trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "convnextv2-tiny-22k-384-finetuned-spiderTraining100-1000-finetuned-spiderTraining5-100/checkpoint-12",
  "epoch": 4.8,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.96,
      "eval_accuracy": 0.9,
      "eval_f1": 0.9035725677830941,
      "eval_loss": 0.5551295280456543,
      "eval_precision": 0.9178571428571429,
      "eval_recall": 0.9121212121212121,
      "eval_runtime": 2.9056,
      "eval_samples_per_second": 17.208,
      "eval_steps_per_second": 1.377,
      "step": 6
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.3767,
      "step": 10
    },
    {
      "epoch": 1.92,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.094626285135746,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.1597,
      "eval_samples_per_second": 23.151,
      "eval_steps_per_second": 1.852,
      "step": 12
    },
    {
      "epoch": 2.88,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.04393688589334488,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.0599,
      "eval_samples_per_second": 24.272,
      "eval_steps_per_second": 1.942,
      "step": 18
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.1899,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.98,
      "eval_f1": 0.9779710144927536,
      "eval_loss": 0.041164983063936234,
      "eval_precision": 0.975,
      "eval_recall": 0.9833333333333334,
      "eval_runtime": 2.1688,
      "eval_samples_per_second": 23.054,
      "eval_steps_per_second": 1.844,
      "step": 25
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0,
      "loss": 0.1423,
      "step": 30
    },
    {
      "epoch": 4.8,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.03655298054218292,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.4104,
      "eval_samples_per_second": 20.743,
      "eval_steps_per_second": 1.659,
      "step": 30
    },
    {
      "epoch": 4.8,
      "step": 30,
      "total_flos": 1.411417875855442e+17,
      "train_loss": 0.5696131110191345,
      "train_runtime": 63.9531,
      "train_samples_per_second": 31.038,
      "train_steps_per_second": 0.469
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.411417875855442e+17,
  "trial_name": null,
  "trial_params": null
}