trainer_state.json

{
  "best_metric": 0.9346666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0645/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": 8.813031196594238,
      "learning_rate": 5e-05,
      "loss": 0.8563,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.26279088854789734,
      "eval_runtime": 11.3094,
      "eval_samples_per_second": 331.583,
      "eval_steps_per_second": 5.217,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5e-05,
      "loss": 0.1258,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9306666666666666,
      "eval_loss": 0.2325691431760788,
      "eval_runtime": 11.2984,
      "eval_samples_per_second": 331.904,
      "eval_steps_per_second": 5.222,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.08593228459358215,
      "learning_rate": 5e-05,
      "loss": 0.053,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.2565654516220093,
      "eval_runtime": 11.0421,
      "eval_samples_per_second": 339.608,
      "eval_steps_per_second": 5.343,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.502264022827148,
      "learning_rate": 5e-05,
      "loss": 0.0298,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.2741648852825165,
      "eval_runtime": 11.4818,
      "eval_samples_per_second": 326.605,
      "eval_steps_per_second": 5.139,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.019043147563934326,
      "learning_rate": 5e-05,
      "loss": 0.0171,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.27967944741249084,
      "eval_runtime": 11.1367,
      "eval_samples_per_second": 336.724,
      "eval_steps_per_second": 5.298,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}