trainer_state.json

{
  "best_metric": 0.7321212121212122,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-woody/checkpoint-58",
  "epoch": 6.0,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.5619,
      "step": 10
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.5605,
      "step": 20
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.5729,
      "step": 30
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0,
      "loss": 0.5495,
      "step": 40
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0,
      "loss": 0.574,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 23.8499,
      "eval_samples_per_second": 34.591,
      "eval_steps_per_second": 1.09,
      "step": 58
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0,
      "loss": 0.5409,
      "step": 60
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0,
      "loss": 0.5495,
      "step": 70
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0,
      "loss": 0.5537,
      "step": 80
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0,
      "loss": 0.5539,
      "step": 90
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0,
      "loss": 0.5504,
      "step": 100
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0,
      "loss": 0.5784,
      "step": 110
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 23.8406,
      "eval_samples_per_second": 34.605,
      "eval_steps_per_second": 1.091,
      "step": 116
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0,
      "loss": 0.5645,
      "step": 120
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0,
      "loss": 0.5768,
      "step": 130
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0,
      "loss": 0.5415,
      "step": 140
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0,
      "loss": 0.576,
      "step": 150
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0,
      "loss": 0.5632,
      "step": 160
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0,
      "loss": 0.5476,
      "step": 170
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 23.8868,
      "eval_samples_per_second": 34.538,
      "eval_steps_per_second": 1.088,
      "step": 174
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0,
      "loss": 0.5587,
      "step": 180
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0,
      "loss": 0.5587,
      "step": 190
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0,
      "loss": 0.5611,
      "step": 200
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0,
      "loss": 0.5516,
      "step": 210
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0,
      "loss": 0.5601,
      "step": 220
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0,
      "loss": 0.5571,
      "step": 230
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 23.9324,
      "eval_samples_per_second": 34.472,
      "eval_steps_per_second": 1.086,
      "step": 232
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0,
      "loss": 0.5592,
      "step": 240
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0,
      "loss": 0.551,
      "step": 250
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0,
      "loss": 0.5555,
      "step": 260
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0,
      "loss": 0.5747,
      "step": 270
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0,
      "loss": 0.5506,
      "step": 280
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.5577,
      "step": 290
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 23.9303,
      "eval_samples_per_second": 34.475,
      "eval_steps_per_second": 1.086,
      "step": 290
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0,
      "loss": 0.5576,
      "step": 300
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0,
      "loss": 0.5426,
      "step": 310
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0,
      "loss": 0.5654,
      "step": 320
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.0,
      "loss": 0.5757,
      "step": 330
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.0,
      "loss": 0.5625,
      "step": 340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7321212121212122,
      "eval_loss": 0.5392071008682251,
      "eval_runtime": 24.6087,
      "eval_samples_per_second": 33.525,
      "eval_steps_per_second": 1.057,
      "step": 348
    },
    {
      "epoch": 6.0,
      "step": 348,
      "total_flos": 1.1070360374520545e+18,
      "train_loss": 0.5594298346289273,
      "train_runtime": 1485.7871,
      "train_samples_per_second": 29.976,
      "train_steps_per_second": 0.234
    }
  ],
  "max_steps": 348,
  "num_train_epochs": 6,
  "total_flos": 1.1070360374520545e+18,
  "trial_name": null,
  "trial_params": null
}