trainer_state.json

{
  "best_metric": 0.852,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0268/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": 49.897918701171875,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6336,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5869333333333333,
      "eval_loss": 2.9584121704101562,
      "eval_runtime": 14.2432,
      "eval_samples_per_second": 263.283,
      "eval_steps_per_second": 4.142,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 103.08943939208984,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6716,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7602666666666666,
      "eval_loss": 0.9408249855041504,
      "eval_runtime": 14.3819,
      "eval_samples_per_second": 260.744,
      "eval_steps_per_second": 4.102,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 91.54322052001953,
      "learning_rate": 2.5e-05,
      "loss": 0.7255,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8285333333333333,
      "eval_loss": 0.6104303598403931,
      "eval_runtime": 14.3283,
      "eval_samples_per_second": 261.721,
      "eval_steps_per_second": 4.118,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 130.05728149414062,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5349,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5356705784797668,
      "eval_runtime": 14.3343,
      "eval_samples_per_second": 261.61,
      "eval_steps_per_second": 4.116,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 86.14727020263672,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4363,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5075793862342834,
      "eval_runtime": 13.6819,
      "eval_samples_per_second": 274.085,
      "eval_steps_per_second": 4.312,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 84.61822509765625,
      "learning_rate": 0.0,
      "loss": 0.398,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.852,
      "eval_loss": 0.49229907989501953,
      "eval_runtime": 14.2251,
      "eval_samples_per_second": 263.619,
      "eval_steps_per_second": 4.148,
      "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
}