Edit model card

Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 29334.1406750679
Emissions (Co2eq in kg) 0.0191897816027374
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 7.5
CPU energy (kWh) 0.3463053195810985
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.0611123913536468
Consumed energy (kWh) 0.4074177109347459
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) 0.05646822079950571
Emissions (Co2eq in kg) 0.011489205097734928

Note

20 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name ft_bs16_1lr6_base_x8
sequence_length 400
num_epoch 20
learning_rate 1e-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 108600

Training and Testing steps

Epoch Train Loss Test Loss Accuracy Recall
0 0.523328 0.476205 0.776141 0.906442
1 0.431474 0.413639 0.813697 0.866564
2 0.384488 0.402209 0.823270 0.897239
3 0.353091 0.387237 0.822533 0.800613
4 0.328723 0.390632 0.836524 0.918712
5 0.314824 0.373720 0.835052 0.848160
6 0.299005 0.389435 0.810751 0.750000
7 0.289835 0.386018 0.835052 0.860429
8 0.273817 0.388888 0.829897 0.814417
9 0.257712 0.386943 0.837997 0.871166
10 0.236881 0.410112 0.832842 0.855828
11 0.218910 0.429738 0.820324 0.837423
12 0.207044 0.461636 0.832106 0.891104
13 0.192752 0.454077 0.817378 0.828221
14 0.167404 0.477347 0.802651 0.754601
15 0.146702 0.511787 0.810751 0.875767
16 0.134885 0.540342 0.814433 0.858896
17 0.118554 0.552969 0.807069 0.802147
18 0.105443 0.596917 0.805596 0.803681
19 0.085186 0.638636 0.796024 0.757669
Downloads last month
3
Safetensors
Model size
61.3M params
Tensor type
F32
·
Inference API
Examples
Mask token: [MASK]
This model can be loaded on Inference API (serverless).