trainer_state.json

{
  "best_metric": 0.7288,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0361/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": 82.5856704711914,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8468,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33973333333333333,
      "eval_loss": 3.759275436401367,
      "eval_runtime": 8.067,
      "eval_samples_per_second": 464.858,
      "eval_steps_per_second": 7.314,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 132.63768005371094,
      "learning_rate": 2.25e-05,
      "loss": 3.283,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5269333333333334,
      "eval_loss": 2.723909378051758,
      "eval_runtime": 8.0544,
      "eval_samples_per_second": 465.585,
      "eval_steps_per_second": 7.325,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 243.7537841796875,
      "learning_rate": 1.5e-05,
      "loss": 2.1345,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.648,
      "eval_loss": 1.7104169130325317,
      "eval_runtime": 8.0207,
      "eval_samples_per_second": 467.541,
      "eval_steps_per_second": 7.356,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 453.5697326660156,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.5032,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7184,
      "eval_loss": 1.2958998680114746,
      "eval_runtime": 8.0431,
      "eval_samples_per_second": 466.237,
      "eval_steps_per_second": 7.335,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 242.99021911621094,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.2844,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7261333333333333,
      "eval_loss": 1.1939525604248047,
      "eval_runtime": 8.0137,
      "eval_samples_per_second": 467.951,
      "eval_steps_per_second": 7.362,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 208.60256958007812,
      "learning_rate": 0.0,
      "loss": 1.2209,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7288,
      "eval_loss": 1.1882296800613403,
      "eval_runtime": 8.0635,
      "eval_samples_per_second": 465.06,
      "eval_steps_per_second": 7.317,
      "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
}