trainer_state.json

{
  "best_metric": 0.8553459119496856,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-student_six_classes/checkpoint-23",
  "epoch": 2.8085106382978724,
  "eval_steps": 500,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.85,
      "grad_norm": 5.6343159675598145,
      "learning_rate": 3.965517241379311e-05,
      "loss": 1.4387,
      "step": 10
    },
    {
      "epoch": 0.94,
      "eval_accuracy": 0.6367924528301887,
      "eval_loss": 0.9083201885223389,
      "eval_runtime": 8.5969,
      "eval_samples_per_second": 73.98,
      "eval_steps_per_second": 2.326,
      "step": 11
    },
    {
      "epoch": 1.7,
      "grad_norm": 9.409465789794922,
      "learning_rate": 2.2413793103448276e-05,
      "loss": 0.7445,
      "step": 20
    },
    {
      "epoch": 1.96,
      "eval_accuracy": 0.8553459119496856,
      "eval_loss": 0.532645583152771,
      "eval_runtime": 10.5737,
      "eval_samples_per_second": 60.149,
      "eval_steps_per_second": 1.891,
      "step": 23
    },
    {
      "epoch": 2.55,
      "grad_norm": 7.701065540313721,
      "learning_rate": 5.172413793103448e-06,
      "loss": 0.4879,
      "step": 30
    },
    {
      "epoch": 2.81,
      "eval_accuracy": 0.7751572327044025,
      "eval_loss": 0.4916297495365143,
      "eval_runtime": 7.7495,
      "eval_samples_per_second": 82.07,
      "eval_steps_per_second": 2.581,
      "step": 33
    },
    {
      "epoch": 2.81,
      "step": 33,
      "total_flos": 1.0400908167453082e+17,
      "train_loss": 0.8560382669622247,
      "train_runtime": 123.6615,
      "train_samples_per_second": 36.001,
      "train_steps_per_second": 0.267
    }
  ],
  "logging_steps": 10,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.0400908167453082e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}