trainer_state.json

{
  "best_metric": 0.8832,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0510/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": 7e-05,
      "loss": 1.5142,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8362666666666667,
      "eval_loss": 0.6425653100013733,
      "eval_runtime": 6.0372,
      "eval_samples_per_second": 621.154,
      "eval_steps_per_second": 9.773,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.509000837802887,
      "learning_rate": 7e-05,
      "loss": 0.4352,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.493673712015152,
      "eval_runtime": 5.6861,
      "eval_samples_per_second": 659.498,
      "eval_steps_per_second": 10.376,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.24306213855743408,
      "learning_rate": 7e-05,
      "loss": 0.2384,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8554666666666667,
      "eval_loss": 0.483403742313385,
      "eval_runtime": 6.2518,
      "eval_samples_per_second": 599.824,
      "eval_steps_per_second": 9.437,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.08368632197380066,
      "learning_rate": 7e-05,
      "loss": 0.1326,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.4907594919204712,
      "eval_runtime": 5.6631,
      "eval_samples_per_second": 662.179,
      "eval_steps_per_second": 10.418,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10073795914649963,
      "learning_rate": 7e-05,
      "loss": 0.0958,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.4410150945186615,
      "eval_runtime": 5.7292,
      "eval_samples_per_second": 654.539,
      "eval_steps_per_second": 10.298,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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
}