Downloads · 30 days
13
32% of all-time downloads
ThunBERT_bs64_lr5
damgomz/ThunBERT_bs64_lr5
ThunBERT_bs64_lr5 is a fill-mask model from damgomz. Use it when you need the model to fill a missing word. It is set up for transformers.
All-time downloads
41
Public
Parameters
11.8M
614 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.3 MB · 95%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 15, 2024
- Updated
- May 17, 2024
- SHA
- 8c838949
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 184456.9054911137 |
| Emissions (Co2eq in kg) | 0.1930682235875487 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 37.5 |
| CPU energy (kWh) | 2.1776130225039214 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 1.921412976679702 |
| Consumed energy (kWh) | 4.099025999183643 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 4 |
| CPU model | Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz |
| GPU count | nan |
| GPU model | nan |
Environmental Impact (for one core)
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.35507954307039385 |
| Emissions (Co2eq in kg) | 0.07224562131735286 |
Note
15 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ThunBERT_bs64_lr5 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| batch_size | 64 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 10202 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 6.313161 | 3.869947 |
| 0.5 | 3.235009 | 3.143104 |
| 1.0 | 3.136574 | 2.972763 |
| 1.5 | 2.935173 | 2.894075 |
| 2.0 | 2.882950 | 2.869101 |
| 2.5 | 2.833622 | 2.830031 |
| 3.0 | 2.800498 | 2.798549 |
| 3.5 | 2.762751 | 2.772544 |
| 4.0 | 2.737487 | 2.744573 |
| 4.5 | 2.709161 | 2.716146 |
| 5.0 | 2.674846 | 2.692947 |
| 5.5 | 2.647017 | 2.664257 |
| 6.0 | 2.625876 | 2.656301 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 15, 2024
- Updated
- May 17, 2024