Environmental Impact (CODE CARBON DEFAULT)
Metric | Value |
---|---|
Duration (in seconds) | 199222.14457845688 |
Emissions (Co2eq in kg) | 0.2085228370280885 |
CPU power (W) | 42.5 |
GPU power (W) | [No GPU] |
RAM power (W) | 37.5 |
CPU energy (kWh) | 2.3519248156185015 |
GPU energy (kWh) | [No GPU] |
RAM energy (kWh) | 2.075217644798255 |
Consumed energy (kWh) | 4.427142460416734 |
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) | 0.3835026283135295 |
Emissions (Co2eq in kg) | 0.07802867329322895 |
Note
30 April 2024
My Config
Config | Value |
---|---|
checkpoint | albert-base-v2 |
model_name | BERTrand_bs16_lr6 |
sequence_length | 400 |
num_epoch | 12 |
learning_rate | 5e-06 |
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 | 12597 |
Training and Testing steps
Epoch | Train Loss | Test Loss |
---|---|---|
0.0 | 15.499363 | 15.126202 |
0.5 | 8.243008 | 8.091313 |
1.0 | 7.354550 | 7.973097 |
1.5 | 7.244512 | 7.687902 |
2.0 | 7.199471 | 7.686438 |
2.5 | 7.161911 | 7.657964 |
3.0 | 7.049606 | 7.765894 |
3.5 | 7.091233 | 7.786471 |
4.0 | 7.060327 | 7.814007 |
4.5 | 7.164975 | 7.602441 |
5.0 | 7.008690 | 7.586652 |
5.5 | 7.035732 | 7.525334 |
6.0 | 7.045719 | 7.715493 |
6.5 | 7.108394 | 7.486681 |
7.0 | 6.992529 | 7.641908 |
7.5 | 6.993111 | 7.575982 |
8.0 | 7.051304 | 7.670884 |
8.5 | 7.075128 | 7.527084 |
9.0 | 7.010871 | 7.556140 |
9.5 | 6.978617 | 7.623441 |
10.0 | 7.033166 | 7.562979 |
10.5 | 7.026733 | 7.549661 |
11.0 | 7.080350 | 7.510597 |
11.5 | 6.955319 | 7.589880 |
12.0 | 7.023086 | 7.495114 |
- Downloads last month
- 3
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.