trainer_state.json

{
  "best_metric": 0.7442666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0201/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": 76.22543334960938,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8473,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3253333333333333,
      "eval_loss": 3.723315954208374,
      "eval_runtime": 7.9996,
      "eval_samples_per_second": 468.774,
      "eval_steps_per_second": 7.375,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 710.7960205078125,
      "learning_rate": 2.25e-05,
      "loss": 3.2509,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5464,
      "eval_loss": 2.602921724319458,
      "eval_runtime": 7.9951,
      "eval_samples_per_second": 469.037,
      "eval_steps_per_second": 7.38,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 272.2463073730469,
      "learning_rate": 1.5e-05,
      "loss": 1.9249,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6898666666666666,
      "eval_loss": 1.4412859678268433,
      "eval_runtime": 7.3038,
      "eval_samples_per_second": 513.429,
      "eval_steps_per_second": 8.078,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 138.12547302246094,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.2132,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7309333333333333,
      "eval_loss": 1.1102101802825928,
      "eval_runtime": 7.272,
      "eval_samples_per_second": 515.678,
      "eval_steps_per_second": 8.113,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 228.4980010986328,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.012,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7442666666666666,
      "eval_loss": 1.0119237899780273,
      "eval_runtime": 7.3526,
      "eval_samples_per_second": 510.023,
      "eval_steps_per_second": 8.024,
      "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}