trainer_state.json

{
  "best_metric": 0.9128919860627178,
  "best_model_checkpoint": "brain-tumor-classification/checkpoint-81",
  "epoch": 4.938271604938271,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 13.366371154785156,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0827,
      "step": 20
    },
    {
      "epoch": 0.9876543209876543,
      "eval_accuracy": 0.7630662020905923,
      "eval_loss": 0.5737153887748718,
      "eval_runtime": 2.4539,
      "eval_samples_per_second": 116.958,
      "eval_steps_per_second": 3.668,
      "step": 20
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 7.611490249633789,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5357,
      "step": 40
    },
    {
      "epoch": 1.9753086419753085,
      "eval_accuracy": 0.8641114982578397,
      "eval_loss": 0.3689139187335968,
      "eval_runtime": 2.4398,
      "eval_samples_per_second": 117.633,
      "eval_steps_per_second": 3.689,
      "step": 40
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 7.663794040679932,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.3875,
      "step": 60
    },
    {
      "epoch": 2.962962962962963,
      "eval_accuracy": 0.8954703832752613,
      "eval_loss": 0.29916301369667053,
      "eval_runtime": 2.5481,
      "eval_samples_per_second": 112.634,
      "eval_steps_per_second": 3.532,
      "step": 60
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.111477851867676,
      "learning_rate": 1.0555555555555555e-05,
      "loss": 0.2921,
      "step": 81
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9128919860627178,
      "eval_loss": 0.27263280749320984,
      "eval_runtime": 2.6327,
      "eval_samples_per_second": 109.015,
      "eval_steps_per_second": 3.419,
      "step": 81
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 9.39560317993164,
      "learning_rate": 0.0,
      "loss": 0.2716,
      "step": 100
    },
    {
      "epoch": 4.938271604938271,
      "eval_accuracy": 0.9128919860627178,
      "eval_loss": 0.23185838758945465,
      "eval_runtime": 3.5061,
      "eval_samples_per_second": 81.858,
      "eval_steps_per_second": 2.567,
      "step": 100
    },
    {
      "epoch": 4.938271604938271,
      "step": 100,
      "total_flos": 3.1727957353537536e+17,
      "train_loss": 0.5141408157348633,
      "train_runtime": 269.7071,
      "train_samples_per_second": 47.885,
      "train_steps_per_second": 0.371
    }
  ],
  "logging_steps": 500,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.1727957353537536e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}