trainer_state.json

{
  "best_metric": 0.8957333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0195/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": 157.25726318359375,
      "learning_rate": 7e-05,
      "loss": 3.1632,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6981333333333334,
      "eval_loss": 1.3223464488983154,
      "eval_runtime": 7.6303,
      "eval_samples_per_second": 491.459,
      "eval_steps_per_second": 7.732,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 77.81354522705078,
      "learning_rate": 7e-05,
      "loss": 0.7995,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8386666666666667,
      "eval_loss": 0.5484474897384644,
      "eval_runtime": 7.8047,
      "eval_samples_per_second": 480.478,
      "eval_steps_per_second": 7.56,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 58.8615837097168,
      "learning_rate": 7e-05,
      "loss": 0.4441,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.4222109913825989,
      "eval_runtime": 7.7806,
      "eval_samples_per_second": 481.967,
      "eval_steps_per_second": 7.583,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 75.31504821777344,
      "learning_rate": 7e-05,
      "loss": 0.3189,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.38464999198913574,
      "eval_runtime": 7.9631,
      "eval_samples_per_second": 470.925,
      "eval_steps_per_second": 7.409,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 144.9026336669922,
      "learning_rate": 7e-05,
      "loss": 0.2433,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.37830787897109985,
      "eval_runtime": 7.7532,
      "eval_samples_per_second": 483.671,
      "eval_steps_per_second": 7.61,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 71.94446563720703,
      "learning_rate": 7e-05,
      "loss": 0.1867,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8957333333333334,
      "eval_loss": 0.3544939458370209,
      "eval_runtime": 7.7623,
      "eval_samples_per_second": 483.105,
      "eval_steps_per_second": 7.601,
      "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
}