Downloads · 30 days
7
39% of all-time downloads
fp_bs8_lr5_x4
damgomz/fp_bs8_lr5_x4
fp_bs8_lr5_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
18
Public
Parameters
32.5M
1.7 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
- Jun 25, 2024
- Updated
- Jun 27, 2024
- SHA
- 2468915e
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 177735.54814982414 |
| Emissions (Co2eq in kg) | 0.1337112984336831 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 15.0 |
| CPU energy (kWh) | 2.098262737140218 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.7405580614348248 |
| Consumed energy (kWh) | 2.8388207985750444 |
| 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) | 0.34214093018841146 |
| Emissions (Co2eq in kg) | 0.06961308969201445 |
Note
24 juin 2024 !
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs8_lr5_x4 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| 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 | 81287 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 15.470805 | 10.927505 |
| 0.5 | 3.806336 | 3.467919 |
| 1.0 | 3.306795 | 3.229490 |
| 1.5 | 3.119937 | 3.106039 |
| 2.0 | 2.988004 | 2.978410 |
| 2.5 | 2.893831 | 2.911033 |
| 3.0 | 2.817451 | 2.824359 |
| 3.5 | 2.749720 | 2.786094 |
| 4.0 | 2.679766 | 2.726988 |
| 4.5 | 2.637161 | 2.677145 |
| 5.0 | 2.585987 | 2.642253 |
| 5.5 | 2.547930 | 2.603068 |
| 6.0 | 2.514662 | 2.587190 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- Jun 25, 2024
- Updated
- Jun 27, 2024