Downloads · 30 days
9
25% of all-time downloads
BERTrand_bs64_lr5_MLM
damgomz/BERTrand_bs64_lr5_MLM
BERTrand_bs64_lr5_MLM 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
36
Public
Parameters
11.2M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors44.9 MB · 95%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 2, 2024
- Updated
- May 5, 2024
- SHA
- 468fccf0
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 218668.64404559135 |
| Emissions (Co2eq in kg) | 0.2825201325920018 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 56.25 |
| CPU energy (kWh) | 2.5815012231401315 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 3.416675728347145 |
| Consumed energy (kWh) | 5.99817695148727 |
| 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) | 0.4209371397877633 |
| Emissions (Co2eq in kg) | 0.0856452189178566 |
Note
2 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | BERTrand_bs64_lr5_MLM |
| sequence_length | 400 |
| num_epoch | 12 |
| learning_rate | 5e-05 |
| batch_size | 64 |
| weight_decay | 0.0 |
| warm_up_prop | 0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 3270 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 14.601907 | 13.069239 |
| 0.5 | 7.447329 | 6.978540 |
| 1.0 | 6.960886 | 6.950151 |
| 1.5 | 4.932429 | 2.806009 |
| 2.0 | 2.701225 | 2.655897 |
| 2.5 | 2.606577 | 2.581771 |
| 3.0 | 2.548158 | 2.557307 |
| 3.5 | 2.505096 | 2.519658 |
| 4.0 | 2.481079 | 2.493212 |
| 4.5 | 2.450955 | 2.467917 |
| 5.0 | 2.436830 | 2.450555 |
| 5.5 | 2.415499 | 2.444447 |
| 6.0 | 2.396800 | 2.423250 |
| 6.5 | 2.386172 | 2.408114 |
| 7.0 | 2.366631 | 2.397662 |
| 7.5 | 2.364014 | 2.391399 |
| 8.0 | 2.338708 | 2.381241 |
| 8.5 | 2.341727 | 2.370836 |
| 9.0 | 2.321789 | 2.366722 |
| 9.5 | 2.321147 | 2.363208 |
| 10.0 | 2.313457 | 2.352971 |
| 10.5 | 2.306482 | 2.342249 |
| 11.0 | 2.295090 | 2.330649 |
| 11.5 | 2.306711 | 2.333718 |
| 12.0 | 2.291483 | 2.335983 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 2, 2024
- Updated
- May 5, 2024