trainer_state.json

{
  "best_metric": 0.8789333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0241/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": 42.29973602294922,
      "learning_rate": 0.0003,
      "loss": 1.5911,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8349333333333333,
      "eval_loss": 0.5521154999732971,
      "eval_runtime": 7.9455,
      "eval_samples_per_second": 471.966,
      "eval_steps_per_second": 7.426,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 40.49729919433594,
      "learning_rate": 0.0003,
      "loss": 0.4902,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.45499366521835327,
      "eval_runtime": 8.4848,
      "eval_samples_per_second": 441.965,
      "eval_steps_per_second": 6.954,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 34.91142272949219,
      "learning_rate": 0.0003,
      "loss": 0.3344,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8712,
      "eval_loss": 0.4243099093437195,
      "eval_runtime": 8.2001,
      "eval_samples_per_second": 457.31,
      "eval_steps_per_second": 7.195,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 33.24995040893555,
      "learning_rate": 0.0003,
      "loss": 0.2538,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.43361371755599976,
      "eval_runtime": 8.2733,
      "eval_samples_per_second": 453.265,
      "eval_steps_per_second": 7.131,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.889402389526367,
      "learning_rate": 0.0003,
      "loss": 0.1968,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.4397202432155609,
      "eval_runtime": 8.1797,
      "eval_samples_per_second": 458.453,
      "eval_steps_per_second": 7.213,
      "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
}