trainer_state.json

{
  "best_metric": 0.8949333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0629/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": 80.72282409667969,
      "learning_rate": 7e-05,
      "loss": 3.2014,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6850666666666667,
      "eval_loss": 1.5952421426773071,
      "eval_runtime": 4.9661,
      "eval_samples_per_second": 755.114,
      "eval_steps_per_second": 11.88,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 116.1220932006836,
      "learning_rate": 7e-05,
      "loss": 0.9135,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8277333333333333,
      "eval_loss": 0.5884715914726257,
      "eval_runtime": 4.9766,
      "eval_samples_per_second": 753.533,
      "eval_steps_per_second": 11.856,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 71.61376953125,
      "learning_rate": 7e-05,
      "loss": 0.5169,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.4429035782814026,
      "eval_runtime": 4.9872,
      "eval_samples_per_second": 751.931,
      "eval_steps_per_second": 11.83,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 94.28514099121094,
      "learning_rate": 7e-05,
      "loss": 0.3706,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.3670665919780731,
      "eval_runtime": 5.0404,
      "eval_samples_per_second": 743.992,
      "eval_steps_per_second": 11.705,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 56.02350997924805,
      "learning_rate": 7e-05,
      "loss": 0.2856,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.3995930850505829,
      "eval_runtime": 5.0267,
      "eval_samples_per_second": 746.023,
      "eval_steps_per_second": 11.737,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 94.5501708984375,
      "learning_rate": 7e-05,
      "loss": 0.2221,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.3425503373146057,
      "eval_runtime": 4.9737,
      "eval_samples_per_second": 753.961,
      "eval_steps_per_second": 11.862,
      "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
}