Edit model card

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 151651.88416481018
Emissions (Co2eq in kg) 0.1140884166517009
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 15.0
CPU energy (kWh) 1.7903310629947349
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.6318768869787442
Consumed energy (kWh) 2.422207949973481
Country name Switzerland
Cloud provider nan
Cloud region nan
CPU count 6
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) 0.2919298770172596
Emissions (Co2eq in kg) 0.059396987964550646

Note

23 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name fp_bs64_lr5_x8
sequence_length 400
num_epoch 6
learning_rate 5e-05
batch_size 64
weight_decay 0.0
warm_up_prop 0.0
drop_out_prob 0.1
packing_length 100
train_test_split 0.2
num_steps 10339

Training and Testing steps

Epoch Train Loss Test Loss
0.0 16.989065 15.229211
0.5 4.269291 3.716872
1.0 3.579481 3.484213
1.5 3.391314 3.360293
2.0 3.284667 3.264651
2.5 3.194252 3.194249
3.0 3.128233 3.120842
3.5 3.062395 3.079286
4.0 3.018365 3.026540
4.5 2.979813 2.999546
5.0 2.942663 2.967505
5.5 2.907309 2.946242
6.0 2.890174 2.926466
Downloads last month
1
Safetensors
Model size
60.8M params
Tensor type
F32
·
Inference API
Examples
Mask token: [MASK]
This model can be loaded on Inference API (serverless).