trainer_state.json

{
  "best_metric": 0.3924731182795699,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-47",
  "epoch": 8.88888888888889,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8888888888888888,
      "eval_accuracy": 0.13978494623655913,
      "eval_loss": 2.8975272178649902,
      "eval_runtime": 21.8981,
      "eval_samples_per_second": 8.494,
      "eval_steps_per_second": 0.137,
      "step": 6
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 3.0052640438079834,
      "learning_rate": 4.62962962962963e-05,
      "loss": 2.9658,
      "step": 10
    },
    {
      "epoch": 1.925925925925926,
      "eval_accuracy": 0.22043010752688172,
      "eval_loss": 2.6865546703338623,
      "eval_runtime": 21.7609,
      "eval_samples_per_second": 8.547,
      "eval_steps_per_second": 0.138,
      "step": 13
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 4.745502948760986,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 2.6529,
      "step": 20
    },
    {
      "epoch": 2.962962962962963,
      "eval_accuracy": 0.3010752688172043,
      "eval_loss": 2.4369595050811768,
      "eval_runtime": 21.5886,
      "eval_samples_per_second": 8.616,
      "eval_steps_per_second": 0.139,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.34946236559139787,
      "eval_loss": 2.2516093254089355,
      "eval_runtime": 21.6045,
      "eval_samples_per_second": 8.609,
      "eval_steps_per_second": 0.139,
      "step": 27
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 6.134488105773926,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.3311,
      "step": 30
    },
    {
      "epoch": 4.888888888888889,
      "eval_accuracy": 0.3709677419354839,
      "eval_loss": 2.1685309410095215,
      "eval_runtime": 21.6954,
      "eval_samples_per_second": 8.573,
      "eval_steps_per_second": 0.138,
      "step": 33
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 7.691503524780273,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 2.1441,
      "step": 40
    },
    {
      "epoch": 5.925925925925926,
      "eval_accuracy": 0.3655913978494624,
      "eval_loss": 2.0986852645874023,
      "eval_runtime": 21.7432,
      "eval_samples_per_second": 8.554,
      "eval_steps_per_second": 0.138,
      "step": 40
    },
    {
      "epoch": 6.962962962962963,
      "eval_accuracy": 0.3924731182795699,
      "eval_loss": 2.05673885345459,
      "eval_runtime": 21.4068,
      "eval_samples_per_second": 8.689,
      "eval_steps_per_second": 0.14,
      "step": 47
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 6.981929302215576,
      "learning_rate": 9.259259259259259e-06,
      "loss": 2.0507,
      "step": 50
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3870967741935484,
      "eval_loss": 2.041614055633545,
      "eval_runtime": 21.6481,
      "eval_samples_per_second": 8.592,
      "eval_steps_per_second": 0.139,
      "step": 54
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 5.651075839996338,
      "learning_rate": 0.0,
      "loss": 1.988,
      "step": 60
    },
    {
      "epoch": 8.88888888888889,
      "eval_accuracy": 0.3763440860215054,
      "eval_loss": 2.0368075370788574,
      "eval_runtime": 21.6178,
      "eval_samples_per_second": 8.604,
      "eval_steps_per_second": 0.139,
      "step": 60
    },
    {
      "epoch": 8.88888888888889,
      "step": 60,
      "total_flos": 3.7044103653339955e+17,
      "train_loss": 2.3554419835408527,
      "train_runtime": 1715.7637,
      "train_samples_per_second": 9.733,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "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": 3.7044103653339955e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}