{
  "best_metric": 0.26666666666666666,
  "best_model_checkpoint": "videomae-base-finetuned-caer-subset-5-classes-base-model\\checkpoint-139",
  "epoch": 1.444,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 11.07775592803955,
      "learning_rate": 2e-05,
      "loss": 1.6854,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 16.159523010253906,
      "learning_rate": 4e-05,
      "loss": 1.6475,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 15.219178199768066,
      "learning_rate": 4.888888888888889e-05,
      "loss": 1.6296,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 12.341416358947754,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.7157,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 14.330547332763672,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.652,
      "step": 50
    },
    {
      "epoch": 0.24,
      "grad_norm": 12.243963241577148,
      "learning_rate": 4.222222222222222e-05,
      "loss": 1.6353,
      "step": 60
    },
    {
      "epoch": 0.28,
      "grad_norm": 12.711626052856445,
      "learning_rate": 4e-05,
      "loss": 1.6923,
      "step": 70
    },
    {
      "epoch": 0.32,
      "grad_norm": 16.082073211669922,
      "learning_rate": 3.777777777777778e-05,
      "loss": 1.5922,
      "step": 80
    },
    {
      "epoch": 0.36,
      "grad_norm": 16.63982582092285,
      "learning_rate": 3.555555555555556e-05,
      "loss": 1.7151,
      "step": 90
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.993603706359863,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.718,
      "step": 100
    },
    {
      "epoch": 0.44,
      "grad_norm": 11.654336929321289,
      "learning_rate": 3.111111111111111e-05,
      "loss": 1.6497,
      "step": 110
    },
    {
      "epoch": 0.48,
      "grad_norm": 10.800435066223145,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 1.6542,
      "step": 120
    },
    {
      "epoch": 0.52,
      "grad_norm": 9.841632843017578,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.5763,
      "step": 130
    },
    {
      "epoch": 0.56,
      "eval_accuracy": 0.26666666666666666,
      "eval_loss": 1.641332983970642,
      "eval_runtime": 9.3839,
      "eval_samples_per_second": 3.197,
      "eval_steps_per_second": 1.598,
      "step": 139
    },
    {
      "epoch": 1.0,
      "grad_norm": 13.519031524658203,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 1.5659,
      "step": 140
    },
    {
      "epoch": 1.04,
      "grad_norm": 9.212859153747559,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.6481,
      "step": 150
    },
    {
      "epoch": 1.08,
      "grad_norm": 10.454906463623047,
      "learning_rate": 2e-05,
      "loss": 1.7381,
      "step": 160
    },
    {
      "epoch": 1.12,
      "grad_norm": 11.107510566711426,
      "learning_rate": 1.777777777777778e-05,
      "loss": 1.6243,
      "step": 170
    },
    {
      "epoch": 1.16,
      "grad_norm": 9.847452163696289,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 1.5956,
      "step": 180
    },
    {
      "epoch": 1.2,
      "grad_norm": 11.35783576965332,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.6769,
      "step": 190
    },
    {
      "epoch": 1.24,
      "grad_norm": 8.935040473937988,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.5996,
      "step": 200
    },
    {
      "epoch": 1.28,
      "grad_norm": 10.564764976501465,
      "learning_rate": 8.88888888888889e-06,
      "loss": 1.7105,
      "step": 210
    },
    {
      "epoch": 1.32,
      "grad_norm": 9.259597778320312,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6253,
      "step": 220
    },
    {
      "epoch": 1.36,
      "grad_norm": 15.238162994384766,
      "learning_rate": 4.444444444444445e-06,
      "loss": 1.5752,
      "step": 230
    },
    {
      "epoch": 1.4,
      "grad_norm": 9.198563575744629,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 1.5624,
      "step": 240
    },
    {
      "epoch": 1.44,
      "grad_norm": 9.007689476013184,
      "learning_rate": 0.0,
      "loss": 1.5825,
      "step": 250
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.2,
      "eval_loss": 1.615497350692749,
      "eval_runtime": 9.657,
      "eval_samples_per_second": 3.107,
      "eval_steps_per_second": 1.553,
      "step": 250
    },
    {
      "epoch": 1.44,
      "step": 250,
      "total_flos": 6.2304896360448e+17,
      "train_loss": 1.6427093963623047,
      "train_runtime": 248.4449,
      "train_samples_per_second": 2.013,
      "train_steps_per_second": 1.006
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.2328767123287671,
      "eval_loss": 1.6937663555145264,
      "eval_runtime": 21.9862,
      "eval_samples_per_second": 3.32,
      "eval_steps_per_second": 1.683,
      "step": 250
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.2328767123287671,
      "eval_loss": 1.693766474723816,
      "eval_runtime": 22.6545,
      "eval_samples_per_second": 3.222,
      "eval_steps_per_second": 1.633,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 6.2304896360448e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}