trainer_state.json

{
  "best_metric": 0.9146666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0832/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": 124.42582702636719,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.1791,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5295311808586121,
      "eval_runtime": 7.8727,
      "eval_samples_per_second": 476.329,
      "eval_steps_per_second": 7.494,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.33154296875,
      "learning_rate": 0.000375,
      "loss": 0.3768,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.3690202534198761,
      "eval_runtime": 8.0652,
      "eval_samples_per_second": 464.961,
      "eval_steps_per_second": 7.315,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 42.58807373046875,
      "learning_rate": 0.00025,
      "loss": 0.2169,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8976,
      "eval_loss": 0.3606549799442291,
      "eval_runtime": 7.8499,
      "eval_samples_per_second": 477.714,
      "eval_steps_per_second": 7.516,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.270179748535156,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1137,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9002666666666667,
      "eval_loss": 0.36078891158103943,
      "eval_runtime": 7.8413,
      "eval_samples_per_second": 478.239,
      "eval_steps_per_second": 7.524,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 22.109786987304688,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0514,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9130666666666667,
      "eval_loss": 0.33478158712387085,
      "eval_runtime": 7.9094,
      "eval_samples_per_second": 474.122,
      "eval_steps_per_second": 7.46,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.49112319946289,
      "learning_rate": 0.0,
      "loss": 0.0321,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.3367697298526764,
      "eval_runtime": 7.8613,
      "eval_samples_per_second": 477.02,
      "eval_steps_per_second": 7.505,
      "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
}