trainer_state.json

{
  "best_metric": 0.952,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0504/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": 0.11309988796710968,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5936,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9312,
      "eval_loss": 0.23246382176876068,
      "eval_runtime": 6.3209,
      "eval_samples_per_second": 593.268,
      "eval_steps_per_second": 9.334,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13655443489551544,
      "learning_rate": 6e-05,
      "loss": 0.1068,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9357333333333333,
      "eval_loss": 0.20686708390712738,
      "eval_runtime": 5.7868,
      "eval_samples_per_second": 648.024,
      "eval_steps_per_second": 10.196,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.21627917885780334,
      "learning_rate": 4.5e-05,
      "loss": 0.0452,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.2197275012731552,
      "eval_runtime": 5.8585,
      "eval_samples_per_second": 640.101,
      "eval_steps_per_second": 10.071,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2191307693719864,
      "learning_rate": 3e-05,
      "loss": 0.0154,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9485333333333333,
      "eval_loss": 0.18471750617027283,
      "eval_runtime": 5.7617,
      "eval_samples_per_second": 650.854,
      "eval_steps_per_second": 10.24,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.039519790560007095,
      "learning_rate": 1.5e-05,
      "loss": 0.0059,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9512,
      "eval_loss": 0.18195348978042603,
      "eval_runtime": 6.3095,
      "eval_samples_per_second": 594.337,
      "eval_steps_per_second": 9.351,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04656016454100609,
      "learning_rate": 0.0,
      "loss": 0.0025,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.18496564030647278,
      "eval_runtime": 5.8552,
      "eval_samples_per_second": 640.461,
      "eval_steps_per_second": 10.077,
      "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}