{
  "best_metric": 0.6727272727272727,
  "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-114",
  "epoch": 3.22972972972973,
  "eval_steps": 500,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 10.621135711669922,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7046,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 15.56004524230957,
      "learning_rate": 4.81203007518797e-05,
      "loss": 0.6959,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 12.019503593444824,
      "learning_rate": 4.43609022556391e-05,
      "loss": 0.6924,
      "step": 30
    },
    {
      "epoch": 0.25675675675675674,
      "eval_accuracy": 0.5454545454545454,
      "eval_loss": 0.6671423316001892,
      "eval_runtime": 167.6467,
      "eval_samples_per_second": 0.328,
      "eval_steps_per_second": 0.084,
      "step": 38
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 5.8651123046875,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 0.7766,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 4.48609733581543,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.7431,
      "step": 50
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 17.070894241333008,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 0.7388,
      "step": 60
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 5.109278678894043,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.6664,
      "step": 70
    },
    {
      "epoch": 1.2567567567567568,
      "eval_accuracy": 0.6181818181818182,
      "eval_loss": 0.6748194694519043,
      "eval_runtime": 170.038,
      "eval_samples_per_second": 0.323,
      "eval_steps_per_second": 0.082,
      "step": 76
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 8.704899787902832,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.7082,
      "step": 80
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 7.929505825042725,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.6429,
      "step": 90
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 17.118267059326172,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.8039,
      "step": 100
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 7.988255500793457,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.5947,
      "step": 110
    },
    {
      "epoch": 2.2567567567567566,
      "eval_accuracy": 0.6727272727272727,
      "eval_loss": 0.6094833612442017,
      "eval_runtime": 168.4773,
      "eval_samples_per_second": 0.326,
      "eval_steps_per_second": 0.083,
      "step": 114
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 7.859794616699219,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.5892,
      "step": 120
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 12.87205982208252,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.5001,
      "step": 130
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 13.842416763305664,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.5049,
      "step": 140
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.6181818181818182,
      "eval_loss": 0.6914771199226379,
      "eval_runtime": 166.1396,
      "eval_samples_per_second": 0.331,
      "eval_steps_per_second": 0.084,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "step": 148,
      "total_flos": 7.264556556620268e+17,
      "train_loss": 0.6650454998016357,
      "train_runtime": 4992.096,
      "train_samples_per_second": 0.119,
      "train_steps_per_second": 0.03
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.6255781054496765,
      "eval_runtime": 189.5334,
      "eval_samples_per_second": 0.364,
      "eval_steps_per_second": 0.095,
      "step": 148
    },
    {
      "epoch": 3.22972972972973,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.6255780458450317,
      "eval_runtime": 237.0624,
      "eval_samples_per_second": 0.291,
      "eval_steps_per_second": 0.076,
      "step": 148
    }
  ],
  "logging_steps": 10,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 7.264556556620268e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}