trainer_state.json

{
  "best_metric": 0.9445333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0891/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": 2.603332042694092,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6017,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9208,
      "eval_loss": 0.26967257261276245,
      "eval_runtime": 11.8305,
      "eval_samples_per_second": 316.978,
      "eval_steps_per_second": 4.987,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05037952959537506,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1409,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9285333333333333,
      "eval_loss": 0.2536710500717163,
      "eval_runtime": 11.8174,
      "eval_samples_per_second": 317.328,
      "eval_steps_per_second": 4.993,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.021221984177827835,
      "learning_rate": 5e-05,
      "loss": 0.0638,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.23000222444534302,
      "eval_runtime": 12.3604,
      "eval_samples_per_second": 303.389,
      "eval_steps_per_second": 4.773,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.008111350238323212,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0265,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.2424672544002533,
      "eval_runtime": 12.1148,
      "eval_samples_per_second": 309.538,
      "eval_steps_per_second": 4.87,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0295035969465971,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0099,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.22837942838668823,
      "eval_runtime": 11.9762,
      "eval_samples_per_second": 313.121,
      "eval_steps_per_second": 4.926,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.022662004455924034,
      "learning_rate": 0.0,
      "loss": 0.0059,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.21831467747688293,
      "eval_runtime": 12.2324,
      "eval_samples_per_second": 306.564,
      "eval_steps_per_second": 4.823,
      "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
}