Unable to reproduce results for spacetimeformer

[TayyabaZainab0807]

I am using the following command that is provided by this repo (only difference is the batch_size)

python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100 --d_ff 400 --enc_layers 5 --dec_layers 5 --l2_coeff 1e-3 --dropout_ff .2 --dropout_emb .1 --d_qk 20 --d_v 20 --n_heads 6 --run_name spatiotemporal_al_solar --batch_size 3 --class_loss_imp 0 --initial_downsample_convs 1 --decay_factor .8 --warmup_steps 1000

I am getting the following results (where as I am expecting MSE: ~7.75):
test/acc -1.0
test/class_loss 0.0
test/forecast_loss 0.08704246580600739
test/loss 0.08704246580600739
test/mae 1.7290080221756612
test/mape 21375719.51865129
test/mse 9.604532779042728
test/norm_mae 0.1794128092716004
test/norm_mse 0.0870416207133817
test/recon_loss -1.0
test/smape 1.4066449396255207

[jakegrigsby]

There is a big difference between a batch size of 32 and a batch size of 3!

This is probably the most memory-intensive dataset in the paper. It should be possible to get closer to 7.75 using a larger batch size but a smaller model with more of the memory saving tricks

[TayyabaZainab0807]

Thanks, that works for spacetimeformer model.
I am not able to find the right commands to replicate the other results for lstm, lstnet etc. Are you able to provide that as well?

[HariniS2506]

I used the same command and with GPUs set -

python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100 --d_ff 400 --enc_layers 5 --dec_layers 5 --l2_coeff 1e-3 --dropout_ff .2 --dropout_emb .1 --d_qk 20 --d_v 20 --n_heads 6 --run_name spatiotemporal_al_solar --batch_size 32 --class_loss_imp 0 --initial_downsample_convs 1 --decay_factor .8 --warmup_steps 1000 --gpus 0 1, and still see the MSE at ~9. Were there any other changes that you had to do?

test/acc : -1.0
test/class_loss : 0.0
test/forecast_loss : 0.08345500379800797
test/loss : 0.08345500379800797
test/mae : 1.7061005777056486
test/mape : 20300980.869295612
test/mse : 9.204660098343183
test/norm_mae : 0.17708396412653812
test/norm_mse : 0.08345417754154151
test/recon_loss : -1.0
test/smape : 1.403714211316733