Environmental Impact (CODE CARBON DEFAULT)

Metric Value
Duration (in seconds) 31476.51491165161
Emissions (Co2eq in kg) 0.0193557967525063
CPU power (W) 42.5
GPU power (W) [No GPU]
RAM power (W) 4.500000000000001
CPU energy (kWh) 0.3715970706832078
GPU energy (kWh) [No GPU]
RAM energy (kWh) 0.0393453032049536
Consumed energy (kWh) 0.4109423738881623
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) 0.060592291204929344
Emissions (Co2eq in kg) 0.012328301673730212

Note

17 May 2024

My Config

Config Value
checkpoint albert-base-v2
model_name ft_bs32_lr6_base_x4
sequence_length 400
num_epoch 12
learning_rate 5e-06
batch_size 32
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 0.464978 0.393267 0.820324 0.863497
1 0.357935 0.372957 0.837261 0.881902
2 0.307998 0.368084 0.840206 0.819018
3 0.270172 0.422406 0.818851 0.742331
4 0.219624 0.438727 0.824742 0.814417
5 0.160742 0.480765 0.811487 0.891104
6 0.098260 0.613929 0.811487 0.866564
7 0.068914 0.678225 0.814433 0.771472
8 0.034506 0.775600 0.809278 0.826687
9 0.030098 0.782375 0.811487 0.842025
10 0.035147 0.840999 0.804860 0.849693
11 0.019798 0.855098 0.821060 0.860429
Downloads last month
-
Safetensors
Model size
32.9M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support