trainer_state.json

{
  "best_metric": 0.7178666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0524/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": 97.34038543701172,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8504,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3376,
      "eval_loss": 3.7191035747528076,
      "eval_runtime": 15.5294,
      "eval_samples_per_second": 241.477,
      "eval_steps_per_second": 3.799,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 450.8140869140625,
      "learning_rate": 2.25e-05,
      "loss": 3.3394,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5130666666666667,
      "eval_loss": 2.9021401405334473,
      "eval_runtime": 15.5423,
      "eval_samples_per_second": 241.277,
      "eval_steps_per_second": 3.796,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 267.87152099609375,
      "learning_rate": 1.5e-05,
      "loss": 2.2218,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6616,
      "eval_loss": 1.7151447534561157,
      "eval_runtime": 15.5805,
      "eval_samples_per_second": 240.685,
      "eval_steps_per_second": 3.787,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 146.92637634277344,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.5055,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7098666666666666,
      "eval_loss": 1.3047242164611816,
      "eval_runtime": 15.5196,
      "eval_samples_per_second": 241.63,
      "eval_steps_per_second": 3.802,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 302.82342529296875,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.278,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7165333333333334,
      "eval_loss": 1.1961243152618408,
      "eval_runtime": 15.654,
      "eval_samples_per_second": 239.556,
      "eval_steps_per_second": 3.769,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 711.12109375,
      "learning_rate": 0.0,
      "loss": 1.2177,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7178666666666667,
      "eval_loss": 1.1834114789962769,
      "eval_runtime": 15.5433,
      "eval_samples_per_second": 241.261,
      "eval_steps_per_second": 3.796,
      "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
}