trainer_state.json

{
  "best_metric": 0.9608,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0153/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": 0.2357640266418457,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.6578,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.22200016677379608,
      "eval_runtime": 6.8508,
      "eval_samples_per_second": 547.378,
      "eval_steps_per_second": 8.612,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09473360329866409,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.1186,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.18318131566047668,
      "eval_runtime": 6.6286,
      "eval_samples_per_second": 565.729,
      "eval_steps_per_second": 8.901,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.053070858120918274,
      "learning_rate": 3.5e-05,
      "loss": 0.0501,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9570666666666666,
      "eval_loss": 0.16767558455467224,
      "eval_runtime": 6.9559,
      "eval_samples_per_second": 539.11,
      "eval_steps_per_second": 8.482,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.040220703929662704,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0168,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9576,
      "eval_loss": 0.1649273782968521,
      "eval_runtime": 6.7426,
      "eval_samples_per_second": 556.169,
      "eval_steps_per_second": 8.75,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.650630533695221,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0063,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9608,
      "eval_loss": 0.15782125294208527,
      "eval_runtime": 6.8336,
      "eval_samples_per_second": 548.76,
      "eval_steps_per_second": 8.634,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}