trainer_state.json

{
  "best_metric": 0.932,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0250/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": 2.7439513206481934,
      "learning_rate": 0.00025,
      "loss": 0.5949,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.4120529890060425,
      "eval_runtime": 12.2271,
      "eval_samples_per_second": 306.697,
      "eval_steps_per_second": 4.825,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05754368007183075,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.229,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.40196654200553894,
      "eval_runtime": 12.3582,
      "eval_samples_per_second": 303.442,
      "eval_steps_per_second": 4.774,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7240079641342163,
      "learning_rate": 0.00015,
      "loss": 0.1117,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.36361268162727356,
      "eval_runtime": 12.4189,
      "eval_samples_per_second": 301.959,
      "eval_steps_per_second": 4.751,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.012444403022527695,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.0469,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.3289934992790222,
      "eval_runtime": 11.5843,
      "eval_samples_per_second": 323.715,
      "eval_steps_per_second": 5.093,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0055501083843410015,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0162,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.2958865463733673,
      "eval_runtime": 11.3692,
      "eval_samples_per_second": 329.839,
      "eval_steps_per_second": 5.189,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.003321966854855418,
      "learning_rate": 0.0,
      "loss": 0.0033,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.28558677434921265,
      "eval_runtime": 12.4984,
      "eval_samples_per_second": 300.039,
      "eval_steps_per_second": 4.721,
      "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
}