Downloads · 30 days
9
43% of all-time downloads
fp_bs8_lr1e4_x4
damgomz/fp_bs8_lr1e4_x4
fp_bs8_lr1e4_x4 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
21
Public
Parameters
32.5M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors130 MB · 98%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- Jul 6, 2024
- Updated
- Jul 10, 2024
- SHA
- 13eea018
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 192283.67964935303 |
| Emissions (Co2eq in kg) | 0.1446556131795172 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 15.0 |
| CPU energy (kWh) | 2.2700089682180074 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.8011702674567661 |
| Consumed energy (kWh) | 3.071179235674767 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 6 |
| 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) | 0.3701460833250046 |
| Emissions (Co2eq in kg) | 0.07531110786266326 |
Note
5 juillet 2024 !
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs8_lr1e4_x4 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 0.0001 |
| batch_size | 8 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 81709 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 17.859739 | 13.066814 |
| 0.5 | 3.997183 | 3.593726 |
| 1.0 | 3.391947 | 3.265344 |
| 1.5 | 6.459209 | 6.977757 |
| 2.0 | 6.985903 | 6.983891 |
| 2.5 | 6.982025 | 7.001526 |
| 3.0 | 6.995377 | 6.998771 |
| 3.5 | 6.984867 | 6.995654 |
| 4.0 | 6.984822 | 6.994850 |
| 4.5 | 6.975999 | 6.984660 |
| 5.0 | 6.978274 | 6.982478 |
| 5.5 | 6.975072 | 6.977838 |
| 6.0 | 6.976715 | 6.982384 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- Jul 6, 2024
- Updated
- Jul 10, 2024