trainer_state.json

{
  "best_metric": 0.8933333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0380/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": 313.1441955566406,
      "learning_rate": 7e-05,
      "loss": 3.3752,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6037333333333333,
      "eval_loss": 1.831628441810608,
      "eval_runtime": 8.1527,
      "eval_samples_per_second": 459.973,
      "eval_steps_per_second": 7.237,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 150.1922607421875,
      "learning_rate": 7e-05,
      "loss": 1.0576,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8112,
      "eval_loss": 0.6637126207351685,
      "eval_runtime": 8.1162,
      "eval_samples_per_second": 462.039,
      "eval_steps_per_second": 7.269,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 123.14275360107422,
      "learning_rate": 7e-05,
      "loss": 0.5821,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.4669433534145355,
      "eval_runtime": 8.1427,
      "eval_samples_per_second": 460.533,
      "eval_steps_per_second": 7.246,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 141.0977020263672,
      "learning_rate": 7e-05,
      "loss": 0.4257,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.413972407579422,
      "eval_runtime": 8.1531,
      "eval_samples_per_second": 459.949,
      "eval_steps_per_second": 7.237,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 151.00146484375,
      "learning_rate": 7e-05,
      "loss": 0.3375,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.3760710060596466,
      "eval_runtime": 8.1165,
      "eval_samples_per_second": 462.023,
      "eval_steps_per_second": 7.269,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 82.18573760986328,
      "learning_rate": 7e-05,
      "loss": 0.2587,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.3440153896808624,
      "eval_runtime": 8.1481,
      "eval_samples_per_second": 460.231,
      "eval_steps_per_second": 7.241,
      "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
}