trainer_state.json

{
  "best_metric": 0.8858666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0319/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": 16.442495346069336,
      "learning_rate": 5e-05,
      "loss": 0.8569,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8570666666666666,
      "eval_loss": 0.48315343260765076,
      "eval_runtime": 6.5229,
      "eval_samples_per_second": 574.901,
      "eval_steps_per_second": 9.045,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.120173215866089,
      "learning_rate": 5e-05,
      "loss": 0.2269,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8818666666666667,
      "eval_loss": 0.3977842330932617,
      "eval_runtime": 6.3584,
      "eval_samples_per_second": 589.775,
      "eval_steps_per_second": 9.279,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.999114990234375,
      "learning_rate": 5e-05,
      "loss": 0.1212,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4836024045944214,
      "eval_runtime": 6.2523,
      "eval_samples_per_second": 599.776,
      "eval_steps_per_second": 9.436,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.005533615592867136,
      "learning_rate": 5e-05,
      "loss": 0.0852,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.5095071792602539,
      "eval_runtime": 7.7792,
      "eval_samples_per_second": 482.053,
      "eval_steps_per_second": 7.584,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.7430849075317383,
      "learning_rate": 5e-05,
      "loss": 0.0677,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.4815800189971924,
      "eval_runtime": 6.3793,
      "eval_samples_per_second": 587.835,
      "eval_steps_per_second": 9.249,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.004901567008346319,
      "learning_rate": 5e-05,
      "loss": 0.0608,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.4990997314453125,
      "eval_runtime": 6.3195,
      "eval_samples_per_second": 593.399,
      "eval_steps_per_second": 9.336,
      "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
}