trainer_state.json

{
  "best_metric": 0.3472,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0024/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": 14.410115242004395,
      "learning_rate": 0.00045308279750597147,
      "loss": 3.4454,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1736,
      "eval_loss": 3.1152546405792236,
      "eval_runtime": 5.4601,
      "eval_samples_per_second": 686.805,
      "eval_steps_per_second": 10.806,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.872701644897461,
      "learning_rate": 0.00032859887408054946,
      "loss": 2.9255,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21653333333333333,
      "eval_loss": 2.8915603160858154,
      "eval_runtime": 5.2088,
      "eval_samples_per_second": 719.937,
      "eval_steps_per_second": 11.327,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.531230926513672,
      "learning_rate": 0.00017409285223383064,
      "loss": 2.6596,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2904,
      "eval_loss": 2.607163190841675,
      "eval_runtime": 5.2518,
      "eval_samples_per_second": 714.041,
      "eval_steps_per_second": 11.234,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.342174530029297,
      "learning_rate": 4.8580780844727946e-05,
      "loss": 2.3792,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3312,
      "eval_loss": 2.442992687225342,
      "eval_runtime": 5.2614,
      "eval_samples_per_second": 712.744,
      "eval_steps_per_second": 11.214,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.594440460205078,
      "learning_rate": 4.00518547519213e-09,
      "loss": 2.1106,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3472,
      "eval_loss": 2.429314136505127,
      "eval_runtime": 5.2657,
      "eval_samples_per_second": 712.156,
      "eval_steps_per_second": 11.205,
      "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
}