Downloads · 30 days
7
26% of all-time downloads
BERTrand_bs64_lr6
damgomz/BERTrand_bs64_lr6
BERTrand_bs64_lr6 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
27
Public
Parameters
11.8M
1.2 GB 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 1, 2024
- Updated
- May 4, 2024
- SHA
- 7faaf4c3
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 210196.29861307144 |
| Emissions (Co2eq in kg) | 0.2715737813178914 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 56.25 |
| CPU energy (kWh) | 2.4814802918722147 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 3.284294985041019 |
| Consumed energy (kWh) | 5.765775276913259 |
| 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) | 0.4046278748301625 |
| Emissions (Co2eq in kg) | 0.08232688362345299 |
Note
30 April 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | BERTrand_bs64_lr6 |
| sequence_length | 400 |
| num_epoch | 12 |
| learning_rate | 5e-06 |
| batch_size | 64 |
| weight_decay | 0.0 |
| warm_up_prop | 0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 3147 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 15.574399 | 15.096123 |
| 0.5 | 9.594637 | 8.148669 |
| 1.0 | 7.853338 | 8.074202 |
| 1.5 | 7.905947 | 7.939530 |
| 2.0 | 7.834033 | 7.833388 |
| 2.5 | 7.720610 | 7.871610 |
| 3.0 | 7.495963 | 7.976839 |
| 3.5 | 7.330389 | 7.752517 |
| 4.0 | 7.214343 | 7.848690 |
| 4.5 | 7.346055 | 7.724831 |
| 5.0 | 7.110836 | 7.715771 |
| 5.5 | 7.125741 | 7.595748 |
| 6.0 | 7.127250 | 7.659738 |
| 6.5 | 7.239036 | 7.671448 |
| 7.0 | 7.073343 | 7.705375 |
| 7.5 | 7.070813 | 7.589307 |
| 8.0 | 7.124647 | 7.582091 |
| 8.5 | 7.166616 | 7.539913 |
| 9.0 | 7.092505 | 7.611073 |
| 9.5 | 7.048057 | 7.625665 |
| 10.0 | 7.101367 | 7.564788 |
| 10.5 | 7.108332 | 7.602001 |
| 11.0 | 7.179604 | 7.554187 |
| 11.5 | 7.028062 | 7.575663 |
| 12.0 | 7.086092 | 7.574604 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 1, 2024
- Updated
- May 4, 2024