trainer_state.json

{
  "best_metric": 0.7125333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0239/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 113.0516586303711,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 3.8372,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4245333333333333,
      "eval_loss": 3.716008186340332,
      "eval_runtime": 12.2716,
      "eval_samples_per_second": 305.583,
      "eval_steps_per_second": 4.808,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 80.44564056396484,
      "learning_rate": 1.963525491562421e-05,
      "loss": 3.2017,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5722666666666667,
      "eval_loss": 2.733705997467041,
      "eval_runtime": 12.4427,
      "eval_samples_per_second": 301.383,
      "eval_steps_per_second": 4.742,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 221.40504455566406,
      "learning_rate": 1.036474508437579e-05,
      "loss": 2.1285,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6642666666666667,
      "eval_loss": 1.7387620210647583,
      "eval_runtime": 12.2607,
      "eval_samples_per_second": 305.854,
      "eval_steps_per_second": 4.812,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 160.4095458984375,
      "learning_rate": 2.86474508437579e-06,
      "loss": 1.5269,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7098666666666666,
      "eval_loss": 1.4424079656600952,
      "eval_runtime": 12.4335,
      "eval_samples_per_second": 301.604,
      "eval_steps_per_second": 4.745,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 121.55972290039062,
      "learning_rate": 0.0,
      "loss": 1.3906,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7125333333333334,
      "eval_loss": 1.373414158821106,
      "eval_runtime": 12.8457,
      "eval_samples_per_second": 291.926,
      "eval_steps_per_second": 4.593,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}