{
  "best_metric": 0.34285714285714286,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-75",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "grad_norm": 10.281960487365723,
      "learning_rate": 4.850746268656717e-05,
      "loss": 2.3601,
      "step": 10
    },
    {
      "epoch": 0.27,
      "grad_norm": 11.063933372497559,
      "learning_rate": 4.104477611940299e-05,
      "loss": 2.211,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 10.219429016113281,
      "learning_rate": 3.358208955223881e-05,
      "loss": 2.0991,
      "step": 30
    },
    {
      "epoch": 0.53,
      "grad_norm": 10.343681335449219,
      "learning_rate": 2.6119402985074626e-05,
      "loss": 2.0743,
      "step": 40
    },
    {
      "epoch": 0.67,
      "grad_norm": 16.12186622619629,
      "learning_rate": 1.865671641791045e-05,
      "loss": 2.0251,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 11.030004501342773,
      "learning_rate": 1.119402985074627e-05,
      "loss": 1.7871,
      "step": 60
    },
    {
      "epoch": 0.93,
      "grad_norm": 16.10842514038086,
      "learning_rate": 3.7313432835820893e-06,
      "loss": 1.886,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.34285714285714286,
      "eval_loss": 1.6963948011398315,
      "eval_runtime": 13.6425,
      "eval_samples_per_second": 5.131,
      "eval_steps_per_second": 1.319,
      "step": 75
    },
    {
      "epoch": 1.0,
      "step": 75,
      "total_flos": 3.73846047031296e+17,
      "train_loss": 2.0343732452392578,
      "train_runtime": 184.675,
      "train_samples_per_second": 1.624,
      "train_steps_per_second": 0.406
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.36774193548387096,
      "eval_loss": 1.8300830125808716,
      "eval_runtime": 29.3467,
      "eval_samples_per_second": 5.282,
      "eval_steps_per_second": 1.329,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.36774193548387096,
      "eval_loss": 1.830082893371582,
      "eval_runtime": 27.9297,
      "eval_samples_per_second": 5.55,
      "eval_steps_per_second": 1.396,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.36774193548387096,
      "eval_loss": 1.8300830125808716,
      "eval_runtime": 28.0549,
      "eval_samples_per_second": 5.525,
      "eval_steps_per_second": 1.39,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.36774193548387096,
      "eval_loss": 1.830082893371582,
      "eval_runtime": 28.5402,
      "eval_samples_per_second": 5.431,
      "eval_steps_per_second": 1.366,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 3.73846047031296e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}