trainer_state.json

{
  "best_metric": 0.9258666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0173/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": 6.626648902893066,
      "learning_rate": 5.604204204204204e-05,
      "loss": 0.8167,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.43035513162612915,
      "eval_runtime": 11.6883,
      "eval_samples_per_second": 320.834,
      "eval_steps_per_second": 5.048,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 44.98486328125,
      "learning_rate": 4.2042042042042036e-05,
      "loss": 0.2515,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.37828436493873596,
      "eval_runtime": 11.9222,
      "eval_samples_per_second": 314.54,
      "eval_steps_per_second": 4.949,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.344958305358887,
      "learning_rate": 2.8042042042042038e-05,
      "loss": 0.1089,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9,
      "eval_loss": 0.34193849563598633,
      "eval_runtime": 11.728,
      "eval_samples_per_second": 319.746,
      "eval_steps_per_second": 5.031,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.014975634403526783,
      "learning_rate": 1.404204204204204e-05,
      "loss": 0.048,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9192,
      "eval_loss": 0.2839203178882599,
      "eval_runtime": 11.765,
      "eval_samples_per_second": 318.742,
      "eval_steps_per_second": 5.015,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3030140399932861,
      "learning_rate": 4.204204204204204e-08,
      "loss": 0.0129,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9258666666666666,
      "eval_loss": 0.2653484642505646,
      "eval_runtime": 11.5022,
      "eval_samples_per_second": 326.024,
      "eval_steps_per_second": 5.129,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}