 0.0004241071428571429,
      "loss": 2.503,
      "step": 410
    },
    {
      "epoch": 2.3125,
      "grad_norm": 0.8852252960205078,
      "learning_rate": 0.0003125,
      "loss": 2.5164,
      "step": 420
    },
    {
      "epoch": 2.3125,
      "eval_accuracy": 0.09375,
      "eval_loss": 2.632814645767212,
      "eval_runtime": 46.978,
      "eval_samples_per_second": 1.362,
      "eval_steps_per_second": 0.341,
      "step": 420
    },
    {
      "epoch": 3.0223214285714284,
      "grad_norm": 0.6743168234825134,
      "learning_rate": 0.00020089285714285717,
      "loss": 2.4885,
      "step": 430
    },
    {
      "epoch": 3.044642857142857,
      "grad_norm": 0.9455771446228027,
      "learning_rate": 8.928571428571429e-05,
      "loss": 2.4843,
      "step": 440
    },
    {
      "epoch": 3.0625,
      "eval_accuracy": 0.09375,
      "eval_loss": 2.6358964443206787,
      "eval_runtime": 48.0713,
      "eval_samples_per_second": 1.331,
      "eval_steps_per_second": 0.333,
      "step": 448
    },
    {
      "epoch": 3.0625,
      "step": 448,
      "total_flos": 2.2294481154124677e+18,
      "train_loss": 2.6722778379917145,
      "train_runtime": 2217.7009,
      "train_samples_per_second": 0.808,
      "train_steps_per_second": 0.202
    },
    {
      "epoch": 3.0625,
      "eval_accuracy": 0.10975609756097561,
      "eval_loss": 2.736180067062378,
      "eval_runtime": 72.4695,
      "eval_samples_per_second": 1.132,
      "eval_steps_per_second": 0.29,
      "step": 448
    },
    {
      "epoch": 3.0625,
      "eval_accuracy": 0.10975609756097561,
      "eval_loss": 2.736180067062378,
      "eval_runtime": 71.6531,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 0.293,
      "step": 448
    }
  ],
  "logging_steps": 10,
  "max_steps": 448,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2294481154124677e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}