Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|---|---|
| Duration (in seconds) | 125291.3116736412 |
| Emissions (Co2eq in kg) | 0.0942573142848324 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 15.0 |
| CPU energy (kWh) | 1.479130924265915 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.522043451752268 |
| Consumed energy (kWh) | 2.001174376018184 |
| 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 |
Environmental Impact (for one core)
| Metric | Value |
|---|---|
| CPU energy (kWh) | 0.2411857749717593 |
| Emissions (Co2eq in kg) | 0.049072430405509467 |
Note
5 juillet 2024 !
My Config
| Config | Value |
|---|---|
| checkpoint | albert-base-v2 |
| model_name | fp_bs64_lr2e4_x4 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 0.0002 |
| 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 | 10332 |
Training and Testing steps
| Epoch | Train Loss | Test Loss |
|---|---|---|
| 0.0 | 14.371099 | 14.290434 |
| 0.5 | 7.091239 | 7.022568 |
| 1.0 | 7.002407 | 6.996346 |
| 1.5 | 6.980824 | 6.989908 |
| 2.0 | 6.981019 | 6.980749 |
| 2.5 | 6.966194 | 6.972139 |
| 3.0 | 6.963864 | 6.964913 |
| 3.5 | 6.958073 | 6.956380 |
| 4.0 | 6.949960 | 6.955792 |
| 4.5 | 6.947310 | 6.939385 |
| 5.0 | 6.937805 | 6.950055 |
| 5.5 | 6.928126 | 6.943197 |
| 6.0 | 6.936392 | 6.936043 |
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.