trainer_state.json

{
  "best_metric": 0.7922666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0953/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": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.0001,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7024,
      "eval_loss": 0.9947742819786072,
      "eval_runtime": 6.3584,
      "eval_samples_per_second": 589.776,
      "eval_steps_per_second": 9.279,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.833688735961914,
      "learning_rate": 0.0003,
      "loss": 0.7594,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7664,
      "eval_loss": 0.7709715962409973,
      "eval_runtime": 6.3111,
      "eval_samples_per_second": 594.194,
      "eval_steps_per_second": 9.349,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.4602,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7752,
      "eval_loss": 0.7744066119194031,
      "eval_runtime": 6.327,
      "eval_samples_per_second": 592.702,
      "eval_steps_per_second": 9.325,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.8605542778968811,
      "learning_rate": 0.0003,
      "loss": 0.3041,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7810666666666667,
      "eval_loss": 0.7699115872383118,
      "eval_runtime": 6.2181,
      "eval_samples_per_second": 603.082,
      "eval_steps_per_second": 9.488,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.2334,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7922666666666667,
      "eval_loss": 0.7509628534317017,
      "eval_runtime": 6.2662,
      "eval_samples_per_second": 598.45,
      "eval_steps_per_second": 9.416,
      "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
}