trainer_state.json

{
  "best_metric": 0.9589333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0170/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": 0.9650863409042358,
      "learning_rate": 8.657457896300791e-05,
      "loss": 0.6327,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.25583741068840027,
      "eval_runtime": 7.1356,
      "eval_samples_per_second": 525.533,
      "eval_steps_per_second": 8.268,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 36.720977783203125,
      "learning_rate": 7.681980515339464e-05,
      "loss": 0.1334,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.22143137454986572,
      "eval_runtime": 6.9553,
      "eval_samples_per_second": 539.159,
      "eval_steps_per_second": 8.483,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.608771324157715,
      "learning_rate": 6.222075445642905e-05,
      "loss": 0.0626,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.21358735859394073,
      "eval_runtime": 7.3643,
      "eval_samples_per_second": 509.215,
      "eval_steps_per_second": 8.012,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.032919690012931824,
      "learning_rate": 4.5e-05,
      "loss": 0.03,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9429333333333333,
      "eval_loss": 0.2188883274793625,
      "eval_runtime": 6.5349,
      "eval_samples_per_second": 573.84,
      "eval_steps_per_second": 9.028,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04310397803783417,
      "learning_rate": 2.7779245543570963e-05,
      "loss": 0.012,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9589333333333333,
      "eval_loss": 0.16719397902488708,
      "eval_runtime": 8.2481,
      "eval_samples_per_second": 454.653,
      "eval_steps_per_second": 7.153,
      "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
}