Downloads · 30 days
4
15% of all-time downloads
damgomz/fp_bs32_lr5_x12
fp_bs32_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
4
15% of all-time downloads
All-time downloads
26
Public
Parameters
89.2M
4.6 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) | 201453.1611688137 |
| Emissions (Co2eq in kg) | 0.1317863700331207 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 7.5 |
| CPU energy (kWh) | 2.378262123556449 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.4196905745416857 |
| Consumed energy (kWh) | 2.7979526980981446 |
| 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 |
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.38779733524996635 |
| Emissions (Co2eq in kg) | 0.07890248812445204 |
23 May 2024
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs32_lr5_x12 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| batch_size | 32 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 20692 |
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 15.421972 | 13.059559 |
| 0.5 | 4.497486 | 4.070924 |
| 1.0 | 3.918884 | 3.823591 |
| 1.5 | 3.720594 | 3.667123 |
| 2.0 | 3.583184 | 3.566541 |
| 2.5 | 3.484332 | 3.466024 |
| 3.0 | 3.405282 | 3.404479 |
| 3.5 | 3.322916 | 3.341581 |
| 4.0 | 3.257505 | 3.292218 |
| 4.5 | 3.211615 | 3.236657 |
| 5.0 | 3.172503 | 3.200394 |
| 5.5 | 3.131317 | 3.165646 |
| 6.0 | 3.103778 | 3.159209 |