Downloads · 30 days
12
26% of all-time downloads
bert_large_finetuned_ontonotes
filippo-baglini/bert_large_finetuned_ontonotes
bert_large_finetuned_ontonotes is a token classification model from filippo-baglini. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
46
Public
Parameters
333M
2.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 8, 2025
- Updated
- May 8, 2025
- SHA
- e076ff5b
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bert_large_finetuned_ontonotes
This model is a fine-tuned version of bert-large-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0693
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0887 | 1.0 | 893 | 0.0781 |
| 0.0864 | 2.0 | 1786 | 0.0732 |
| 0.0726 | 3.0 | 2679 | 0.0693 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 8, 2025
- Updated
- May 8, 2025