trainer_state.json

{
  "best_metric": 0.8936,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0409/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": 52.54358673095703,
      "learning_rate": 7e-05,
      "loss": 3.2152,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6717333333333333,
      "eval_loss": 1.435573935508728,
      "eval_runtime": 9.0936,
      "eval_samples_per_second": 412.378,
      "eval_steps_per_second": 6.488,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 199.96563720703125,
      "learning_rate": 7e-05,
      "loss": 0.8291,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8485333333333334,
      "eval_loss": 0.5243803262710571,
      "eval_runtime": 7.0059,
      "eval_samples_per_second": 535.267,
      "eval_steps_per_second": 8.422,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 139.43077087402344,
      "learning_rate": 7e-05,
      "loss": 0.4312,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8712,
      "eval_loss": 0.42643287777900696,
      "eval_runtime": 7.1053,
      "eval_samples_per_second": 527.774,
      "eval_steps_per_second": 8.304,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 88.94485473632812,
      "learning_rate": 7e-05,
      "loss": 0.2866,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.3771096169948578,
      "eval_runtime": 7.3918,
      "eval_samples_per_second": 507.316,
      "eval_steps_per_second": 7.982,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 53.55785369873047,
      "learning_rate": 7e-05,
      "loss": 0.1975,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.38137248158454895,
      "eval_runtime": 7.0283,
      "eval_samples_per_second": 533.559,
      "eval_steps_per_second": 8.395,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 92.73090362548828,
      "learning_rate": 7e-05,
      "loss": 0.134,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.36458346247673035,
      "eval_runtime": 7.4663,
      "eval_samples_per_second": 502.259,
      "eval_steps_per_second": 7.902,
      "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
}