trainer_state.json

{
  "best_metric": 0.8536,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0652/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": 113.26158905029297,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.3606,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5834666666666667,
      "eval_loss": 1.9241058826446533,
      "eval_runtime": 7.7254,
      "eval_samples_per_second": 485.414,
      "eval_steps_per_second": 7.637,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 95.07300567626953,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 1.1707,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7850666666666667,
      "eval_loss": 0.7771873474121094,
      "eval_runtime": 7.4115,
      "eval_samples_per_second": 505.97,
      "eval_steps_per_second": 7.961,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 134.04541015625,
      "learning_rate": 3.5e-05,
      "loss": 0.6723,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8373333333333334,
      "eval_loss": 0.5707262754440308,
      "eval_runtime": 7.8566,
      "eval_samples_per_second": 477.303,
      "eval_steps_per_second": 7.51,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 101.44512176513672,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.5295,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5363022685050964,
      "eval_runtime": 7.4864,
      "eval_samples_per_second": 500.909,
      "eval_steps_per_second": 7.881,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 63.05415725708008,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.469,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5278724431991577,
      "eval_runtime": 7.9038,
      "eval_samples_per_second": 474.455,
      "eval_steps_per_second": 7.465,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 85.95564270019531,
      "learning_rate": 0.0,
      "loss": 0.4464,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8536,
      "eval_loss": 0.4980102479457855,
      "eval_runtime": 7.5349,
      "eval_samples_per_second": 497.687,
      "eval_steps_per_second": 7.83,
      "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
}