trainer_state.json

{
  "best_metric": 0.8898666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0307/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 70.88812255859375,
      "learning_rate": 7e-05,
      "loss": 3.2034,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6602666666666667,
      "eval_loss": 1.4916390180587769,
      "eval_runtime": 7.7478,
      "eval_samples_per_second": 484.006,
      "eval_steps_per_second": 7.615,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 180.65335083007812,
      "learning_rate": 7e-05,
      "loss": 0.8972,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8234666666666667,
      "eval_loss": 0.5901433825492859,
      "eval_runtime": 7.6846,
      "eval_samples_per_second": 487.986,
      "eval_steps_per_second": 7.678,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 70.29180908203125,
      "learning_rate": 7e-05,
      "loss": 0.4822,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8570666666666666,
      "eval_loss": 0.46624723076820374,
      "eval_runtime": 7.7164,
      "eval_samples_per_second": 485.979,
      "eval_steps_per_second": 7.646,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 144.04161071777344,
      "learning_rate": 7e-05,
      "loss": 0.3133,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.39557936787605286,
      "eval_runtime": 7.7166,
      "eval_samples_per_second": 485.966,
      "eval_steps_per_second": 7.646,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 287.69952392578125,
      "learning_rate": 7e-05,
      "loss": 0.2202,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.41149747371673584,
      "eval_runtime": 7.6921,
      "eval_samples_per_second": 487.513,
      "eval_steps_per_second": 7.67,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 108.07672882080078,
      "learning_rate": 7e-05,
      "loss": 0.1524,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.4146367609500885,
      "eval_runtime": 7.6853,
      "eval_samples_per_second": 487.942,
      "eval_steps_per_second": 7.677,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 98.99820709228516,
      "learning_rate": 7e-05,
      "loss": 0.1051,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.42138171195983887,
      "eval_runtime": 7.7381,
      "eval_samples_per_second": 484.614,
      "eval_steps_per_second": 7.625,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 408.8406982421875,
      "learning_rate": 7e-05,
      "loss": 0.0751,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.4142014980316162,
      "eval_runtime": 7.7491,
      "eval_samples_per_second": 483.927,
      "eval_steps_per_second": 7.614,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}