trainer_state.json

{
  "best_metric": 0.9277333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0606/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": 1.6784658432006836,
      "learning_rate": 0.0001,
      "loss": 0.5992,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9157333333333333,
      "eval_loss": 0.28317388892173767,
      "eval_runtime": 13.4144,
      "eval_samples_per_second": 279.55,
      "eval_steps_per_second": 4.398,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6161868572235107,
      "learning_rate": 0.0001,
      "loss": 0.1575,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9226666666666666,
      "eval_loss": 0.27453795075416565,
      "eval_runtime": 13.5688,
      "eval_samples_per_second": 276.37,
      "eval_steps_per_second": 4.348,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.014710146933794022,
      "learning_rate": 0.0001,
      "loss": 0.0926,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9210666666666667,
      "eval_loss": 0.2773815095424652,
      "eval_runtime": 13.5148,
      "eval_samples_per_second": 277.474,
      "eval_steps_per_second": 4.366,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02338651567697525,
      "learning_rate": 0.0001,
      "loss": 0.0682,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9237333333333333,
      "eval_loss": 0.3106629550457001,
      "eval_runtime": 13.4102,
      "eval_samples_per_second": 279.639,
      "eval_steps_per_second": 4.4,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.09984494000673294,
      "learning_rate": 0.0001,
      "loss": 0.0535,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9277333333333333,
      "eval_loss": 0.3056626319885254,
      "eval_runtime": 13.5354,
      "eval_samples_per_second": 277.052,
      "eval_steps_per_second": 4.359,
      "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}