trainer_state.json

{
  "best_metric": 0.8677333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0755/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": 133.30435180664062,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.1267,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6701333333333334,
      "eval_loss": 1.5844824314117432,
      "eval_runtime": 7.9481,
      "eval_samples_per_second": 471.809,
      "eval_steps_per_second": 7.423,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 200.49990844726562,
      "learning_rate": 6e-05,
      "loss": 0.9562,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8098666666666666,
      "eval_loss": 0.6883994936943054,
      "eval_runtime": 7.9851,
      "eval_samples_per_second": 469.625,
      "eval_steps_per_second": 7.389,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 98.93816375732422,
      "learning_rate": 4.5e-05,
      "loss": 0.6059,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.5511116981506348,
      "eval_runtime": 7.9849,
      "eval_samples_per_second": 469.638,
      "eval_steps_per_second": 7.389,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 113.85294342041016,
      "learning_rate": 3e-05,
      "loss": 0.4869,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.848,
      "eval_loss": 0.5143257975578308,
      "eval_runtime": 8.5149,
      "eval_samples_per_second": 440.406,
      "eval_steps_per_second": 6.929,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 127.41891479492188,
      "learning_rate": 1.5e-05,
      "loss": 0.4197,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4721313416957855,
      "eval_runtime": 8.0413,
      "eval_samples_per_second": 466.341,
      "eval_steps_per_second": 7.337,
      "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
}