trainer_state.json

{
  "best_metric": 0.8272,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0007/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": 100.51819610595703,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.7233,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4829333333333333,
      "eval_loss": 3.170290470123291,
      "eval_runtime": 14.4592,
      "eval_samples_per_second": 259.351,
      "eval_steps_per_second": 4.08,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 195.52691650390625,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.9555,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7136,
      "eval_loss": 1.1700083017349243,
      "eval_runtime": 14.6695,
      "eval_samples_per_second": 255.632,
      "eval_steps_per_second": 4.022,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 189.39056396484375,
      "learning_rate": 2.5e-05,
      "loss": 0.9326,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7898666666666667,
      "eval_loss": 0.7559321522712708,
      "eval_runtime": 15.0796,
      "eval_samples_per_second": 248.681,
      "eval_steps_per_second": 3.913,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 481.6527404785156,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.7037,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8173333333333334,
      "eval_loss": 0.6441612243652344,
      "eval_runtime": 14.6579,
      "eval_samples_per_second": 255.835,
      "eval_steps_per_second": 4.025,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 92.86109161376953,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.6221,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8218666666666666,
      "eval_loss": 0.6306751370429993,
      "eval_runtime": 14.6596,
      "eval_samples_per_second": 255.805,
      "eval_steps_per_second": 4.025,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 106.04248809814453,
      "learning_rate": 0.0,
      "loss": 0.6027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8272,
      "eval_loss": 0.6131772994995117,
      "eval_runtime": 14.6829,
      "eval_samples_per_second": 255.399,
      "eval_steps_per_second": 4.018,
      "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
}