trainer_state.json

{
  "best_metric": 0.8994666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0048/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": 25.952600479125977,
      "learning_rate": 0.0004,
      "loss": 1.3114,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8224,
      "eval_loss": 0.5435203313827515,
      "eval_runtime": 15.8189,
      "eval_samples_per_second": 237.058,
      "eval_steps_per_second": 3.73,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.827674865722656,
      "learning_rate": 0.0003,
      "loss": 0.4082,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.43150871992111206,
      "eval_runtime": 16.15,
      "eval_samples_per_second": 232.199,
      "eval_steps_per_second": 3.653,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.108694076538086,
      "learning_rate": 0.0002,
      "loss": 0.2335,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.37177544832229614,
      "eval_runtime": 15.933,
      "eval_samples_per_second": 235.36,
      "eval_steps_per_second": 3.703,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.898340225219727,
      "learning_rate": 0.0001,
      "loss": 0.1365,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.3740991950035095,
      "eval_runtime": 15.8037,
      "eval_samples_per_second": 237.286,
      "eval_steps_per_second": 3.733,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 36.12678909301758,
      "learning_rate": 0.0,
      "loss": 0.0811,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8994666666666666,
      "eval_loss": 0.3528398871421814,
      "eval_runtime": 13.8768,
      "eval_samples_per_second": 270.236,
      "eval_steps_per_second": 4.252,
      "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
}