Edit model card

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 37993.74807047844
Emissions (Co2eq in kg) 0.0229906147552034
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 3.75
CPU energy (kWh) 0.4485365634348655
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.0395765287543337
Consumed energy (kWh) 0.4881130921891984
Country name Switzerland
Cloud provider nan
Cloud region nan
CPU count 2
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) 0.07313796503567101
Emissions (Co2eq in kg) 0.014880884660937389

Note

19 juin 2024

My Config

Config Value
checkpoint albert-base-v2
model_name BERTrand_base_x2
sequence_length 400
num_epoch 6
learning_rate 9e-06
batch_size 16
weight_decay 0.0
warm_up_prop 0.0
drop_out_prob 0.1
packing_length 100
train_test_split 0.2
num_steps 36660

Training and Testing steps

Epoch Train Loss Test Loss F-beta Score TN FP FN TP
0 0.000000 0.762512 0.001627 753.000000 9.000000 765.000000 1.000000
1 0.285383 0.236045 0.945052 638.000000 124.000000 23.000000 743.000000
2 0.171418 0.223179 0.937339 662.000000 100.000000 36.000000 730.000000
3 0.113694 0.209987 0.938465 671.000000 91.000000 37.000000 729.000000
4 0.064221 0.242213 0.933953 674.000000 88.000000 42.000000 724.000000
5 0.041251 0.297383 0.924348 669.000000 93.000000 50.000000 716.000000
6 0.029554 0.291359 0.926215 690.000000 72.000000 53.000000 713.000000
Downloads last month
8
Safetensors
Model size
18.8M params
Tensor type
F32
·
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.