trainer_state.json

{
  "best_metric": 0.9562666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0869/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": 0.7502056360244751,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.6876,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.20280416309833527,
      "eval_runtime": 11.4029,
      "eval_samples_per_second": 328.865,
      "eval_steps_per_second": 5.174,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1483200490474701,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.1231,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.22741711139678955,
      "eval_runtime": 11.4328,
      "eval_samples_per_second": 328.004,
      "eval_steps_per_second": 5.161,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04390304535627365,
      "learning_rate": 3.5e-05,
      "loss": 0.053,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.19377493858337402,
      "eval_runtime": 11.4965,
      "eval_samples_per_second": 326.185,
      "eval_steps_per_second": 5.132,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04046060889959335,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0159,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9538666666666666,
      "eval_loss": 0.17779748141765594,
      "eval_runtime": 11.4576,
      "eval_samples_per_second": 327.294,
      "eval_steps_per_second": 5.149,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3658474385738373,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0076,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.956,
      "eval_loss": 0.1700756847858429,
      "eval_runtime": 11.3925,
      "eval_samples_per_second": 329.164,
      "eval_steps_per_second": 5.179,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3250828683376312,
      "learning_rate": 0.0,
      "loss": 0.0049,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9562666666666667,
      "eval_loss": 0.16626565158367157,
      "eval_runtime": 11.505,
      "eval_samples_per_second": 325.944,
      "eval_steps_per_second": 5.128,
      "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
}