Downloads · 30 days
17
52% of all-time downloads
BERT_BASE_TS_phonetic_wikitext_0.1
psktoure/BERT_BASE_TS_phonetic_wikitext_0.1
BERT_BASE_TS_phonetic_wikitext_0.1 is a fill-mask model from psktoure. 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
33
Public
Parameters
110M
14.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jan 29, 2025
- Updated
- Jan 29, 2025
- SHA
- 33799f89
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_BASE_TS_phonetic_wikitext_0.1
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6507
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: 1e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0329 | 0.3019 | 2000 | 1.8882 |
| 1.9681 | 0.6039 | 4000 | 1.8298 |
| 1.9319 | 0.9058 | 6000 | 1.7763 |
| 1.9071 | 1.2077 | 8000 | 1.7500 |
| 1.8933 | 1.5097 | 10000 | 1.7627 |
| 1.873 | 1.8116 | 12000 | 1.7301 |
| 1.8574 | 2.1135 | 14000 | 1.7349 |
| 1.8503 | 2.4155 | 16000 | 1.7112 |
| 1.8429 | 2.7174 | 18000 | 1.7434 |
| 1.8313 | 3.0193 | 20000 | 1.7067 |
| 1.8255 | 3.3213 | 22000 | 1.7033 |
| 1.8157 | 3.6232 | 24000 | 1.7196 |
| 1.8141 | 3.9251 | 26000 | 1.6885 |
| 1.8041 | 4.2271 | 28000 | 1.6771 |
| 1.8056 | 4.5290 | 30000 | 1.6808 |
| 1.8046 | 4.8309 | 32000 | 1.7183 |
| 1.7945 | 5.1329 | 34000 | 1.7004 |
| 1.7953 | 5.4348 | 36000 | 1.6781 |
| 1.785 | 5.7367 | 38000 | 1.6549 |
| 1.7834 | 6.0386 | 40000 | 1.6632 |
| 1.786 | 6.3406 | 42000 | 1.6552 |
| 1.7751 | 6.6425 | 44000 | 1.6625 |
| 1.7791 | 6.9444 | 46000 | 1.6730 |
| 1.7751 | 7.2464 | 48000 | 1.6537 |
| 1.7682 | 7.5483 | 50000 | 1.6641 |
| 1.7733 | 7.8502 | 52000 | 1.6872 |
| 1.7644 | 8.1522 | 54000 | 1.6517 |
| 1.7707 | 8.4541 | 56000 | 1.6492 |
| 1.7662 | 8.7560 | 58000 | 1.6529 |
| 1.7649 | 9.0580 | 60000 | 1.6670 |
| 1.7594 | 9.3599 | 62000 | 1.6597 |
| 1.7583 | 9.6618 | 64000 | 1.6389 |
| 1.7631 | 9.9638 | 66000 | 1.6507 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jan 29, 2025
- Updated
- Jan 29, 2025