trainer_state.json

{
  "best_global_step": 81,
  "best_metric": 0.9062870699881376,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-81",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 81,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 5.524842739105225,
      "learning_rate": 5e-05,
      "loss": 1.2682,
      "step": 10
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 4.206063270568848,
      "learning_rate": 4.305555555555556e-05,
      "loss": 0.6695,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8469750889679716,
      "eval_loss": 0.4013451039791107,
      "eval_runtime": 9.4164,
      "eval_samples_per_second": 89.525,
      "eval_steps_per_second": 2.867,
      "step": 27
    },
    {
      "epoch": 1.1132075471698113,
      "grad_norm": 6.539760112762451,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.4746,
      "step": 30
    },
    {
      "epoch": 1.490566037735849,
      "grad_norm": 4.813919544219971,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.4048,
      "step": 40
    },
    {
      "epoch": 1.8679245283018868,
      "grad_norm": 6.418631553649902,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.3488,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9051008303677343,
      "eval_loss": 0.25734663009643555,
      "eval_runtime": 8.9376,
      "eval_samples_per_second": 94.321,
      "eval_steps_per_second": 3.021,
      "step": 54
    },
    {
      "epoch": 2.2264150943396226,
      "grad_norm": 6.001177787780762,
      "learning_rate": 1.527777777777778e-05,
      "loss": 0.3491,
      "step": 60
    },
    {
      "epoch": 2.6037735849056602,
      "grad_norm": 7.376132011413574,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.2949,
      "step": 70
    },
    {
      "epoch": 2.981132075471698,
      "grad_norm": 5.631875514984131,
      "learning_rate": 1.388888888888889e-06,
      "loss": 0.3074,
      "step": 80
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9062870699881376,
      "eval_loss": 0.2386484593153,
      "eval_runtime": 8.9413,
      "eval_samples_per_second": 94.282,
      "eval_steps_per_second": 3.02,
      "step": 81
    },
    {
      "epoch": 3.0,
      "step": 81,
      "total_flos": 2.5123352003463168e+17,
      "train_loss": 0.5117499912962501,
      "train_runtime": 261.4945,
      "train_samples_per_second": 38.651,
      "train_steps_per_second": 0.31
    }
  ],
  "logging_steps": 10,
  "max_steps": 81,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.5123352003463168e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}