trainer_state.json

{
  "best_metric": 0.9138666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0907/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": 157.40846252441406,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.5633,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8256,
      "eval_loss": 0.6815613508224487,
      "eval_runtime": 7.0497,
      "eval_samples_per_second": 531.938,
      "eval_steps_per_second": 8.369,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 281.7699890136719,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.536,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.3922813832759857,
      "eval_runtime": 7.0105,
      "eval_samples_per_second": 534.914,
      "eval_steps_per_second": 8.416,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 95.80467987060547,
      "learning_rate": 5e-05,
      "loss": 0.3204,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.3224680423736572,
      "eval_runtime": 7.0902,
      "eval_samples_per_second": 528.897,
      "eval_steps_per_second": 8.321,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 86.4976806640625,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2319,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9109333333333334,
      "eval_loss": 0.31058475375175476,
      "eval_runtime": 8.2883,
      "eval_samples_per_second": 452.446,
      "eval_steps_per_second": 7.118,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 96.94808959960938,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1895,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9138666666666667,
      "eval_loss": 0.30408763885498047,
      "eval_runtime": 7.0615,
      "eval_samples_per_second": 531.046,
      "eval_steps_per_second": 8.355,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}