Environmental Impact (CODE CARBON DEFAULT)
Metric | Value |
---|---|
Duration (in seconds) | 190422.01247096065 |
Emissions (Co2eq in kg) | 0.1993119180945443 |
CPU power (W) | 42.5 |
GPU power (W) | [No GPU] |
RAM power (W) | 37.5 |
CPU energy (kWh) | 2.2480348206905836 |
GPU energy (kWh) | [No GPU] |
RAM energy (kWh) | 1.9835508801341004 |
Consumed energy (kWh) | 4.231585700824702 |
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 |
Environmental Impact (for one core)
Metric | Value |
---|---|
CPU energy (kWh) | 0.3665623740065992 |
Emissions (Co2eq in kg) | 0.07458195488445958 |
Note
30 April 2024
My Config
Config | Value |
---|---|
checkpoint | albert-base-v2 |
model_name | BERTrand_bs16_lr5 |
sequence_length | 400 |
num_epoch | 12 |
learning_rate | 5e-05 |
batch_size | 16 |
weight_decay | 0.0 |
warm_up_prop | 0 |
drop_out_prob | 0.1 |
packing_length | 100 |
train_test_split | 0.2 |
num_steps | 12590 |
Training and Testing steps
Epoch | Train Loss | Test Loss |
---|---|---|
0.0 | 15.505644 | 13.835570 |
0.5 | 2.703247 | 3.216191 |
1.0 | 2.525614 | 3.149906 |
1.5 | 2.203586 | 3.040256 |
2.0 | 2.160747 | 2.952961 |
2.5 | 2.370840 | 2.949682 |
3.0 | 2.350076 | 2.925128 |
3.5 | 2.110838 | 2.981181 |
4.0 | 1.903310 | 2.836523 |
4.5 | 2.270815 | 2.814076 |
5.0 | 2.256549 | 2.848042 |
5.5 | 2.214569 | 2.812752 |
6.0 | 1.896058 | 2.755932 |
6.5 | 2.082173 | 2.737672 |
7.0 | 2.156056 | 2.711664 |
7.5 | 2.133011 | 2.690121 |
8.0 | 1.826039 | 2.718429 |
8.5 | 1.919896 | 2.646301 |
9.0 | 2.058763 | 2.616522 |
9.5 | 2.088796 | 2.676844 |
10.0 | 1.848681 | 2.622713 |
10.5 | 1.776635 | 2.581153 |
11.0 | 2.059736 | 2.579319 |
11.5 | 2.055293 | 2.591116 |
12.0 | 1.912107 | 2.555768 |
- Downloads last month
- 2
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.