Downloads · 30 days
8
25% of all-time downloads
ft_bs64_lr7_base_x4
damgomz/ft_bs64_lr7_base_x4
ft_bs64_lr7_base_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
32
Public
Parameters
32.9M
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors132 MB · 98%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 17, 2024
- Updated
- May 17, 2024
- SHA
- 0c73e787
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 26475.748703956604 |
| Emissions (Co2eq in kg) | 0.0173198704923115 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 7.5 |
| CPU energy (kWh) | 0.3125603431133757 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.0551573378766576 |
| Consumed energy (kWh) | 0.3677176809900338 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 3 |
| 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) | 0.05096581625511646 |
| Emissions (Co2eq in kg) | 0.010369668242383001 |
Note
17 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ft_bs64_lr7_base_x4 |
| sequence_length | 400 |
| num_epoch | 15 |
| learning_rate | 5e-07 |
| 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 | 81450 |
Training and Testing steps
| Epoch | Train Loss | Test Loss | Accuracy | Recall |
|---|---|---|---|---|
| 0 | 0.640842 | 0.587673 | 0.723122 | 0.808282 |
| 1 | 0.545254 | 0.528299 | 0.735641 | 0.806748 |
| 2 | 0.498372 | 0.501702 | 0.748895 | 0.838957 |
| 3 | 0.471714 | 0.477527 | 0.768778 | 0.829755 |
| 4 | 0.449965 | 0.455789 | 0.776878 | 0.846626 |
| 5 | 0.423347 | 0.442834 | 0.784978 | 0.884969 |
| 6 | 0.402362 | 0.414682 | 0.806333 | 0.832822 |
| 7 | 0.380589 | 0.400692 | 0.811487 | 0.855828 |
| 8 | 0.367983 | 0.393791 | 0.814433 | 0.852761 |
| 9 | 0.355760 | 0.386102 | 0.822533 | 0.825153 |
| 10 | 0.348000 | 0.381949 | 0.824006 | 0.865031 |
| 11 | 0.343452 | 0.382962 | 0.824006 | 0.875767 |
| 12 | 0.334328 | 0.381772 | 0.824006 | 0.878834 |
| 13 | 0.328141 | 0.387798 | 0.823270 | 0.892638 |
| 14 | 0.323139 | 0.377890 | 0.824742 | 0.878834 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 17, 2024
- Updated
- May 17, 2024