trainer_state.json

{
  "best_metric": 0.6936,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0719/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": 144.1595458984375,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.8588,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2906666666666667,
      "eval_loss": 3.754946708679199,
      "eval_runtime": 8.6389,
      "eval_samples_per_second": 434.083,
      "eval_steps_per_second": 6.83,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 168.9088897705078,
      "learning_rate": 2.25e-05,
      "loss": 3.3946,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5002666666666666,
      "eval_loss": 2.973689556121826,
      "eval_runtime": 7.8956,
      "eval_samples_per_second": 474.951,
      "eval_steps_per_second": 7.473,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 376.8825988769531,
      "learning_rate": 1.5e-05,
      "loss": 2.3627,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6093333333333333,
      "eval_loss": 1.881471872329712,
      "eval_runtime": 7.3919,
      "eval_samples_per_second": 507.312,
      "eval_steps_per_second": 7.982,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 115.972412109375,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.6136,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6589333333333334,
      "eval_loss": 1.458915114402771,
      "eval_runtime": 7.5716,
      "eval_samples_per_second": 495.272,
      "eval_steps_per_second": 7.792,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 202.09486389160156,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.3486,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6821333333333334,
      "eval_loss": 1.3778820037841797,
      "eval_runtime": 7.4147,
      "eval_samples_per_second": 505.753,
      "eval_steps_per_second": 7.957,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 91.00862884521484,
      "learning_rate": 0.0,
      "loss": 1.291,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6936,
      "eval_loss": 1.3025822639465332,
      "eval_runtime": 7.3603,
      "eval_samples_per_second": 509.487,
      "eval_steps_per_second": 8.016,
      "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
}