Downloads · 30 days
11
27% of all-time downloads
ft_bs64_lr7_base_x2
damgomz/ft_bs64_lr7_base_x2
ft_bs64_lr7_base_x2 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
41
Public
Parameters
18.8M
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors75.1 MB · 97%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- albert
- Access
- Public
- Created
- May 16, 2024
- Updated
- May 17, 2024
- SHA
- 48027ac1
Try a prompt
Model card
From the Hugging Face model README
Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 26423.72340154648 |
| Emissions (Co2eq in kg) | 0.0172858379899915 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 7.5 |
| CPU energy (kWh) | 0.3119461647588344 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.0550489731361468 |
| Consumed energy (kWh) | 0.3669951378949813 |
| 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) | 0.050865667547976966 |
| Emissions (Co2eq in kg) | 0.010349291665605703 |
Note
17 May 2024
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | ft_bs64_lr7_base_x2 |
| 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 | 0.664386 | 0.632545 | 0.740795 | 0.837423 |
| 1 | 0.589979 | 0.557067 | 0.743741 | 0.838957 |
| 2 | 0.512979 | 0.506961 | 0.767305 | 0.808282 |
| 3 | 0.471688 | 0.479002 | 0.779823 | 0.869632 |
| 4 | 0.439011 | 0.454375 | 0.788660 | 0.803681 |
| 5 | 0.413775 | 0.434841 | 0.802651 | 0.848160 |
| 6 | 0.392609 | 0.420262 | 0.807806 | 0.842025 |
| 7 | 0.380271 | 0.409428 | 0.809278 | 0.803681 |
| 8 | 0.365458 | 0.399789 | 0.825479 | 0.861963 |
| 9 | 0.353928 | 0.391207 | 0.829161 | 0.858896 |
| 10 | 0.342954 | 0.388762 | 0.827688 | 0.863497 |
| 11 | 0.335871 | 0.389029 | 0.827688 | 0.880368 |
| 12 | 0.328735 | 0.381536 | 0.827688 | 0.863497 |
| 13 | 0.320389 | 0.374983 | 0.827688 | 0.837423 |
| 14 | 0.314211 | 0.374905 | 0.826951 | 0.826687 |
- Task
- Fill-Mask
- Library
- transformers
- Type
- albert
- Languages
- en
- Created
- May 16, 2024
- Updated
- May 17, 2024