trainer_state.json

{
  "best_metric": 0.7178666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0286/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": 278.3050842285156,
      "learning_rate": 2.5e-05,
      "loss": 3.8614,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2712,
      "eval_loss": 3.773193836212158,
      "eval_runtime": 7.9192,
      "eval_samples_per_second": 473.53,
      "eval_steps_per_second": 7.45,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 243.6114501953125,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 3.4534,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5045333333333333,
      "eval_loss": 3.04854679107666,
      "eval_runtime": 7.5809,
      "eval_samples_per_second": 494.663,
      "eval_steps_per_second": 7.783,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 290.26727294921875,
      "learning_rate": 1.5e-05,
      "loss": 2.4584,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6181333333333333,
      "eval_loss": 1.921509027481079,
      "eval_runtime": 7.7153,
      "eval_samples_per_second": 486.05,
      "eval_steps_per_second": 7.647,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 140.73501586914062,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.6615,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6781333333333334,
      "eval_loss": 1.3707404136657715,
      "eval_runtime": 7.7111,
      "eval_samples_per_second": 486.315,
      "eval_steps_per_second": 7.651,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 87.38561248779297,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 1.3293,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7029333333333333,
      "eval_loss": 1.198474645614624,
      "eval_runtime": 7.7094,
      "eval_samples_per_second": 486.421,
      "eval_steps_per_second": 7.653,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 276.86407470703125,
      "learning_rate": 0.0,
      "loss": 1.2263,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7178666666666667,
      "eval_loss": 1.1450833082199097,
      "eval_runtime": 7.6637,
      "eval_samples_per_second": 489.318,
      "eval_steps_per_second": 7.699,
      "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
}