trainer_state.json

{
  "best_metric": 0.9181333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0985/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 72.35640716552734,
      "learning_rate": 0.0001,
      "loss": 2.5747,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7928,
      "eval_loss": 0.7884613275527954,
      "eval_runtime": 8.6335,
      "eval_samples_per_second": 434.353,
      "eval_steps_per_second": 6.834,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 130.49696350097656,
      "learning_rate": 0.0001,
      "loss": 0.5705,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.4543565511703491,
      "eval_runtime": 7.9836,
      "eval_samples_per_second": 469.714,
      "eval_steps_per_second": 7.39,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 59.256778717041016,
      "learning_rate": 0.0001,
      "loss": 0.3572,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.36618945002555847,
      "eval_runtime": 7.9261,
      "eval_samples_per_second": 473.122,
      "eval_steps_per_second": 7.444,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 103.17833709716797,
      "learning_rate": 0.0001,
      "loss": 0.2472,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8981333333333333,
      "eval_loss": 0.3323862552642822,
      "eval_runtime": 7.9641,
      "eval_samples_per_second": 470.863,
      "eval_steps_per_second": 7.408,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 278.4313049316406,
      "learning_rate": 0.0001,
      "loss": 0.1788,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9085333333333333,
      "eval_loss": 0.32417967915534973,
      "eval_runtime": 7.927,
      "eval_samples_per_second": 473.065,
      "eval_steps_per_second": 7.443,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 53.160343170166016,
      "learning_rate": 0.0001,
      "loss": 0.1248,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9125333333333333,
      "eval_loss": 0.3162786662578583,
      "eval_runtime": 7.8558,
      "eval_samples_per_second": 477.352,
      "eval_steps_per_second": 7.51,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 73.04103088378906,
      "learning_rate": 0.0001,
      "loss": 0.0952,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.3252105712890625,
      "eval_runtime": 7.8853,
      "eval_samples_per_second": 475.566,
      "eval_steps_per_second": 7.482,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 65.88885498046875,
      "learning_rate": 0.0001,
      "loss": 0.0736,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9181333333333334,
      "eval_loss": 0.332558810710907,
      "eval_runtime": 8.9353,
      "eval_samples_per_second": 419.685,
      "eval_steps_per_second": 6.603,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 6.5411433916416e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}