metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: google/bert_uncased_L-4_H-512_A-8
model-index:
- name: bert-small-finetuned-ner-to-multilabel-xglue-ner
results: []
bert-small-finetuned-ner-to-multilabel-xglue-ner
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0616
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2168 | 0.28 | 500 | 0.1212 |
| 0.1067 | 0.57 | 1000 | 0.0865 |
| 0.0878 | 0.85 | 1500 | 0.0710 |
| 0.0667 | 1.14 | 2000 | 0.0670 |
| 0.0529 | 1.42 | 2500 | 0.0614 |
| 0.0516 | 1.71 | 3000 | 0.0577 |
| 0.0469 | 1.99 | 3500 | 0.0608 |
| 0.033 | 2.28 | 4000 | 0.0592 |
| 0.0317 | 2.56 | 4500 | 0.0616 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1