trainer_state.json

{
  "best_metric": 0.8672,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0306/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": 66.89022827148438,
      "learning_rate": 0.0001,
      "loss": 2.9628,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6733333333333333,
      "eval_loss": 1.2682733535766602,
      "eval_runtime": 8.3456,
      "eval_samples_per_second": 449.336,
      "eval_steps_per_second": 7.07,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 60.283302307128906,
      "learning_rate": 0.0001,
      "loss": 0.8619,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8077333333333333,
      "eval_loss": 0.6476805806159973,
      "eval_runtime": 8.343,
      "eval_samples_per_second": 449.478,
      "eval_steps_per_second": 7.072,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 242.97259521484375,
      "learning_rate": 0.0001,
      "loss": 0.5348,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8413333333333334,
      "eval_loss": 0.5337095260620117,
      "eval_runtime": 8.4422,
      "eval_samples_per_second": 444.196,
      "eval_steps_per_second": 6.989,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 262.89190673828125,
      "learning_rate": 0.0001,
      "loss": 0.3935,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.4830036461353302,
      "eval_runtime": 8.2627,
      "eval_samples_per_second": 453.846,
      "eval_steps_per_second": 7.141,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 87.95759582519531,
      "learning_rate": 0.0001,
      "loss": 0.2923,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.4706448018550873,
      "eval_runtime": 8.1865,
      "eval_samples_per_second": 458.07,
      "eval_steps_per_second": 7.207,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 62.42591857910156,
      "learning_rate": 0.0001,
      "loss": 0.2283,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.44882121682167053,
      "eval_runtime": 8.2435,
      "eval_samples_per_second": 454.901,
      "eval_steps_per_second": 7.157,
      "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
}