trainer_state.json

{
  "best_metric": 0.8816,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0699/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": 55.502960205078125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.7043,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7602666666666666,
      "eval_loss": 0.86543869972229,
      "eval_runtime": 14.1039,
      "eval_samples_per_second": 265.885,
      "eval_steps_per_second": 4.183,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 110.67059326171875,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6477,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5082654356956482,
      "eval_runtime": 14.326,
      "eval_samples_per_second": 261.761,
      "eval_steps_per_second": 4.118,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 120.12176513671875,
      "learning_rate": 5e-05,
      "loss": 0.3964,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.4217889904975891,
      "eval_runtime": 14.1955,
      "eval_samples_per_second": 264.169,
      "eval_steps_per_second": 4.156,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 138.71478271484375,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.287,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8717333333333334,
      "eval_loss": 0.40434959530830383,
      "eval_runtime": 14.3526,
      "eval_samples_per_second": 261.276,
      "eval_steps_per_second": 4.111,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 145.56008911132812,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2218,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.3823191225528717,
      "eval_runtime": 14.1669,
      "eval_samples_per_second": 264.702,
      "eval_steps_per_second": 4.165,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 64.53092956542969,
      "learning_rate": 0.0,
      "loss": 0.1956,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8816,
      "eval_loss": 0.3676557242870331,
      "eval_runtime": 14.1099,
      "eval_samples_per_second": 265.771,
      "eval_steps_per_second": 4.181,
      "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
}