Downloads · 30 days
5
18% of all-time downloads
bottleneckBERTNaiveLarge
colaguo/bottleneckBERTNaiveLarge
bottleneckBERTNaiveLarge is a fill-mask model from colaguo. Use it when you need the model to fill a missing word. 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
28
Public
Parameters
110M
17.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 57%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 21, 2025
- Updated
- Mar 21, 2025
- SHA
- a612cc80
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. -->
bottleneckBERTNaiveLarge
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6059
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: 32
- eval_batch_size: 32
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5127 | 0.2565 | 500 | 2.3510 |
| 2.3725 | 0.5131 | 1000 | 2.1748 |
| 2.2831 | 0.7696 | 1500 | 2.1483 |
| 2.2449 | 1.0262 | 2000 | 2.0949 |
| 2.1528 | 1.2827 | 2500 | 2.0488 |
| 2.0983 | 1.5393 | 3000 | 2.0060 |
| 2.0759 | 1.7958 | 3500 | 1.9816 |
| 2.041 | 2.0523 | 4000 | 1.9463 |
| 1.9968 | 2.3089 | 4500 | 1.9486 |
| 1.9619 | 2.5654 | 5000 | 1.8828 |
| 1.9562 | 2.8220 | 5500 | 1.8673 |
| 1.8602 | 3.0785 | 6000 | 1.8672 |
| 1.8518 | 3.3350 | 6500 | 1.8396 |
| 1.9018 | 3.5916 | 7000 | 1.8198 |
| 1.8382 | 3.8481 | 7500 | 1.8130 |
| 1.772 | 4.1047 | 8000 | 1.7946 |
| 1.7975 | 4.3612 | 8500 | 1.7969 |
| 1.7607 | 4.6178 | 9000 | 1.7562 |
| 1.7784 | 4.8743 | 9500 | 1.7573 |
| 1.7218 | 5.1308 | 10000 | 1.7460 |
| 1.7168 | 5.3874 | 10500 | 1.7086 |
| 1.6769 | 5.6439 | 11000 | 1.7056 |
| 1.6516 | 5.9005 | 11500 | 1.6827 |
| 1.6521 | 6.1570 | 12000 | 1.6822 |
| 1.6314 | 6.4135 | 12500 | 1.6814 |
| 1.6361 | 6.6701 | 13000 | 1.6649 |
| 1.6258 | 6.9266 | 13500 | 1.6498 |
| 1.5767 | 7.1832 | 14000 | 1.6543 |
| 1.5556 | 7.4397 | 14500 | 1.6411 |
| 1.5617 | 7.6963 | 15000 | 1.6478 |
| 1.592 | 7.9528 | 15500 | 1.6274 |
| 1.519 | 8.2093 | 16000 | 1.6358 |
| 1.5476 | 8.4659 | 16500 | 1.5946 |
| 1.5254 | 8.7224 | 17000 | 1.5997 |
| 1.5117 | 8.9790 | 17500 | 1.6184 |
| 1.5238 | 9.2355 | 18000 | 1.5940 |
| 1.4984 | 9.4920 | 18500 | 1.5980 |
| 1.5024 | 9.7486 | 19000 | 1.6059 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 21, 2025
- Updated
- Mar 21, 2025