trainer_state.json

{
  "best_metric": 0.876,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0206/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": 5e-05,
      "loss": 0.8111,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.4855836033821106,
      "eval_runtime": 6.9434,
      "eval_samples_per_second": 540.083,
      "eval_steps_per_second": 8.497,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 96.61934661865234,
      "learning_rate": 5e-05,
      "loss": 0.2783,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.428962767124176,
      "eval_runtime": 8.3674,
      "eval_samples_per_second": 448.17,
      "eval_steps_per_second": 7.051,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.454345226287842,
      "learning_rate": 5e-05,
      "loss": 0.1568,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.45718657970428467,
      "eval_runtime": 7.6765,
      "eval_samples_per_second": 488.507,
      "eval_steps_per_second": 7.686,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 35.553375244140625,
      "learning_rate": 5e-05,
      "loss": 0.114,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8728,
      "eval_loss": 0.49637481570243835,
      "eval_runtime": 7.4917,
      "eval_samples_per_second": 500.554,
      "eval_steps_per_second": 7.875,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 25.236854553222656,
      "learning_rate": 5e-05,
      "loss": 0.0833,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.5164222717285156,
      "eval_runtime": 6.8395,
      "eval_samples_per_second": 548.286,
      "eval_steps_per_second": 8.626,
      "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
}