trainer_state.json

{
  "best_metric": 0.955,
  "best_model_checkpoint": "convnextv2-tiny-22k-384-finetuned-Spiders/checkpoint-50",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6257,
      "step": 10
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3622,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.925,
      "eval_f1": 0.9302325581395349,
      "eval_loss": 0.20231212675571442,
      "eval_precision": 0.9259259259259259,
      "eval_recall": 0.9345794392523364,
      "eval_runtime": 10.2461,
      "eval_samples_per_second": 19.52,
      "eval_steps_per_second": 1.269,
      "step": 25
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.2914,
      "step": 30
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.2233,
      "step": 40
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 0.2266,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.955,
      "eval_f1": 0.958139534883721,
      "eval_loss": 0.1582118272781372,
      "eval_precision": 0.9537037037037037,
      "eval_recall": 0.9626168224299065,
      "eval_runtime": 9.1443,
      "eval_samples_per_second": 21.872,
      "eval_steps_per_second": 1.422,
      "step": 50
    },
    {
      "epoch": 2.0,
      "step": 50,
      "total_flos": 2.366961881186304e+17,
      "train_loss": 0.3458255386352539,
      "train_runtime": 204.4792,
      "train_samples_per_second": 15.65,
      "train_steps_per_second": 0.245
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.366961881186304e+17,
  "trial_name": null,
  "trial_params": null
}