trainer_state.json

{
  "best_metric": 0.8813333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0996/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": 84.1761703491211,
      "learning_rate": 0.0003,
      "loss": 1.5358,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8250666666666666,
      "eval_loss": 0.5527979731559753,
      "eval_runtime": 8.4847,
      "eval_samples_per_second": 441.973,
      "eval_steps_per_second": 6.954,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.379898071289062,
      "learning_rate": 0.0003,
      "loss": 0.4547,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.3983769714832306,
      "eval_runtime": 8.3548,
      "eval_samples_per_second": 448.844,
      "eval_steps_per_second": 7.062,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 51.53542709350586,
      "learning_rate": 0.0003,
      "loss": 0.2826,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.4311361312866211,
      "eval_runtime": 8.4445,
      "eval_samples_per_second": 444.074,
      "eval_steps_per_second": 6.987,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 38.08618927001953,
      "learning_rate": 0.0003,
      "loss": 0.1842,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.41668805480003357,
      "eval_runtime": 8.2573,
      "eval_samples_per_second": 454.141,
      "eval_steps_per_second": 7.145,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.60391616821289,
      "learning_rate": 0.0003,
      "loss": 0.1312,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.44390246272087097,
      "eval_runtime": 8.3075,
      "eval_samples_per_second": 451.401,
      "eval_steps_per_second": 7.102,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 51.16313552856445,
      "learning_rate": 0.0003,
      "loss": 0.1086,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.4737653434276581,
      "eval_runtime": 8.33,
      "eval_samples_per_second": 450.179,
      "eval_steps_per_second": 7.083,
      "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
}