Token Classification
Transformers
Safetensors
Korean
roberta
named-entity-recognition
timex
korean
Eval Results (legacy)
Instructions to use kwoncho/ko-sroberta-korean-time-expression-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kwoncho/ko-sroberta-korean-time-expression-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="kwoncho/ko-sroberta-korean-time-expression-classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("kwoncho/ko-sroberta-korean-time-expression-classifier") model = AutoModelForTokenClassification.from_pretrained("kwoncho/ko-sroberta-korean-time-expression-classifier") - Notebooks
- Google Colab
- Kaggle
| { | |
| "eval_loss": 0.034969817847013474, | |
| "eval_precision": 0.8264533883728931, | |
| "eval_recall": 0.8267614923575464, | |
| "eval_f1": 0.8266074116550786, | |
| "eval_token_accuracy": 0.9898756337293201, | |
| "eval_label_date_precision": 0.8494581707845688, | |
| "eval_label_date_recall": 0.8366919989753223, | |
| "eval_label_date_f1": 0.8430267572915771, | |
| "eval_label_date_support": 23422, | |
| "eval_label_time_precision": 0.7933171651845864, | |
| "eval_label_time_recall": 0.8032742155525239, | |
| "eval_label_time_f1": 0.7982646420824295, | |
| "eval_label_time_support": 3665, | |
| "eval_label_duration_precision": 0.7847959754052544, | |
| "eval_label_duration_recall": 0.824669603524229, | |
| "eval_label_duration_f1": 0.8042388658169841, | |
| "eval_label_duration_support": 6810, | |
| "eval_label_set_precision": 0.7106652587117213, | |
| "eval_label_set_recall": 0.6909650924024641, | |
| "eval_label_set_f1": 0.7006767308693389, | |
| "eval_label_set_support": 974, | |
| "eval_runtime": 98.5723, | |
| "eval_samples_per_second": 455.422, | |
| "eval_steps_per_second": 28.466, | |
| "epoch": 2.0 | |
| } |