trainer_state.json

{
  "best_metric": 0.8666666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0191/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": 84.47499084472656,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.2138,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6490666666666667,
      "eval_loss": 1.59994375705719,
      "eval_runtime": 14.1899,
      "eval_samples_per_second": 264.272,
      "eval_steps_per_second": 4.158,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 86.1268081665039,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.9351,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8034666666666667,
      "eval_loss": 0.6672253608703613,
      "eval_runtime": 13.2269,
      "eval_samples_per_second": 283.513,
      "eval_steps_per_second": 4.461,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 101.21334838867188,
      "learning_rate": 3.5e-05,
      "loss": 0.516,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8456,
      "eval_loss": 0.5095032453536987,
      "eval_runtime": 13.179,
      "eval_samples_per_second": 284.544,
      "eval_steps_per_second": 4.477,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 93.6971435546875,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.3707,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8525333333333334,
      "eval_loss": 0.47677311301231384,
      "eval_runtime": 13.2513,
      "eval_samples_per_second": 282.991,
      "eval_steps_per_second": 4.452,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 239.6897430419922,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.3133,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8666666666666667,
      "eval_loss": 0.43970340490341187,
      "eval_runtime": 13.4837,
      "eval_samples_per_second": 278.113,
      "eval_steps_per_second": 4.376,
      "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
}