Downloads · 30 days
8
25% of all-time downloads
BERTrand_bs32_lr5_MLM
damgomz/BERTrand_bs32_lr5_MLM
BERTrand_bs32_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
32
Public
Parameters
11.2M
1.2 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
- 16fe383b
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 241846.94831728935 |
| Emissions (Co2eq in kg) | 0.2531373303414664 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 37.5 |
| CPU energy (kWh) | 2.855132522919462 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 2.5192189842984076 |
| Consumed energy (kWh) | 5.374351507217819 |
| 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) | 0.465555375510782 |
| Emissions (Co2eq in kg) | 0.09472338809093833 |
Note
2 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | BERTrand_bs32_lr5_MLM |
| sequence_length | 400 |
| num_epoch | 12 |
| learning_rate | 5e-05 |
| batch_size | 32 |
| weight_decay | 0.0 |
| warm_up_prop | 0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 6509 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 14.582730 | 13.090466 |
| 0.5 | 7.178169 | 6.963820 |
| 1.0 | 6.951572 | 6.939177 |
| 1.5 | 6.934508 | 6.940333 |
| 2.0 | 6.930150 | 6.935123 |
| 2.5 | 6.926595 | 6.925497 |
| 3.0 | 6.917610 | 6.923100 |
| 3.5 | 6.916435 | 6.919485 |
| 4.0 | 6.908440 | 6.914777 |
| 4.5 | 6.902250 | 6.908236 |
| 5.0 | 6.903971 | 6.906971 |
| 5.5 | 6.895701 | 6.909616 |
| 6.0 | 6.901696 | 6.901040 |
| 6.5 | 6.894878 | 6.902892 |
| 7.0 | 6.885180 | 6.895142 |
| 7.5 | 6.880067 | 6.894078 |
| 8.0 | 6.892053 | 6.900025 |
| 8.5 | 6.894274 | 6.898358 |
| 9.0 | 6.887418 | 6.895299 |
| 9.5 | 6.885919 | 6.891501 |
| 10.0 | 6.874649 | 6.886208 |
| 10.5 | 6.875007 | 6.893515 |
| 11.0 | 6.876712 | 6.886130 |
| 11.5 | 6.877406 | 6.883194 |
| 12.0 | 6.878842 | 6.884918 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 2, 2024
- Updated
- May 5, 2024