trainer_state.json

{
  "best_metric": 0.8541333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0242/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": 93.34886932373047,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6507,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6061333333333333,
      "eval_loss": 3.022564649581909,
      "eval_runtime": 7.0781,
      "eval_samples_per_second": 529.804,
      "eval_steps_per_second": 8.336,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 168.55899047851562,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.6981,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7808,
      "eval_loss": 0.9125609397888184,
      "eval_runtime": 7.2687,
      "eval_samples_per_second": 515.909,
      "eval_steps_per_second": 8.117,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 256.1194152832031,
      "learning_rate": 2.5e-05,
      "loss": 0.7889,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8272,
      "eval_loss": 0.6210859417915344,
      "eval_runtime": 7.2034,
      "eval_samples_per_second": 520.589,
      "eval_steps_per_second": 8.191,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 163.99990844726562,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5813,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5485057234764099,
      "eval_runtime": 7.3296,
      "eval_samples_per_second": 511.621,
      "eval_steps_per_second": 8.05,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 117.14061737060547,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4787,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5229950547218323,
      "eval_runtime": 7.4769,
      "eval_samples_per_second": 501.546,
      "eval_steps_per_second": 7.891,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 265.1102294921875,
      "learning_rate": 0.0,
      "loss": 0.4313,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.503170907497406,
      "eval_runtime": 7.5325,
      "eval_samples_per_second": 497.844,
      "eval_steps_per_second": 7.833,
      "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
}