trainer_state.json

{
  "best_metric": 0.9424,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0620/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": 0.08448620140552521,
      "learning_rate": 0.00025,
      "loss": 0.5811,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.3836095631122589,
      "eval_runtime": 12.0782,
      "eval_samples_per_second": 310.476,
      "eval_steps_per_second": 4.885,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04101579263806343,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.2299,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.3179427683353424,
      "eval_runtime": 11.7465,
      "eval_samples_per_second": 319.245,
      "eval_steps_per_second": 5.023,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.05000549182295799,
      "learning_rate": 0.00015,
      "loss": 0.1155,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.294179230928421,
      "eval_runtime": 12.2789,
      "eval_samples_per_second": 305.402,
      "eval_steps_per_second": 4.805,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05058682709932327,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.049,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.30035337805747986,
      "eval_runtime": 11.6397,
      "eval_samples_per_second": 322.173,
      "eval_steps_per_second": 5.069,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.46643832325935364,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0153,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9392,
      "eval_loss": 0.26747408509254456,
      "eval_runtime": 11.5108,
      "eval_samples_per_second": 325.78,
      "eval_steps_per_second": 5.126,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.022531863301992416,
      "learning_rate": 0.0,
      "loss": 0.0053,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9424,
      "eval_loss": 0.27480894327163696,
      "eval_runtime": 11.626,
      "eval_samples_per_second": 322.554,
      "eval_steps_per_second": 5.075,
      "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
}