Downloads · 30 days
14
54% of all-time downloads
damgomz/fp_bs8_lr2e4_x2
fp_bs8_lr2e4_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.
Downloads · 30 days
14
54% of all-time downloads
All-time downloads
26
Public
Parameters
18.3M
879 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors73.2 MB · 97%
From the Hugging Face model README
| Metric | Value |
|---|---|
| Duration (in seconds) | [More Information Needed] |
| Emissions (Co2eq in kg) | [More Information Needed] |
| CPU power (W) | [NO CPU] |
| GPU power (W) | [No GPU] |
| RAM power (W) | [More Information Needed] |
| CPU energy (kWh) | [No CPU] |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | [More Information Needed] |
| Consumed energy (kWh) | [More Information Needed] |
| Country name | [More Information Needed] |
| Cloud provider | [No Cloud] |
| Cloud region | [No Cloud] |
| CPU count | [No CPU] |
| CPU model | [No CPU] |
| GPU count | [No GPU] |
| GPU model | [No GPU] |
| Metric | Value |
|---|---|
| CPU energy (kWh) | [No CPU] |
| Emissions (Co2eq in kg) | [More Information Needed] |
5 juillet 2024 !
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs8_lr2e4_x2 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 0.0002 |
| 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 | 83270 |
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 18.083176 | 11.266975 |
| 0.5 | 7.142726 | 7.066952 |
| 1.0 | 7.035545 | 7.021196 |
| 1.5 | 6.995318 | 7.026562 |
| 2.0 | 6.978820 | 6.988426 |
| 2.5 | 6.975003 | 6.972350 |
| 3.0 | 6.974181 | 6.971103 |
| 3.5 | 6.967837 | 6.964300 |
| 4.0 | 6.965952 | 6.966316 |
| 4.5 | 6.964535 | 6.966458 |
| 5.0 | 6.956336 | 6.965864 |
| 5.5 | 6.958633 | 6.957286 |