{
  "best_metric": 0.9142857142857143,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
  "epoch": 7.101351351351352,
  "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": 6.34252405166626,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0466,
      "step": 10
    },
    {
      "epoch": 0.12837837837837837,
      "eval_accuracy": 0.6142857142857143,
      "eval_loss": 1.6348506212234497,
      "eval_runtime": 6.1663,
      "eval_samples_per_second": 11.352,
      "eval_steps_per_second": 0.811,
      "step": 19
    },
    {
      "epoch": 1.0067567567567568,
      "grad_norm": 7.780186176300049,
      "learning_rate": 4.81203007518797e-05,
      "loss": 1.8425,
      "step": 20
    },
    {
      "epoch": 1.0743243243243243,
      "grad_norm": 7.907790184020996,
      "learning_rate": 4.43609022556391e-05,
      "loss": 1.348,
      "step": 30
    },
    {
      "epoch": 1.1283783783783783,
      "eval_accuracy": 0.8428571428571429,
      "eval_loss": 0.804053783416748,
      "eval_runtime": 6.6922,
      "eval_samples_per_second": 10.46,
      "eval_steps_per_second": 0.747,
      "step": 38
    },
    {
      "epoch": 2.0135135135135136,
      "grad_norm": 5.862756729125977,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 0.8369,
      "step": 40
    },
    {
      "epoch": 2.081081081081081,
      "grad_norm": 5.44201135635376,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.6208,
      "step": 50
    },
    {
      "epoch": 2.1283783783783785,
      "eval_accuracy": 0.7285714285714285,
      "eval_loss": 0.7582912445068359,
      "eval_runtime": 6.1646,
      "eval_samples_per_second": 11.355,
      "eval_steps_per_second": 0.811,
      "step": 57
    },
    {
      "epoch": 3.02027027027027,
      "grad_norm": 12.206607818603516,
      "learning_rate": 3.3082706766917295e-05,
      "loss": 0.5199,
      "step": 60
    },
    {
      "epoch": 3.0878378378378377,
      "grad_norm": 5.501271724700928,
      "learning_rate": 2.9323308270676693e-05,
      "loss": 0.332,
      "step": 70
    },
    {
      "epoch": 3.1283783783783785,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.45565441250801086,
      "eval_runtime": 6.0418,
      "eval_samples_per_second": 11.586,
      "eval_steps_per_second": 0.828,
      "step": 76
    },
    {
      "epoch": 4.027027027027027,
      "grad_norm": 7.0609965324401855,
      "learning_rate": 2.556390977443609e-05,
      "loss": 0.2761,
      "step": 80
    },
    {
      "epoch": 4.094594594594595,
      "grad_norm": 3.5807061195373535,
      "learning_rate": 2.1804511278195487e-05,
      "loss": 0.2229,
      "step": 90
    },
    {
      "epoch": 4.128378378378378,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.3132798373699188,
      "eval_runtime": 6.754,
      "eval_samples_per_second": 10.364,
      "eval_steps_per_second": 0.74,
      "step": 95
    },
    {
      "epoch": 5.033783783783784,
      "grad_norm": 1.8226597309112549,
      "learning_rate": 1.8045112781954888e-05,
      "loss": 0.2292,
      "step": 100
    },
    {
      "epoch": 5.101351351351352,
      "grad_norm": 6.401218414306641,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.1479,
      "step": 110
    },
    {
      "epoch": 5.128378378378378,
      "eval_accuracy": 0.9,
      "eval_loss": 0.2872016131877899,
      "eval_runtime": 5.5369,
      "eval_samples_per_second": 12.643,
      "eval_steps_per_second": 0.903,
      "step": 114
    },
    {
      "epoch": 6.04054054054054,
      "grad_norm": 4.436432361602783,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.0848,
      "step": 120
    },
    {
      "epoch": 6.108108108108108,
      "grad_norm": 1.9256197214126587,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.0761,
      "step": 130
    },
    {
      "epoch": 6.128378378378378,
      "eval_accuracy": 0.9,
      "eval_loss": 0.28876611590385437,
      "eval_runtime": 6.7507,
      "eval_samples_per_second": 10.369,
      "eval_steps_per_second": 0.741,
      "step": 133
    },
    {
      "epoch": 7.047297297297297,
      "grad_norm": 7.098940372467041,
      "learning_rate": 3.007518796992481e-06,
      "loss": 0.0696,
      "step": 140
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.26643699407577515,
      "eval_runtime": 6.7738,
      "eval_samples_per_second": 10.334,
      "eval_steps_per_second": 0.738,
      "step": 148
    },
    {
      "epoch": 7.101351351351352,
      "step": 148,
      "total_flos": 2.915999166844109e+18,
      "train_loss": 0.5872005439690642,
      "train_runtime": 676.4093,
      "train_samples_per_second": 3.501,
      "train_steps_per_second": 0.219
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9290322580645162,
      "eval_loss": 0.2252088487148285,
      "eval_runtime": 13.824,
      "eval_samples_per_second": 11.212,
      "eval_steps_per_second": 0.723,
      "step": 148
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9290322580645162,
      "eval_loss": 0.2266511768102646,
      "eval_runtime": 13.6046,
      "eval_samples_per_second": 11.393,
      "eval_steps_per_second": 0.735,
      "step": 148
    }
  ],
  "logging_steps": 10,
  "max_steps": 148,
  "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": 2.915999166844109e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}