Edit model card

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 18129.05792498589
Emissions (Co2eq in kg) 0.0118596516104099
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 7.5
CPU energy (kWh) 0.2140232932743098
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.0377686349312464
Consumed energy (kWh) 0.2517919282055566
Country name Switzerland
Cloud provider nan
Cloud region nan
CPU count 3
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) 0.03489843650559783
Emissions (Co2eq in kg) 0.00710054768728614

Note

17 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name ft_bs64_lr6_base_x4
sequence_length 400
num_epoch 12
learning_rate 5e-06
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 65160

Training and Testing steps

Epoch Train Loss Test Loss Accuracy Recall
0 0.494021 0.421029 0.805596 0.891104
1 0.370485 0.376504 0.825479 0.888037
2 0.325639 0.374071 0.835788 0.897239
3 0.287644 0.374302 0.830633 0.906442
4 0.259016 0.370951 0.849779 0.877301
5 0.221142 0.409426 0.824742 0.815951
6 0.192179 0.451972 0.821797 0.852761
7 0.119463 0.534428 0.812960 0.800613
8 0.075451 0.618039 0.817378 0.757669
9 0.051555 0.791213 0.799705 0.702454
10 0.024909 0.752735 0.809278 0.826687
11 0.019373 0.822910 0.813697 0.802147
Downloads last month
4
Safetensors
Model size
32.9M params
Tensor type
F32
·
Inference API
Examples
Mask token: [MASK]
This model can be loaded on Inference API (serverless).