{
  "best_metric": 0.9714285714285714,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300",
  "epoch": 3.25,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "grad_norm": 10.176301956176758,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.3354,
      "step": 10
    },
    {
      "epoch": 0.07,
      "grad_norm": 9.711071014404297,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.276,
      "step": 20
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.255990982055664,
      "learning_rate": 5e-05,
      "loss": 2.2642,
      "step": 30
    },
    {
      "epoch": 0.13,
      "grad_norm": 9.329790115356445,
      "learning_rate": 4.814814814814815e-05,
      "loss": 1.9688,
      "step": 40
    },
    {
      "epoch": 0.17,
      "grad_norm": 13.978023529052734,
      "learning_rate": 4.62962962962963e-05,
      "loss": 2.0701,
      "step": 50
    },
    {
      "epoch": 0.2,
      "grad_norm": 11.406329154968262,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.8035,
      "step": 60
    },
    {
      "epoch": 0.23,
      "grad_norm": 12.162630081176758,
      "learning_rate": 4.259259259259259e-05,
      "loss": 1.7378,
      "step": 70
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.44285714285714284,
      "eval_loss": 1.5572420358657837,
      "eval_runtime": 20.4778,
      "eval_samples_per_second": 3.418,
      "eval_steps_per_second": 0.879,
      "step": 75
    },
    {
      "epoch": 1.02,
      "grad_norm": 17.996007919311523,
      "learning_rate": 4.074074074074074e-05,
      "loss": 1.3051,
      "step": 80
    },
    {
      "epoch": 1.05,
      "grad_norm": 14.904123306274414,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.1915,
      "step": 90
    },
    {
      "epoch": 1.08,
      "grad_norm": 12.795023918151855,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.2382,
      "step": 100
    },
    {
      "epoch": 1.12,
      "grad_norm": 6.919280529022217,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.7473,
      "step": 110
    },
    {
      "epoch": 1.15,
      "grad_norm": 9.821967124938965,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8309,
      "step": 120
    },
    {
      "epoch": 1.18,
      "grad_norm": 37.302799224853516,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.6167,
      "step": 130
    },
    {
      "epoch": 1.22,
      "grad_norm": 6.461385250091553,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.5146,
      "step": 140
    },
    {
      "epoch": 1.25,
      "grad_norm": 6.602764129638672,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.8534,
      "step": 150
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.8428571428571429,
      "eval_loss": 0.5460595488548279,
      "eval_runtime": 20.4645,
      "eval_samples_per_second": 3.421,
      "eval_steps_per_second": 0.88,
      "step": 150
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.2533912658691406,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.3078,
      "step": 160
    },
    {
      "epoch": 2.07,
      "grad_norm": 12.430404663085938,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.4105,
      "step": 170
    },
    {
      "epoch": 2.1,
      "grad_norm": 2.3423736095428467,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.324,
      "step": 180
    },
    {
      "epoch": 2.13,
      "grad_norm": 7.257168292999268,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.4082,
      "step": 190
    },
    {
      "epoch": 2.17,
      "grad_norm": 1.3173214197158813,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.3382,
      "step": 200
    },
    {
      "epoch": 2.2,
      "grad_norm": 7.214090347290039,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.1829,
      "step": 210
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.520891547203064,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.2809,
      "step": 220
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.8,
      "eval_loss": 0.4151771664619446,
      "eval_runtime": 20.0344,
      "eval_samples_per_second": 3.494,
      "eval_steps_per_second": 0.898,
      "step": 225
    },
    {
      "epoch": 3.02,
      "grad_norm": 1.3751813173294067,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.2315,
      "step": 230
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.3773820996284485,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.1139,
      "step": 240
    },
    {
      "epoch": 3.08,
      "grad_norm": 10.172246932983398,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.1207,
      "step": 250
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.3173903822898865,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0985,
      "step": 260
    },
    {
      "epoch": 3.15,
      "grad_norm": 3.554419994354248,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.091,
      "step": 270
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.5874926447868347,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.203,
      "step": 280
    },
    {
      "epoch": 3.22,
      "grad_norm": 1.359855055809021,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.2804,
      "step": 290
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.3671231269836426,
      "learning_rate": 0.0,
      "loss": 0.2052,
      "step": 300
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.12919138371944427,
      "eval_runtime": 20.4637,
      "eval_samples_per_second": 3.421,
      "eval_steps_per_second": 0.88,
      "step": 300
    },
    {
      "epoch": 3.25,
      "step": 300,
      "total_flos": 1.495384188125184e+18,
      "train_loss": 0.8450019814570745,
      "train_runtime": 806.0143,
      "train_samples_per_second": 1.489,
      "train_steps_per_second": 0.372
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9096774193548387,
      "eval_loss": 0.2958908975124359,
      "eval_runtime": 45.0779,
      "eval_samples_per_second": 3.438,
      "eval_steps_per_second": 0.865,
      "step": 300
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.9096774193548387,
      "eval_loss": 0.2958908677101135,
      "eval_runtime": 44.2297,
      "eval_samples_per_second": 3.504,
      "eval_steps_per_second": 0.882,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.495384188125184e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}