trainer_state.json

{
  "best_metric": 0.8874666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0865/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": 179.89146423339844,
      "learning_rate": 5.833333333333333e-05,
      "loss": 3.3555,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.668,
      "eval_loss": 2.0001118183135986,
      "eval_runtime": 7.4903,
      "eval_samples_per_second": 500.648,
      "eval_steps_per_second": 7.877,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 144.23544311523438,
      "learning_rate": 4.666666666666666e-05,
      "loss": 1.0089,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.6041626334190369,
      "eval_runtime": 7.6275,
      "eval_samples_per_second": 491.639,
      "eval_steps_per_second": 7.735,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 110.59944152832031,
      "learning_rate": 3.5e-05,
      "loss": 0.4845,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.46247410774230957,
      "eval_runtime": 7.6218,
      "eval_samples_per_second": 492.008,
      "eval_steps_per_second": 7.741,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 110.31440734863281,
      "learning_rate": 2.333333333333333e-05,
      "loss": 0.3391,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8762666666666666,
      "eval_loss": 0.4057832658290863,
      "eval_runtime": 7.5868,
      "eval_samples_per_second": 494.28,
      "eval_steps_per_second": 7.777,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 107.7212905883789,
      "learning_rate": 1.1666666666666665e-05,
      "loss": 0.2704,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.38226237893104553,
      "eval_runtime": 7.5823,
      "eval_samples_per_second": 494.572,
      "eval_steps_per_second": 7.781,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 125.5625,
      "learning_rate": 0.0,
      "loss": 0.2332,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.3722061812877655,
      "eval_runtime": 7.792,
      "eval_samples_per_second": 481.262,
      "eval_steps_per_second": 7.572,
      "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
}