trainer_state.json

{
  "best_metric": 0.9851851851851852,
  "best_model_checkpoint": "/kaggle/working/swin-brain-plane-classification/checkpoint-45",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.199264049530029,
      "learning_rate": 5e-05,
      "loss": 1.1833,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6074074074074074,
      "eval_loss": 0.9675570130348206,
      "eval_runtime": 0.7682,
      "eval_samples_per_second": 175.727,
      "eval_steps_per_second": 6.508,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.081261157989502,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.8399,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8592592592592593,
      "eval_loss": 0.5346508026123047,
      "eval_runtime": 0.7504,
      "eval_samples_per_second": 179.9,
      "eval_steps_per_second": 6.663,
      "step": 10
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.020309925079346,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.5341,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9481481481481482,
      "eval_loss": 0.2379625141620636,
      "eval_runtime": 0.7591,
      "eval_samples_per_second": 177.839,
      "eval_steps_per_second": 6.587,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.26108455657959,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3583,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9629629629629629,
      "eval_loss": 0.13244035840034485,
      "eval_runtime": 0.7541,
      "eval_samples_per_second": 179.024,
      "eval_steps_per_second": 6.631,
      "step": 20
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.511073112487793,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.2197,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9555555555555556,
      "eval_loss": 0.1311105489730835,
      "eval_runtime": 0.7578,
      "eval_samples_per_second": 178.154,
      "eval_steps_per_second": 6.598,
      "step": 25
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.359658241271973,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.1995,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9777777777777777,
      "eval_loss": 0.08695662766695023,
      "eval_runtime": 0.7501,
      "eval_samples_per_second": 179.972,
      "eval_steps_per_second": 6.666,
      "step": 30
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.365365028381348,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.1485,
      "step": 35
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9777777777777777,
      "eval_loss": 0.11073008179664612,
      "eval_runtime": 0.7524,
      "eval_samples_per_second": 179.431,
      "eval_steps_per_second": 6.646,
      "step": 35
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.843384265899658,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.1689,
      "step": 40
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9777777777777777,
      "eval_loss": 0.07976409047842026,
      "eval_runtime": 0.7575,
      "eval_samples_per_second": 178.206,
      "eval_steps_per_second": 6.6,
      "step": 40
    },
    {
      "epoch": 9.0,
      "grad_norm": 4.395670413970947,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.1339,
      "step": 45
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9851851851851852,
      "eval_loss": 0.05875137820839882,
      "eval_runtime": 0.7546,
      "eval_samples_per_second": 178.893,
      "eval_steps_per_second": 6.626,
      "step": 45
    },
    {
      "epoch": 10.0,
      "grad_norm": 7.337897777557373,
      "learning_rate": 0.0,
      "loss": 0.1623,
      "step": 50
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9777777777777777,
      "eval_loss": 0.06197558343410492,
      "eval_runtime": 0.7834,
      "eval_samples_per_second": 172.335,
      "eval_steps_per_second": 6.383,
      "step": 50
    },
    {
      "epoch": 10.0,
      "step": 50,
      "total_flos": 1.565971061889024e+17,
      "train_loss": 0.394845541715622,
      "train_runtime": 86.4231,
      "train_samples_per_second": 72.897,
      "train_steps_per_second": 0.579
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1.565971061889024e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}