trainer_state.json

{
  "best_metric": 0.7397333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0793/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": 334.7185974121094,
      "learning_rate": 2.5e-05,
      "loss": 3.8478,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3522666666666667,
      "eval_loss": 3.763369560241699,
      "eval_runtime": 7.3604,
      "eval_samples_per_second": 509.48,
      "eval_steps_per_second": 8.016,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 71.18836212158203,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 3.3801,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5309333333333334,
      "eval_loss": 2.953477621078491,
      "eval_runtime": 7.331,
      "eval_samples_per_second": 511.527,
      "eval_steps_per_second": 8.048,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 404.7352600097656,
      "learning_rate": 1.5e-05,
      "loss": 2.3108,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6458666666666667,
      "eval_loss": 1.7611116170883179,
      "eval_runtime": 7.3544,
      "eval_samples_per_second": 509.899,
      "eval_steps_per_second": 8.022,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 373.7424011230469,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.5056,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6989333333333333,
      "eval_loss": 1.295870065689087,
      "eval_runtime": 7.3573,
      "eval_samples_per_second": 509.699,
      "eval_steps_per_second": 8.019,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 230.51055908203125,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 1.1985,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7309333333333333,
      "eval_loss": 1.1363532543182373,
      "eval_runtime": 7.3563,
      "eval_samples_per_second": 509.764,
      "eval_steps_per_second": 8.02,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 190.1915283203125,
      "learning_rate": 0.0,
      "loss": 1.0888,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7397333333333334,
      "eval_loss": 1.0774717330932617,
      "eval_runtime": 7.3793,
      "eval_samples_per_second": 508.18,
      "eval_steps_per_second": 7.995,
      "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
}