trainer_state.json

{
  "best_metric": 0.9066666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0499/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": 86.16912078857422,
      "learning_rate": 0.0002799038105676658,
      "loss": 1.5529,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8418666666666667,
      "eval_loss": 0.5376629829406738,
      "eval_runtime": 8.4264,
      "eval_samples_per_second": 445.028,
      "eval_steps_per_second": 7.002,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 37.3266487121582,
      "learning_rate": 0.000225,
      "loss": 0.4516,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8752,
      "eval_loss": 0.4052290916442871,
      "eval_runtime": 8.1781,
      "eval_samples_per_second": 458.544,
      "eval_steps_per_second": 7.214,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 39.21990966796875,
      "learning_rate": 0.00015,
      "loss": 0.2746,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.37267929315567017,
      "eval_runtime": 8.3328,
      "eval_samples_per_second": 450.029,
      "eval_steps_per_second": 7.08,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 55.97043228149414,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.1788,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.904,
      "eval_loss": 0.3429725170135498,
      "eval_runtime": 8.6624,
      "eval_samples_per_second": 432.903,
      "eval_steps_per_second": 6.811,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 39.60421371459961,
      "learning_rate": 2.009618943233419e-05,
      "loss": 0.1224,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.3305855989456177,
      "eval_runtime": 8.2847,
      "eval_samples_per_second": 452.643,
      "eval_steps_per_second": 7.122,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 40.295753479003906,
      "learning_rate": 0.0,
      "loss": 0.1005,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.3300686180591583,
      "eval_runtime": 8.3256,
      "eval_samples_per_second": 450.419,
      "eval_steps_per_second": 7.087,
      "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
}