trainer_state.json

{
  "best_metric": 0.8858666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0384/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 72.84222412109375,
      "learning_rate": 0.0001,
      "loss": 2.5375,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7728,
      "eval_loss": 0.8246504068374634,
      "eval_runtime": 7.121,
      "eval_samples_per_second": 526.611,
      "eval_steps_per_second": 8.285,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.7403335571289,
      "learning_rate": 0.0001,
      "loss": 0.6465,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.48490557074546814,
      "eval_runtime": 7.1189,
      "eval_samples_per_second": 526.769,
      "eval_steps_per_second": 8.288,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 57.98207092285156,
      "learning_rate": 0.0001,
      "loss": 0.4142,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4113468825817108,
      "eval_runtime": 7.5865,
      "eval_samples_per_second": 494.299,
      "eval_steps_per_second": 7.777,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 78.32767486572266,
      "learning_rate": 0.0001,
      "loss": 0.302,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.40172675251960754,
      "eval_runtime": 7.0561,
      "eval_samples_per_second": 531.455,
      "eval_steps_per_second": 8.362,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 67.89668273925781,
      "learning_rate": 0.0001,
      "loss": 0.2197,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.37304219603538513,
      "eval_runtime": 7.6094,
      "eval_samples_per_second": 492.808,
      "eval_steps_per_second": 7.754,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}