{
  "best_metric": 0.964824120603015,
  "best_model_checkpoint": "/kaggle/working/swin-brain-abnormalities-classification/checkpoint-279",
  "epoch": 14.838709677419354,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.989247311827957,
      "grad_norm": 12.819618225097656,
      "learning_rate": 3.285714285714286e-05,
      "loss": 0.928,
      "step": 23
    },
    {
      "epoch": 0.989247311827957,
      "eval_accuracy": 0.7705192629815746,
      "eval_loss": 0.6080142259597778,
      "eval_runtime": 2.7919,
      "eval_samples_per_second": 213.832,
      "eval_steps_per_second": 6.805,
      "step": 23
    },
    {
      "epoch": 1.978494623655914,
      "grad_norm": 15.878138542175293,
      "learning_rate": 4.822580645161291e-05,
      "loss": 0.508,
      "step": 46
    },
    {
      "epoch": 1.978494623655914,
      "eval_accuracy": 0.916247906197655,
      "eval_loss": 0.24024777114391327,
      "eval_runtime": 2.7697,
      "eval_samples_per_second": 215.545,
      "eval_steps_per_second": 6.86,
      "step": 46
    },
    {
      "epoch": 2.967741935483871,
      "grad_norm": 15.8612699508667,
      "learning_rate": 4.451612903225807e-05,
      "loss": 0.3178,
      "step": 69
    },
    {
      "epoch": 2.967741935483871,
      "eval_accuracy": 0.9246231155778895,
      "eval_loss": 0.21210229396820068,
      "eval_runtime": 2.7786,
      "eval_samples_per_second": 214.86,
      "eval_steps_per_second": 6.838,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.1905574798584,
      "learning_rate": 4.0645161290322584e-05,
      "loss": 0.2338,
      "step": 93
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9363484087102177,
      "eval_loss": 0.20449711382389069,
      "eval_runtime": 2.7356,
      "eval_samples_per_second": 218.234,
      "eval_steps_per_second": 6.945,
      "step": 93
    },
    {
      "epoch": 4.989247311827957,
      "grad_norm": 7.354104042053223,
      "learning_rate": 3.6935483870967746e-05,
      "loss": 0.1788,
      "step": 116
    },
    {
      "epoch": 4.989247311827957,
      "eval_accuracy": 0.9296482412060302,
      "eval_loss": 0.24434839189052582,
      "eval_runtime": 2.754,
      "eval_samples_per_second": 216.777,
      "eval_steps_per_second": 6.899,
      "step": 116
    },
    {
      "epoch": 5.978494623655914,
      "grad_norm": 12.372457504272461,
      "learning_rate": 3.322580645161291e-05,
      "loss": 0.1675,
      "step": 139
    },
    {
      "epoch": 5.978494623655914,
      "eval_accuracy": 0.9430485762144054,
      "eval_loss": 0.14566932618618011,
      "eval_runtime": 2.7575,
      "eval_samples_per_second": 216.503,
      "eval_steps_per_second": 6.89,
      "step": 139
    },
    {
      "epoch": 6.967741935483871,
      "grad_norm": 13.181761741638184,
      "learning_rate": 2.9516129032258067e-05,
      "loss": 0.155,
      "step": 162
    },
    {
      "epoch": 6.967741935483871,
      "eval_accuracy": 0.9514237855946399,
      "eval_loss": 0.17081618309020996,
      "eval_runtime": 2.8126,
      "eval_samples_per_second": 212.256,
      "eval_steps_per_second": 6.755,
      "step": 162
    },
    {
      "epoch": 8.0,
      "grad_norm": 43.71896743774414,
      "learning_rate": 2.5645161290322582e-05,
      "loss": 0.1316,
      "step": 186
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9530988274706867,
      "eval_loss": 0.1554775983095169,
      "eval_runtime": 2.7304,
      "eval_samples_per_second": 218.645,
      "eval_steps_per_second": 6.959,
      "step": 186
    },
    {
      "epoch": 8.989247311827956,
      "grad_norm": 8.03194808959961,
      "learning_rate": 2.1935483870967744e-05,
      "loss": 0.1099,
      "step": 209
    },
    {
      "epoch": 8.989247311827956,
      "eval_accuracy": 0.9530988274706867,
      "eval_loss": 0.17324857413768768,
      "eval_runtime": 2.7989,
      "eval_samples_per_second": 213.295,
      "eval_steps_per_second": 6.788,
      "step": 209
    },
    {
      "epoch": 9.978494623655914,
      "grad_norm": 5.151728630065918,
      "learning_rate": 1.8225806451612903e-05,
      "loss": 0.1121,
      "step": 232
    },
    {
      "epoch": 9.978494623655914,
      "eval_accuracy": 0.9581239530988275,
      "eval_loss": 0.13575538992881775,
      "eval_runtime": 2.7641,
      "eval_samples_per_second": 215.983,
      "eval_steps_per_second": 6.874,
      "step": 232
    },
    {
      "epoch": 10.967741935483872,
      "grad_norm": 14.949158668518066,
      "learning_rate": 1.4516129032258066e-05,
      "loss": 0.1007,
      "step": 255
    },
    {
      "epoch": 10.967741935483872,
      "eval_accuracy": 0.9514237855946399,
      "eval_loss": 0.21547764539718628,
      "eval_runtime": 2.7877,
      "eval_samples_per_second": 214.157,
      "eval_steps_per_second": 6.816,
      "step": 255
    },
    {
      "epoch": 12.0,
      "grad_norm": 4.855920314788818,
      "learning_rate": 1.064516129032258e-05,
      "loss": 0.0951,
      "step": 279
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.964824120603015,
      "eval_loss": 0.15059159696102142,
      "eval_runtime": 2.7534,
      "eval_samples_per_second": 216.826,
      "eval_steps_per_second": 6.901,
      "step": 279
    },
    {
      "epoch": 12.989247311827956,
      "grad_norm": 5.928957462310791,
      "learning_rate": 6.935483870967742e-06,
      "loss": 0.0841,
      "step": 302
    },
    {
      "epoch": 12.989247311827956,
      "eval_accuracy": 0.9530988274706867,
      "eval_loss": 0.1921372413635254,
      "eval_runtime": 2.8151,
      "eval_samples_per_second": 212.072,
      "eval_steps_per_second": 6.749,
      "step": 302
    },
    {
      "epoch": 13.978494623655914,
      "grad_norm": 2.9877490997314453,
      "learning_rate": 3.225806451612903e-06,
      "loss": 0.0778,
      "step": 325
    },
    {
      "epoch": 13.978494623655914,
      "eval_accuracy": 0.9530988274706867,
      "eval_loss": 0.20410552620887756,
      "eval_runtime": 2.7514,
      "eval_samples_per_second": 216.98,
      "eval_steps_per_second": 6.906,
      "step": 325
    },
    {
      "epoch": 14.838709677419354,
      "grad_norm": 5.737996578216553,
      "learning_rate": 0.0,
      "loss": 0.0768,
      "step": 345
    },
    {
      "epoch": 14.838709677419354,
      "eval_accuracy": 0.9547738693467337,
      "eval_loss": 0.1908799260854721,
      "eval_runtime": 2.96,
      "eval_samples_per_second": 201.69,
      "eval_steps_per_second": 6.419,
      "step": 345
    },
    {
      "epoch": 14.838709677419354,
      "step": 345,
      "total_flos": 1.0886233115316142e+18,
      "train_loss": 0.21913787420245184,
      "train_runtime": 552.9922,
      "train_samples_per_second": 80.019,
      "train_steps_per_second": 0.624
    }
  ],
  "logging_steps": 1,
  "max_steps": 345,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 1.0886233115316142e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}