Downloads · 30 days
8
26% of all-time downloads
damgomz/fp_bs2_lr2e4_x1
fp_bs2_lr2e4_x1 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
8
26% of all-time downloads
All-time downloads
31
Public
Parameters
11.2M
449 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors44.9 MB · 95%
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_bs2_lr2e4_x1 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 0.0002 |
| batch_size | 2 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 329137 |
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 13.293138 | 5.338855 |
| 0.5 | 7.208543 | 7.114806 |
| 1.0 | 7.129493 | 7.083235 |
| 1.5 | 7.065612 | 7.052887 |
| 2.0 | 7.035378 | 7.039544 |
| 2.5 | 7.033363 | 7.032447 |
| 3.0 | 7.026585 | 7.030799 |
| 3.5 | 7.039110 | 7.038784 |
| 4.0 | 7.031608 | 7.034350 |
| 4.5 | 7.036214 | 7.028307 |