trainer_state.json

{
  "best_metric": 0.8738666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0640/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 72.57778930664062,
      "learning_rate": 0.0003,
      "loss": 1.6042,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8186666666666667,
      "eval_loss": 0.5739161968231201,
      "eval_runtime": 13.4026,
      "eval_samples_per_second": 279.797,
      "eval_steps_per_second": 4.402,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 37.350975036621094,
      "learning_rate": 0.0003,
      "loss": 0.4836,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8549333333333333,
      "eval_loss": 0.4674868583679199,
      "eval_runtime": 13.269,
      "eval_samples_per_second": 282.613,
      "eval_steps_per_second": 4.446,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 146.84283447265625,
      "learning_rate": 0.0003,
      "loss": 0.3044,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.42595699429512024,
      "eval_runtime": 13.1437,
      "eval_samples_per_second": 285.308,
      "eval_steps_per_second": 4.489,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 112.85053253173828,
      "learning_rate": 0.0003,
      "loss": 0.209,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4385715425014496,
      "eval_runtime": 13.2748,
      "eval_samples_per_second": 282.491,
      "eval_steps_per_second": 4.445,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.00667953491211,
      "learning_rate": 0.0003,
      "loss": 0.1641,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.4884811341762543,
      "eval_runtime": 13.2859,
      "eval_samples_per_second": 282.253,
      "eval_steps_per_second": 4.441,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 68.09761810302734,
      "learning_rate": 0.0003,
      "loss": 0.1272,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.49524205923080444,
      "eval_runtime": 13.1929,
      "eval_samples_per_second": 284.243,
      "eval_steps_per_second": 4.472,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}