Downloads · 30 days
21
62% of all-time downloads
ThunBERT_bs8_lr5
damgomz/ThunBERT_bs8_lr5
ThunBERT_bs8_lr5 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
34
Public
Parameters
11.8M
614 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.3 MB · 95%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 15, 2024
- Updated
- May 17, 2024
- SHA
- e3d9a27a
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 199505.3919699192 |
| Emissions (Co2eq in kg) | 0.2088190820973 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 37.5 |
| CPU energy (kWh) | 2.3552678664051694 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 2.078164164704575 |
| Consumed energy (kWh) | 4.433432031109744 |
| 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) | 0.38404787954209446 |
| Emissions (Co2eq in kg) | 0.07813961185488502 |
Note
15 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ThunBERT_bs8_lr5 |
| 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 | 82627 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 7.067743 | 3.953574 |
| 0.5 | 3.522399 | 3.376064 |
| 1.0 | 3.303520 | 3.226876 |
| 1.5 | 3.154914 | 3.167486 |
| 2.0 | 3.058335 | 3.051049 |
| 2.5 | 2.983440 | 2.994546 |
| 3.0 | 2.966602 | 2.926526 |
| 3.5 | 2.846851 | 2.879127 |
| 4.0 | 2.785210 | 2.832286 |
| 4.5 | 2.718725 | 2.795912 |
| 5.0 | 2.670722 | 2.733300 |
| 5.5 | 2.628934 | 2.693741 |
| 6.0 | 2.589258 | 2.672380 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 15, 2024
- Updated
- May 17, 2024