trainer_state.json

{
  "best_metric": 0.8637333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0572/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": 86.44953155517578,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.3546,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6237333333333334,
      "eval_loss": 1.862235188484192,
      "eval_runtime": 7.531,
      "eval_samples_per_second": 497.944,
      "eval_steps_per_second": 7.834,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 131.12750244140625,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 1.1103,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8,
      "eval_loss": 0.7222151160240173,
      "eval_runtime": 7.8559,
      "eval_samples_per_second": 477.349,
      "eval_steps_per_second": 7.51,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 198.15379333496094,
      "learning_rate": 3.5e-05,
      "loss": 0.6171,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.576557993888855,
      "eval_runtime": 7.3553,
      "eval_samples_per_second": 509.834,
      "eval_steps_per_second": 8.021,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 182.50015258789062,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.4815,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5012703537940979,
      "eval_runtime": 7.3402,
      "eval_samples_per_second": 510.882,
      "eval_steps_per_second": 8.038,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 174.18687438964844,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.4302,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.47206541895866394,
      "eval_runtime": 7.3539,
      "eval_samples_per_second": 509.934,
      "eval_steps_per_second": 8.023,
      "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
}