trainer_state.json

{
  "best_metric": 0.8352,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0621/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": 55.090328216552734,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.6539,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5312,
      "eval_loss": 2.882369041442871,
      "eval_runtime": 13.0323,
      "eval_samples_per_second": 287.746,
      "eval_steps_per_second": 4.527,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 144.7902374267578,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.5632,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7501333333333333,
      "eval_loss": 0.905873715877533,
      "eval_runtime": 12.6297,
      "eval_samples_per_second": 296.92,
      "eval_steps_per_second": 4.672,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 135.72291564941406,
      "learning_rate": 2.5e-05,
      "loss": 0.7878,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8021333333333334,
      "eval_loss": 0.6663439273834229,
      "eval_runtime": 12.6995,
      "eval_samples_per_second": 295.288,
      "eval_steps_per_second": 4.646,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 148.44017028808594,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.6161,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8224,
      "eval_loss": 0.573576033115387,
      "eval_runtime": 12.748,
      "eval_samples_per_second": 294.163,
      "eval_steps_per_second": 4.628,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 98.130615234375,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.5571,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.5402754545211792,
      "eval_runtime": 12.7621,
      "eval_samples_per_second": 293.84,
      "eval_steps_per_second": 4.623,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 288.6017761230469,
      "learning_rate": 0.0,
      "loss": 0.5352,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.5418978929519653,
      "eval_runtime": 12.7469,
      "eval_samples_per_second": 294.189,
      "eval_steps_per_second": 4.629,
      "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
}