trainer_state.json

{
  "best_metric": 0.8757333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0353/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": 70.30839538574219,
      "learning_rate": 0.0001,
      "loss": 2.9649,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7189333333333333,
      "eval_loss": 1.0272213220596313,
      "eval_runtime": 7.395,
      "eval_samples_per_second": 507.098,
      "eval_steps_per_second": 7.978,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 104.7484130859375,
      "learning_rate": 0.0001,
      "loss": 0.7466,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8314666666666667,
      "eval_loss": 0.53610759973526,
      "eval_runtime": 7.3587,
      "eval_samples_per_second": 509.6,
      "eval_steps_per_second": 8.018,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 33.25865936279297,
      "learning_rate": 0.0001,
      "loss": 0.4738,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.44955602288246155,
      "eval_runtime": 7.3402,
      "eval_samples_per_second": 510.886,
      "eval_steps_per_second": 8.038,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 51.55455780029297,
      "learning_rate": 0.0001,
      "loss": 0.3394,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.4213697910308838,
      "eval_runtime": 7.5547,
      "eval_samples_per_second": 496.382,
      "eval_steps_per_second": 7.81,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 61.2143440246582,
      "learning_rate": 0.0001,
      "loss": 0.2685,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.4073422849178314,
      "eval_runtime": 7.3861,
      "eval_samples_per_second": 507.708,
      "eval_steps_per_second": 7.988,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}