trainer_state.json

{
  "best_metric": 0.9002666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0322/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": 26.265644073486328,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.325,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.832,
      "eval_loss": 0.5488515496253967,
      "eval_runtime": 8.3743,
      "eval_samples_per_second": 447.801,
      "eval_steps_per_second": 7.045,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.42756462097168,
      "learning_rate": 0.000375,
      "loss": 0.4194,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.4924643337726593,
      "eval_runtime": 8.2769,
      "eval_samples_per_second": 453.069,
      "eval_steps_per_second": 7.128,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.813091278076172,
      "learning_rate": 0.00025,
      "loss": 0.229,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.42012926936149597,
      "eval_runtime": 8.1211,
      "eval_samples_per_second": 461.76,
      "eval_steps_per_second": 7.265,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 31.103120803833008,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1212,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.38803425431251526,
      "eval_runtime": 8.2732,
      "eval_samples_per_second": 453.273,
      "eval_steps_per_second": 7.131,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 19.8493709564209,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0621,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.3855874240398407,
      "eval_runtime": 8.2697,
      "eval_samples_per_second": 453.463,
      "eval_steps_per_second": 7.134,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 44.3847541809082,
      "learning_rate": 0.0,
      "loss": 0.0478,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9002666666666667,
      "eval_loss": 0.3898452818393707,
      "eval_runtime": 8.3056,
      "eval_samples_per_second": 451.505,
      "eval_steps_per_second": 7.104,
      "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
}