trainer_state.json

{
  "best_metric": 0.888,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0687/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": 25.381704330444336,
      "learning_rate": 0.0005,
      "loss": 1.3301,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8357333333333333,
      "eval_loss": 0.5491461157798767,
      "eval_runtime": 7.6258,
      "eval_samples_per_second": 491.753,
      "eval_steps_per_second": 7.737,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 25.20472526550293,
      "learning_rate": 0.0005,
      "loss": 0.4703,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.4484756588935852,
      "eval_runtime": 7.697,
      "eval_samples_per_second": 487.205,
      "eval_steps_per_second": 7.665,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 55.940006256103516,
      "learning_rate": 0.0005,
      "loss": 0.3197,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8792,
      "eval_loss": 0.39895105361938477,
      "eval_runtime": 7.6287,
      "eval_samples_per_second": 491.567,
      "eval_steps_per_second": 7.734,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 30.495161056518555,
      "learning_rate": 0.0005,
      "loss": 0.2358,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8752,
      "eval_loss": 0.4571157693862915,
      "eval_runtime": 7.7296,
      "eval_samples_per_second": 485.15,
      "eval_steps_per_second": 7.633,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.395448684692383,
      "learning_rate": 0.0005,
      "loss": 0.1838,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.40097036957740784,
      "eval_runtime": 7.6195,
      "eval_samples_per_second": 492.157,
      "eval_steps_per_second": 7.743,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 36.04233932495117,
      "learning_rate": 0.0005,
      "loss": 0.148,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.4335234463214874,
      "eval_runtime": 7.6722,
      "eval_samples_per_second": 488.776,
      "eval_steps_per_second": 7.69,
      "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
}