trainer_state.json

{
  "best_metric": 0.9101333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0583/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": 34.572723388671875,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.3904,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8266666666666667,
      "eval_loss": 0.5827487111091614,
      "eval_runtime": 9.3697,
      "eval_samples_per_second": 400.226,
      "eval_steps_per_second": 6.297,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 39.57350158691406,
      "learning_rate": 0.000375,
      "loss": 0.4477,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.4324457049369812,
      "eval_runtime": 8.834,
      "eval_samples_per_second": 424.498,
      "eval_steps_per_second": 6.679,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 17.62663459777832,
      "learning_rate": 0.00025,
      "loss": 0.2439,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.3851519823074341,
      "eval_runtime": 8.3497,
      "eval_samples_per_second": 449.116,
      "eval_steps_per_second": 7.066,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 51.581905364990234,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1195,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.35829785466194153,
      "eval_runtime": 8.5658,
      "eval_samples_per_second": 437.787,
      "eval_steps_per_second": 6.888,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.443008422851562,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.065,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3692903518676758,
      "eval_runtime": 8.8799,
      "eval_samples_per_second": 422.3,
      "eval_steps_per_second": 6.644,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.355199813842773,
      "learning_rate": 0.0,
      "loss": 0.036,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3682650923728943,
      "eval_runtime": 8.3827,
      "eval_samples_per_second": 447.349,
      "eval_steps_per_second": 7.038,
      "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
}