trainer_state.json

{
  "best_metric": 0.8730666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0349/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": 165.3189697265625,
      "learning_rate": 0.0001,
      "loss": 2.8857,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7053333333333334,
      "eval_loss": 1.12528395652771,
      "eval_runtime": 9.396,
      "eval_samples_per_second": 399.105,
      "eval_steps_per_second": 6.279,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 39.72459030151367,
      "learning_rate": 0.0001,
      "loss": 0.8061,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8144,
      "eval_loss": 0.5850844979286194,
      "eval_runtime": 9.3031,
      "eval_samples_per_second": 403.09,
      "eval_steps_per_second": 6.342,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 33.914939880371094,
      "learning_rate": 0.0001,
      "loss": 0.5242,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8429333333333333,
      "eval_loss": 0.5006402730941772,
      "eval_runtime": 9.2169,
      "eval_samples_per_second": 406.862,
      "eval_steps_per_second": 6.401,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 165.58908081054688,
      "learning_rate": 0.0001,
      "loss": 0.4105,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.4468732476234436,
      "eval_runtime": 9.3189,
      "eval_samples_per_second": 402.409,
      "eval_steps_per_second": 6.331,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 32.28816604614258,
      "learning_rate": 0.0001,
      "loss": 0.3145,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.44929009675979614,
      "eval_runtime": 9.2893,
      "eval_samples_per_second": 403.692,
      "eval_steps_per_second": 6.351,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 54.367923736572266,
      "learning_rate": 0.0001,
      "loss": 0.2591,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4079747796058655,
      "eval_runtime": 9.4734,
      "eval_samples_per_second": 395.846,
      "eval_steps_per_second": 6.228,
      "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
}