metadata
base_model: klue/roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: klue-roberta-large-ner-identified
results: []
klue-roberta-large-ner-identified
This model is a fine-tuned version of klue/roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0044
- Precision: 0.9920
- Recall: 0.9977
- F1: 0.9948
- Accuracy: 0.9990
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 61 | 0.0093 | 0.9807 | 0.9931 | 0.9869 | 0.9981 |
| No log | 2.0 | 122 | 0.0065 | 0.9874 | 0.9931 | 0.9903 | 0.9984 |
| No log | 3.0 | 183 | 0.0044 | 0.9920 | 0.9977 | 0.9948 | 0.9990 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1