trainer_state.json

{
  "best_metric": 0.8890666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0200/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": 147.3016357421875,
      "learning_rate": 9e-05,
      "loss": 2.8345,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7445333333333334,
      "eval_loss": 0.9858595728874207,
      "eval_runtime": 7.5803,
      "eval_samples_per_second": 494.706,
      "eval_steps_per_second": 7.783,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 286.6444091796875,
      "learning_rate": 9e-05,
      "loss": 0.6983,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8442666666666667,
      "eval_loss": 0.5034191608428955,
      "eval_runtime": 7.3753,
      "eval_samples_per_second": 508.456,
      "eval_steps_per_second": 8.0,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 61.70878982543945,
      "learning_rate": 9e-05,
      "loss": 0.375,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8762666666666666,
      "eval_loss": 0.395560622215271,
      "eval_runtime": 8.1351,
      "eval_samples_per_second": 460.965,
      "eval_steps_per_second": 7.253,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 89.92761993408203,
      "learning_rate": 9e-05,
      "loss": 0.2344,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8829333333333333,
      "eval_loss": 0.3862365186214447,
      "eval_runtime": 8.2209,
      "eval_samples_per_second": 456.157,
      "eval_steps_per_second": 7.177,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 265.44049072265625,
      "learning_rate": 9e-05,
      "loss": 0.1554,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8882666666666666,
      "eval_loss": 0.38038191199302673,
      "eval_runtime": 7.3055,
      "eval_samples_per_second": 513.315,
      "eval_steps_per_second": 8.076,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 207.2471466064453,
      "learning_rate": 9e-05,
      "loss": 0.1042,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8890666666666667,
      "eval_loss": 0.39145925641059875,
      "eval_runtime": 7.2796,
      "eval_samples_per_second": 515.141,
      "eval_steps_per_second": 8.105,
      "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
}