trainer_state.json

{
  "best_metric": 0.9490666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0390/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": 0.3899373412132263,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.7084,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.24158141016960144,
      "eval_runtime": 6.5677,
      "eval_samples_per_second": 570.973,
      "eval_steps_per_second": 8.983,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.325087785720825,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.1429,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.20413313806056976,
      "eval_runtime": 5.6381,
      "eval_samples_per_second": 665.115,
      "eval_steps_per_second": 10.464,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.255486398935318,
      "learning_rate": 3.5e-05,
      "loss": 0.0652,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.2237406224012375,
      "eval_runtime": 5.6809,
      "eval_samples_per_second": 660.112,
      "eval_steps_per_second": 10.386,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.059558380395174026,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0275,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.1968831568956375,
      "eval_runtime": 5.6685,
      "eval_samples_per_second": 661.545,
      "eval_steps_per_second": 10.408,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.018895957618951797,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0123,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.19339054822921753,
      "eval_runtime": 5.6916,
      "eval_samples_per_second": 658.863,
      "eval_steps_per_second": 10.366,
      "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
}