{
  "best_metric": 0.12027937173843384,
  "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 285,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 0.9387953877449036,
      "learning_rate": 9.649122807017545e-06,
      "loss": 0.6299,
      "step": 10
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.4054632186889648,
      "learning_rate": 9.298245614035088e-06,
      "loss": 0.5138,
      "step": 20
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.2556184530258179,
      "learning_rate": 8.947368421052632e-06,
      "loss": 0.4223,
      "step": 30
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 1.2750768661499023,
      "learning_rate": 8.596491228070176e-06,
      "loss": 0.3304,
      "step": 40
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 1.3711668252944946,
      "learning_rate": 8.24561403508772e-06,
      "loss": 0.293,
      "step": 50
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.8322893977165222,
      "learning_rate": 7.894736842105265e-06,
      "loss": 0.2091,
      "step": 60
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 0.8177331686019897,
      "learning_rate": 7.5438596491228074e-06,
      "loss": 0.1938,
      "step": 70
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 1.0095038414001465,
      "learning_rate": 7.192982456140352e-06,
      "loss": 0.1586,
      "step": 80
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.5976330041885376,
      "learning_rate": 6.842105263157896e-06,
      "loss": 0.134,
      "step": 90
    },
    {
      "epoch": 1.7543859649122808,
      "grad_norm": 3.159658908843994,
      "learning_rate": 6.491228070175439e-06,
      "loss": 0.1313,
      "step": 100
    },
    {
      "epoch": 1.7543859649122808,
      "eval_accuracy": 0.960352422907489,
      "eval_confusion_matrix": [
        [
          57,
          9
        ],
        [
          0,
          161
        ]
      ],
      "eval_loss": 0.18016090989112854,
      "eval_runtime": 25.5277,
      "eval_samples_per_second": 8.892,
      "eval_steps_per_second": 0.313,
      "step": 100
    },
    {
      "epoch": 1.9298245614035088,
      "grad_norm": 4.4438323974609375,
      "learning_rate": 6.140350877192983e-06,
      "loss": 0.1357,
      "step": 110
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.554610013961792,
      "learning_rate": 5.789473684210527e-06,
      "loss": 0.1229,
      "step": 120
    },
    {
      "epoch": 2.280701754385965,
      "grad_norm": 0.2898980677127838,
      "learning_rate": 5.438596491228071e-06,
      "loss": 0.1219,
      "step": 130
    },
    {
      "epoch": 2.456140350877193,
      "grad_norm": 0.43265607953071594,
      "learning_rate": 5.087719298245615e-06,
      "loss": 0.0867,
      "step": 140
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.32516348361968994,
      "learning_rate": 4.736842105263158e-06,
      "loss": 0.0936,
      "step": 150
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 0.4287051558494568,
      "learning_rate": 4.385964912280702e-06,
      "loss": 0.0874,
      "step": 160
    },
    {
      "epoch": 2.982456140350877,
      "grad_norm": 3.535736560821533,
      "learning_rate": 4.035087719298246e-06,
      "loss": 0.0887,
      "step": 170
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 0.3152014911174774,
      "learning_rate": 3.6842105263157896e-06,
      "loss": 0.0949,
      "step": 180
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.28197869658470154,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0864,
      "step": 190
    },
    {
      "epoch": 3.5087719298245617,
      "grad_norm": 4.776849269866943,
      "learning_rate": 2.9824561403508774e-06,
      "loss": 0.0978,
      "step": 200
    },
    {
      "epoch": 3.5087719298245617,
      "eval_accuracy": 0.9691629955947136,
      "eval_confusion_matrix": [
        [
          59,
          7
        ],
        [
          0,
          161
        ]
      ],
      "eval_loss": 0.12027937173843384,
      "eval_runtime": 24.0716,
      "eval_samples_per_second": 9.43,
      "eval_steps_per_second": 0.332,
      "step": 200
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 0.3222098648548126,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.1081,
      "step": 210
    },
    {
      "epoch": 3.8596491228070176,
      "grad_norm": 0.9184278845787048,
      "learning_rate": 2.280701754385965e-06,
      "loss": 0.074,
      "step": 220
    },
    {
      "epoch": 4.035087719298246,
      "grad_norm": 0.5896315574645996,
      "learning_rate": 1.929824561403509e-06,
      "loss": 0.1126,
      "step": 230
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 0.3399348556995392,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 0.0792,
      "step": 240
    },
    {
      "epoch": 4.385964912280702,
      "grad_norm": 0.26603880524635315,
      "learning_rate": 1.2280701754385965e-06,
      "loss": 0.0582,
      "step": 250
    },
    {
      "epoch": 4.56140350877193,
      "grad_norm": 0.25929567217826843,
      "learning_rate": 8.771929824561404e-07,
      "loss": 0.0581,
      "step": 260
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 0.26217120885849,
      "learning_rate": 5.263157894736843e-07,
      "loss": 0.0473,
      "step": 270
    },
    {
      "epoch": 4.912280701754386,
      "grad_norm": 0.3724278509616852,
      "learning_rate": 1.7543859649122808e-07,
      "loss": 0.0989,
      "step": 280
    },
    {
      "epoch": 5.0,
      "step": 285,
      "total_flos": 7.020774259082035e+17,
      "train_loss": 0.16548631944154438,
      "train_runtime": 2814.3096,
      "train_samples_per_second": 3.241,
      "train_steps_per_second": 0.101
    }
  ],
  "logging_steps": 10,
  "max_steps": 285,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.020774259082035e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}