trainer_state.json

{
  "best_metric": 0.4144,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0922/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": 30.680429458618164,
      "learning_rate": 0.00028025614696414387,
      "loss": 3.3478,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22533333333333333,
      "eval_loss": 2.932523488998413,
      "eval_runtime": 8.5418,
      "eval_samples_per_second": 439.019,
      "eval_steps_per_second": 6.907,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 34.889991760253906,
      "learning_rate": 0.00022561193336869865,
      "loss": 2.7707,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2616,
      "eval_loss": 2.688565731048584,
      "eval_runtime": 6.0142,
      "eval_samples_per_second": 623.527,
      "eval_steps_per_second": 9.81,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.5567626953125,
      "learning_rate": 0.00015070756328895485,
      "loss": 2.4837,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.31893333333333335,
      "eval_loss": 2.49717378616333,
      "eval_runtime": 12.2488,
      "eval_samples_per_second": 306.152,
      "eval_steps_per_second": 4.817,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 41.21067810058594,
      "learning_rate": 7.561360219734159e-05,
      "loss": 2.1756,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3736,
      "eval_loss": 2.2569801807403564,
      "eval_runtime": 6.0123,
      "eval_samples_per_second": 623.719,
      "eval_steps_per_second": 9.813,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 37.52667999267578,
      "learning_rate": 2.0451416324810927e-05,
      "loss": 1.838,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4056,
      "eval_loss": 2.170523166656494,
      "eval_runtime": 5.7265,
      "eval_samples_per_second": 654.845,
      "eval_steps_per_second": 10.303,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 41.730804443359375,
      "learning_rate": 1.668828642892306e-09,
      "loss": 1.5679,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4144,
      "eval_loss": 2.204758882522583,
      "eval_runtime": 6.2167,
      "eval_samples_per_second": 603.214,
      "eval_steps_per_second": 9.491,
      "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}