trainer_state.json

{
  "best_metric": 0.8898666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0780/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": 434.86907958984375,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.756,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7661333333333333,
      "eval_loss": 0.8884685635566711,
      "eval_runtime": 14.634,
      "eval_samples_per_second": 256.253,
      "eval_steps_per_second": 4.032,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 123.86804962158203,
      "learning_rate": 6.75e-05,
      "loss": 0.6825,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8456,
      "eval_loss": 0.5033240914344788,
      "eval_runtime": 14.5466,
      "eval_samples_per_second": 257.793,
      "eval_steps_per_second": 4.056,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 143.90487670898438,
      "learning_rate": 4.5e-05,
      "loss": 0.431,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.3888372480869293,
      "eval_runtime": 14.56,
      "eval_samples_per_second": 257.555,
      "eval_steps_per_second": 4.052,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 102.1160659790039,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.3146,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.3711029291152954,
      "eval_runtime": 14.6264,
      "eval_samples_per_second": 256.386,
      "eval_steps_per_second": 4.034,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 70.68318939208984,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.2596,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.3534524440765381,
      "eval_runtime": 14.4863,
      "eval_samples_per_second": 258.866,
      "eval_steps_per_second": 4.073,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 324.7383117675781,
      "learning_rate": 0.0,
      "loss": 0.2464,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.3532673716545105,
      "eval_runtime": 14.4702,
      "eval_samples_per_second": 259.154,
      "eval_steps_per_second": 4.077,
      "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}