damgomz's picture
Upload README.md with huggingface_hub
222b1ec verified
metadata
language: en
tags:
  - fill-mask
kwargs:
  timestamp: '2024-05-05T09:41:17'
  project_name: BERTrand_bs16_lr5_MLM_emissions_tracker
  run_id: 01605f9e-783b-448f-a289-89c5c8cbee1e
  duration: 210252.26313185692
  emissions: 0.2200678251572063
  emissions_rate: 0.000001046684691423244
  cpu_power: 42.5
  gpu_power: 0
  ram_power: 37.5
  cpu_energy: 2.4821408681437296
  gpu_energy: 0
  ram_energy: 2.1901129089991205
  energy_consumed: 4.6722537771428705
  country_name: Switzerland
  country_iso_code: CHE
  region: .nan
  cloud_provider: .nan
  cloud_region: .nan
  os: Linux-5.14.0-70.30.1.el9_0.x86_64-x86_64-with-glibc2.34
  python_version: 3.10.4
  codecarbon_version: 2.3.4
  cpu_count: 4
  cpu_model: Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz
  gpu_count: .nan
  gpu_model: .nan
  longitude: .nan
  latitude: .nan
  ram_total_size: 100
  tracking_mode: machine
  on_cloud: 'N'
  pue: 1

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 210252.26313185692
Emissions (Co2eq in kg) 0.2200678251572063
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 37.5
CPU energy (kWh) 2.4821408681437296
GPU energy (kWh) [No GPU]
RAM energy (kWh) 2.1901129089991205
Consumed energy (kWh) 4.6722537771428705
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) 0.40473560652882457
Emissions (Co2eq in kg) 0.08234880305997729

Note

2 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name BERTrand_bs16_lr5_MLM
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 13033

Training and Testing steps

Epoch Train Loss Test Loss
0.0 14.743229 13.097182
0.5 7.100540 6.967106
1.0 6.948475 6.939338
1.5 6.938035 6.938765
2.0 6.931950 6.935680
2.5 6.923858 6.936854
3.0 6.920174 6.932032
3.5 6.920139 6.914489
4.0 6.911595 6.913473
4.5 6.905194 6.909112
5.0 6.903432 6.907618
5.5 6.901336 6.901513
6.0 6.896765 6.905171
6.5 6.900726 6.894976
7.0 6.881094 6.894709
7.5 6.885156 6.894880
8.0 6.883777 6.893790
8.5 6.884839 6.888695
9.0 6.881206 6.888314
9.5 6.875793 6.884028
10.0 6.871364 6.881168
10.5 6.880161 6.887640
11.0 6.878505 6.883618
11.5 6.873283 6.881647
12.0 6.866277 6.883143