trainer_state.json

{
  "best_metric": 0.7394666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0608/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": 101.00923156738281,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8513,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33786666666666665,
      "eval_loss": 3.7621169090270996,
      "eval_runtime": 7.8869,
      "eval_samples_per_second": 475.473,
      "eval_steps_per_second": 7.481,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 231.39559936523438,
      "learning_rate": 2.25e-05,
      "loss": 3.2202,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5448,
      "eval_loss": 2.6190640926361084,
      "eval_runtime": 8.039,
      "eval_samples_per_second": 466.473,
      "eval_steps_per_second": 7.339,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 318.2526550292969,
      "learning_rate": 1.5e-05,
      "loss": 1.9511,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6858666666666666,
      "eval_loss": 1.5331541299819946,
      "eval_runtime": 7.9004,
      "eval_samples_per_second": 474.66,
      "eval_steps_per_second": 7.468,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 312.0162353515625,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.3815,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7328,
      "eval_loss": 1.2073661088943481,
      "eval_runtime": 7.8821,
      "eval_samples_per_second": 475.76,
      "eval_steps_per_second": 7.485,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 186.2245635986328,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.1752,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7394666666666667,
      "eval_loss": 1.1438153982162476,
      "eval_runtime": 8.0033,
      "eval_samples_per_second": 468.556,
      "eval_steps_per_second": 7.372,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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
}