Views
No views yet
O labels by default. So that does not show up in the final inference result. To bypass that, use ignore_labels=[] in your pipeline config. aggregation_strategy groups the similar entities together, by default it is set to none, you can change it to aggregation _strategy="simple"{
"epoch": 3.370786516853933,
"eval_accuracy": 0.9924499166971433,
"eval_f1": 0.9209117830153314,
"eval_loss": 0.02725333906710148,
"eval_precision": 0.934574030073326,
"eval_recall": 0.908061511168004,
"eval_runtime": 85.2368,
"eval_samples_per_second": 46.107,
"eval_steps_per_second": 1.443,
"step": 1500
}