trainer_state.json

{
  "best_metric": 0.9544,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0986/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": 5.702232837677002,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6195,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9306666666666666,
      "eval_loss": 0.2522014081478119,
      "eval_runtime": 12.973,
      "eval_samples_per_second": 289.061,
      "eval_steps_per_second": 4.548,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05567952245473862,
      "learning_rate": 6e-05,
      "loss": 0.1154,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.1987573504447937,
      "eval_runtime": 16.3896,
      "eval_samples_per_second": 228.803,
      "eval_steps_per_second": 3.6,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.06749565899372101,
      "learning_rate": 4.5e-05,
      "loss": 0.0443,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.20027530193328857,
      "eval_runtime": 11.5882,
      "eval_samples_per_second": 323.605,
      "eval_steps_per_second": 5.091,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06894027441740036,
      "learning_rate": 3e-05,
      "loss": 0.0194,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.2237597554922104,
      "eval_runtime": 11.5871,
      "eval_samples_per_second": 323.636,
      "eval_steps_per_second": 5.092,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.13113661110401154,
      "learning_rate": 1.5e-05,
      "loss": 0.007,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9541333333333334,
      "eval_loss": 0.18618349730968475,
      "eval_runtime": 11.575,
      "eval_samples_per_second": 323.974,
      "eval_steps_per_second": 5.097,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.017091702669858932,
      "learning_rate": 0.0,
      "loss": 0.0035,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9544,
      "eval_loss": 0.1848646104335785,
      "eval_runtime": 11.5752,
      "eval_samples_per_second": 323.969,
      "eval_steps_per_second": 5.097,
      "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
}