trainer_state.json

{
  "best_metric": 0.9498666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0595/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 15.773454666137695,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.8697,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.2536258399486542,
      "eval_runtime": 13.1739,
      "eval_samples_per_second": 284.654,
      "eval_steps_per_second": 4.479,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.523527145385742,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.14,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.22347693145275116,
      "eval_runtime": 13.1379,
      "eval_samples_per_second": 285.434,
      "eval_steps_per_second": 4.491,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9229381084442139,
      "learning_rate": 2.5e-05,
      "loss": 0.0573,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.2079075574874878,
      "eval_runtime": 23.7681,
      "eval_samples_per_second": 157.775,
      "eval_steps_per_second": 2.482,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06014665961265564,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0235,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9461333333333334,
      "eval_loss": 0.2129424661397934,
      "eval_runtime": 12.9768,
      "eval_samples_per_second": 288.978,
      "eval_steps_per_second": 4.547,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07344943284988403,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0105,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9485333333333333,
      "eval_loss": 0.21157731115818024,
      "eval_runtime": 13.0107,
      "eval_samples_per_second": 288.225,
      "eval_steps_per_second": 4.535,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.039831895381212234,
      "learning_rate": 0.0,
      "loss": 0.0066,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.20966947078704834,
      "eval_runtime": 13.1287,
      "eval_samples_per_second": 285.633,
      "eval_steps_per_second": 4.494,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}