trainer_state.json

{
  "best_metric": 0.8952,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0871/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": 48.83985137939453,
      "learning_rate": 8.657457896300791e-05,
      "loss": 3.0002,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7021333333333334,
      "eval_loss": 1.1938588619232178,
      "eval_runtime": 8.6456,
      "eval_samples_per_second": 433.744,
      "eval_steps_per_second": 6.824,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 91.97008514404297,
      "learning_rate": 7.681980515339464e-05,
      "loss": 0.8485,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8325333333333333,
      "eval_loss": 0.5834760665893555,
      "eval_runtime": 8.5359,
      "eval_samples_per_second": 439.321,
      "eval_steps_per_second": 6.912,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 59.9212646484375,
      "learning_rate": 6.222075445642905e-05,
      "loss": 0.5416,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8653333333333333,
      "eval_loss": 0.46234649419784546,
      "eval_runtime": 8.5654,
      "eval_samples_per_second": 437.807,
      "eval_steps_per_second": 6.888,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 59.071533203125,
      "learning_rate": 4.5e-05,
      "loss": 0.4049,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.3928946256637573,
      "eval_runtime": 8.5769,
      "eval_samples_per_second": 437.22,
      "eval_steps_per_second": 6.879,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 62.109683990478516,
      "learning_rate": 2.7779245543570963e-05,
      "loss": 0.3411,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.3619924485683441,
      "eval_runtime": 8.589,
      "eval_samples_per_second": 436.603,
      "eval_steps_per_second": 6.869,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}