trainer_state.json

{
  "best_metric": 0.8882666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0828/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": 66.58690643310547,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.5023,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7968,
      "eval_loss": 0.7390795350074768,
      "eval_runtime": 7.4512,
      "eval_samples_per_second": 503.271,
      "eval_steps_per_second": 7.918,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 73.65161895751953,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5705,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4508278965950012,
      "eval_runtime": 7.0599,
      "eval_samples_per_second": 531.168,
      "eval_steps_per_second": 8.357,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 289.3782958984375,
      "learning_rate": 5e-05,
      "loss": 0.3405,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.38150522112846375,
      "eval_runtime": 7.0073,
      "eval_samples_per_second": 535.154,
      "eval_steps_per_second": 8.42,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 50.922607421875,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2211,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.37862053513526917,
      "eval_runtime": 6.9971,
      "eval_samples_per_second": 535.935,
      "eval_steps_per_second": 8.432,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 139.44342041015625,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1716,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8882666666666666,
      "eval_loss": 0.36978355050086975,
      "eval_runtime": 7.025,
      "eval_samples_per_second": 533.81,
      "eval_steps_per_second": 8.399,
      "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
}