trainer_state.json

{
  "best_metric": 0.8786666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0017/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 94.3195571899414,
      "learning_rate": 8.554359905560886e-05,
      "loss": 2.8183,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7266666666666667,
      "eval_loss": 1.05388605594635,
      "eval_runtime": 7.1515,
      "eval_samples_per_second": 524.367,
      "eval_steps_per_second": 8.25,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 96.1217269897461,
      "learning_rate": 7.305704108364301e-05,
      "loss": 0.7311,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8386666666666667,
      "eval_loss": 0.5456063747406006,
      "eval_runtime": 7.0326,
      "eval_samples_per_second": 533.234,
      "eval_steps_per_second": 8.39,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 102.28990936279297,
      "learning_rate": 5.501344202803415e-05,
      "loss": 0.4255,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.868,
      "eval_loss": 0.449314147233963,
      "eval_runtime": 7.0392,
      "eval_samples_per_second": 532.733,
      "eval_steps_per_second": 8.382,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 79.8839340209961,
      "learning_rate": 3.498655797196586e-05,
      "loss": 0.2791,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.4313231110572815,
      "eval_runtime": 7.1085,
      "eval_samples_per_second": 527.539,
      "eval_steps_per_second": 8.3,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 53.18885803222656,
      "learning_rate": 1.6942958916356995e-05,
      "loss": 0.2032,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.41322338581085205,
      "eval_runtime": 7.0681,
      "eval_samples_per_second": 530.552,
      "eval_steps_per_second": 8.347,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}