trainer_state.json

{
  "best_metric": 0.844,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0869/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": 212.94451904296875,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.6071,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5461333333333334,
      "eval_loss": 2.859215021133423,
      "eval_runtime": 7.7006,
      "eval_samples_per_second": 486.974,
      "eval_steps_per_second": 7.662,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 101.79987335205078,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.5809,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7786666666666666,
      "eval_loss": 0.8422494530677795,
      "eval_runtime": 8.1324,
      "eval_samples_per_second": 461.117,
      "eval_steps_per_second": 7.255,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 131.32266235351562,
      "learning_rate": 2.5e-05,
      "loss": 0.7283,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8117333333333333,
      "eval_loss": 0.6309190988540649,
      "eval_runtime": 7.6961,
      "eval_samples_per_second": 487.262,
      "eval_steps_per_second": 7.666,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 84.31150817871094,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.5569,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8381333333333333,
      "eval_loss": 0.5375580191612244,
      "eval_runtime": 8.19,
      "eval_samples_per_second": 457.877,
      "eval_steps_per_second": 7.204,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 124.47846984863281,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.4867,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8354666666666667,
      "eval_loss": 0.52681964635849,
      "eval_runtime": 7.7444,
      "eval_samples_per_second": 484.222,
      "eval_steps_per_second": 7.618,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 153.6956787109375,
      "learning_rate": 0.0,
      "loss": 0.462,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.844,
      "eval_loss": 0.5205013751983643,
      "eval_runtime": 7.6747,
      "eval_samples_per_second": 488.62,
      "eval_steps_per_second": 7.688,
      "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
}