trainer_state.json

{
  "best_metric": 0.8602666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0422/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": 95.3379898071289,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9097,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6818666666666666,
      "eval_loss": 1.2351219654083252,
      "eval_runtime": 9.1285,
      "eval_samples_per_second": 410.8,
      "eval_steps_per_second": 6.463,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 96.82241821289062,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8739,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8056,
      "eval_loss": 0.6473934054374695,
      "eval_runtime": 8.6325,
      "eval_samples_per_second": 434.406,
      "eval_steps_per_second": 6.835,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 109.10810852050781,
      "learning_rate": 5e-05,
      "loss": 0.5522,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5135024785995483,
      "eval_runtime": 8.6641,
      "eval_samples_per_second": 432.82,
      "eval_steps_per_second": 6.81,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 117.46884155273438,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4331,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8565333333333334,
      "eval_loss": 0.46666982769966125,
      "eval_runtime": 8.7528,
      "eval_samples_per_second": 428.433,
      "eval_steps_per_second": 6.741,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 82.01973724365234,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3759,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8570666666666666,
      "eval_loss": 0.4635440707206726,
      "eval_runtime": 8.5783,
      "eval_samples_per_second": 437.149,
      "eval_steps_per_second": 6.878,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 91.0268325805664,
      "learning_rate": 0.0,
      "loss": 0.3588,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8602666666666666,
      "eval_loss": 0.4553454518318176,
      "eval_runtime": 8.8857,
      "eval_samples_per_second": 422.027,
      "eval_steps_per_second": 6.64,
      "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
}