Downloads · 30 days
5
24% of all-time downloads
damgomz/fp_bs32_lr3e4_x8
fp_bs32_lr3e4_x8 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
5
24% of all-time downloads
All-time downloads
21
Public
Parameters
60.8M
1.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors243 MB · 99%
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_bs32_lr3e4_x8 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 0.0003 |
| 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 | 20759 |
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 12.091244 | 9.005878 |
| 0.5 | 7.135014 | 7.059272 |
| 1.0 | 7.026751 | 7.017254 |
| 1.5 | 6.995179 | 6.992611 |
| 2.0 | 6.981124 | 6.977240 |
| 2.5 | 6.968991 | 6.976820 |
| 3.0 | 6.962148 | 6.971019 |