trainer_state.json

{
  "best_metric": 0.9085333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0441/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": 2.0683603286743164,
      "learning_rate": 5.604204204204204e-05,
      "loss": 0.8271,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8378666666666666,
      "eval_loss": 0.49520230293273926,
      "eval_runtime": 7.1698,
      "eval_samples_per_second": 523.03,
      "eval_steps_per_second": 8.229,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 4.208408408408408e-05,
      "loss": 0.2805,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.4327380955219269,
      "eval_runtime": 6.9262,
      "eval_samples_per_second": 541.42,
      "eval_steps_per_second": 8.518,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 54.30440902709961,
      "learning_rate": 2.808408408408408e-05,
      "loss": 0.1187,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.3788091540336609,
      "eval_runtime": 7.0374,
      "eval_samples_per_second": 532.866,
      "eval_steps_per_second": 8.384,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.0902605056762695,
      "learning_rate": 1.4084084084084082e-05,
      "loss": 0.0455,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.3537125289440155,
      "eval_runtime": 7.0097,
      "eval_samples_per_second": 534.969,
      "eval_steps_per_second": 8.417,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4769321382045746,
      "learning_rate": 8.408408408408407e-08,
      "loss": 0.0139,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9085333333333333,
      "eval_loss": 0.325809508562088,
      "eval_runtime": 6.4951,
      "eval_samples_per_second": 577.356,
      "eval_steps_per_second": 9.084,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}