Downloads · 30 days
9
35% of all-time downloads
damgomz/fp_bs64_lr5_x12
fp_bs64_lr5_x12 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.
Downloads · 30 days
9
35% of all-time downloads
All-time downloads
26
Public
Parameters
89.2M
5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors357 MB · 99%
From the Hugging Face model README
| Metric | Value |
|---|---|
| Duration (in seconds) | 155678.44930887222 |
| Emissions (Co2eq in kg) | 0.1171176028558728 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 15.0 |
| CPU energy (kWh) | 1.837866699090107 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.6486538175841199 |
| Consumed energy (kWh) | 2.4865205166742284 |
| 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 |
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.299681014919579 |
| Emissions (Co2eq in kg) | 0.06097405931264161 |
23 May 2024
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs64_lr5_x12 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| 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 | 10277 |
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 13.221970 | 10.445522 |
| 0.5 | 5.688688 | 4.877213 |
| 1.0 | 4.586195 | 4.400257 |
| 1.5 | 4.258424 | 4.156283 |
| 2.0 | 4.056837 | 4.003972 |
| 2.5 | 3.925051 | 3.884834 |
| 3.0 | 3.825081 | 3.796477 |
| 3.5 | 3.742108 | 3.722046 |
| 4.0 | 3.678339 | 3.669979 |
| 4.5 | 3.617364 | 3.608691 |
| 5.0 | 3.559870 | 3.564922 |
| 5.5 | 3.519773 | 3.532238 |
| 6.0 | 3.486098 | 3.507260 |