trainer_state.json

{
  "best_metric": 0.8301333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0275/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": 104.66632080078125,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.4667,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5312,
      "eval_loss": 2.241473436355591,
      "eval_runtime": 13.3075,
      "eval_samples_per_second": 281.797,
      "eval_steps_per_second": 4.434,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 77.36005401611328,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 1.2424,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7704,
      "eval_loss": 0.7876786589622498,
      "eval_runtime": 13.491,
      "eval_samples_per_second": 277.964,
      "eval_steps_per_second": 4.373,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 136.1300811767578,
      "learning_rate": 3.5e-05,
      "loss": 0.7241,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8002666666666667,
      "eval_loss": 0.6449261903762817,
      "eval_runtime": 13.2545,
      "eval_samples_per_second": 282.923,
      "eval_steps_per_second": 4.451,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 122.68071746826172,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.5825,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8189333333333333,
      "eval_loss": 0.5716555714607239,
      "eval_runtime": 13.8632,
      "eval_samples_per_second": 270.501,
      "eval_steps_per_second": 4.256,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 273.7325439453125,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.5243,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8256,
      "eval_loss": 0.548151433467865,
      "eval_runtime": 13.2267,
      "eval_samples_per_second": 283.517,
      "eval_steps_per_second": 4.461,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 80.77344512939453,
      "learning_rate": 0.0,
      "loss": 0.5041,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8301333333333333,
      "eval_loss": 0.5489699244499207,
      "eval_runtime": 13.3569,
      "eval_samples_per_second": 280.755,
      "eval_steps_per_second": 4.417,
      "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
}