Edit model card

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 37375.12590241432
Emissions (Co2eq in kg) 0.0226162737932339
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 3.75
CPU energy (kWh) 0.4412333646724621
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.0389321051314473
Consumed energy (kWh) 0.4801654698039091
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) 0.07194711736214757
Emissions (Co2eq in kg) 0.014638590978445607

Note

17 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name ft_bs16_lr7_base_x4
sequence_length 400
num_epoch 15
learning_rate 5e-07
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 81450

Training and Testing steps

Epoch Train Loss Test Loss Accuracy Recall
0 0.605615 0.536105 0.730486 0.645706
1 0.482335 0.471153 0.768778 0.822086
2 0.437222 0.441530 0.788660 0.860429
3 0.402839 0.413280 0.807806 0.845092
4 0.377685 0.391815 0.821797 0.845092
5 0.357874 0.384717 0.824006 0.872699
6 0.344697 0.380295 0.827688 0.874233
7 0.332695 0.372667 0.836524 0.838957
8 0.321463 0.372000 0.835788 0.831288
9 0.312764 0.383289 0.830633 0.895706
10 0.301846 0.372779 0.840206 0.875767
11 0.293261 0.393013 0.831370 0.911043
12 0.286456 0.385383 0.829897 0.891104
13 0.277988 0.382923 0.842415 0.881902
14 0.268274 0.382455 0.839470 0.855828
Downloads last month
3
Safetensors
Model size
32.9M params
Tensor type
F32
·
Inference API
Examples
Mask token: [MASK]
This model can be loaded on Inference API (serverless).