trainer_state.json

{
  "best_metric": 0.8247863247863247,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-111",
  "epoch": 2.315315315315315,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.3105,
      "step": 10
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.595959595959596e-05,
      "loss": 2.173,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 2.1044,
      "step": 30
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.49145299145299143,
      "eval_loss": 1.7608355283737183,
      "eval_runtime": 20.0376,
      "eval_samples_per_second": 11.678,
      "eval_steps_per_second": 1.497,
      "step": 38
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.5858585858585855e-05,
      "loss": 1.9043,
      "step": 40
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.080808080808081e-05,
      "loss": 1.4396,
      "step": 50
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.575757575757576e-05,
      "loss": 1.0538,
      "step": 60
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.070707070707071e-05,
      "loss": 0.875,
      "step": 70
    },
    {
      "epoch": 1.34,
      "eval_accuracy": 0.7350427350427351,
      "eval_loss": 0.7819657325744629,
      "eval_runtime": 20.4305,
      "eval_samples_per_second": 11.453,
      "eval_steps_per_second": 1.468,
      "step": 76
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.565656565656566e-05,
      "loss": 0.8563,
      "step": 80
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.0606060606060607e-05,
      "loss": 0.6119,
      "step": 90
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.5474,
      "step": 100
    },
    {
      "epoch": 2.31,
      "learning_rate": 5.050505050505052e-07,
      "loss": 0.5103,
      "step": 110
    },
    {
      "epoch": 2.32,
      "eval_accuracy": 0.8247863247863247,
      "eval_loss": 0.6440751552581787,
      "eval_runtime": 20.0847,
      "eval_samples_per_second": 11.651,
      "eval_steps_per_second": 1.494,
      "step": 111
    },
    {
      "epoch": 2.32,
      "step": 111,
      "total_flos": 1.0966150712918016e+18,
      "train_loss": 1.2986480625900063,
      "train_runtime": 215.193,
      "train_samples_per_second": 4.127,
      "train_steps_per_second": 0.516
    },
    {
      "epoch": 2.32,
      "eval_accuracy": 0.8194444444444444,
      "eval_loss": 0.5837831497192383,
      "eval_runtime": 17.7976,
      "eval_samples_per_second": 12.136,
      "eval_steps_per_second": 1.517,
      "step": 111
    },
    {
      "epoch": 2.32,
      "eval_accuracy": 0.8194444444444444,
      "eval_loss": 0.5837830901145935,
      "eval_runtime": 17.7379,
      "eval_samples_per_second": 12.177,
      "eval_steps_per_second": 1.522,
      "step": 111
    }
  ],
  "max_steps": 111,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.0966150712918016e+18,
  "trial_name": null,
  "trial_params": null
}