Skip to content

Added results for Nvidia GTX 1650 mobile GFX #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lorenzobilli wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Added results for Nvidia GTX 1650 mobile GFX #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions benchmark/pytorch-m1-gpu/lenet-mnist-results/1650-mobile.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
torch 1.11.0
device cuda
Epoch: 001/001 | Batch 0000/0421 | Loss: 2.3098
Epoch: 001/001 | Batch 0100/0421 | Loss: 0.2646
Epoch: 001/001 | Batch 0200/0421 | Loss: 0.1437
Epoch: 001/001 | Batch 0300/0421 | Loss: 0.1009
Epoch: 001/001 | Batch 0400/0421 | Loss: 0.0733
Time / epoch without evaluation: 0.17 min
Epoch: 001/001 | Train: 97.33% | Validation: 97.77% | Best Validation (Ep. 001): 97.77%
Time elapsed: 0.33 min
Total Training Time: 0.33 min
Test accuracy 97.41%
Total Time: 0.37 min
13 changes: 13 additions & 0 deletions benchmark/pytorch-m1-gpu/mlp-results/mlp-1650-mobile.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
torch 1.11.0
device cuda
Epoch: 001/001 | Batch 0000/0421 | Loss: 2.3063
Epoch: 001/001 | Batch 0100/0421 | Loss: 0.3429
Epoch: 001/001 | Batch 0200/0421 | Loss: 0.3083
Epoch: 001/001 | Batch 0300/0421 | Loss: 0.3685
Epoch: 001/001 | Batch 0400/0421 | Loss: 0.3488
Time / epoch without evaluation: 0.15 min
Epoch: 001/001 | Train: 91.51% | Validation: 93.50% | Best Validation (Ep. 001): 93.50%
Time elapsed: 0.31 min
Total Training Time: 0.31 min
Test accuracy 92.02%
Total Time: 0.36 min
84 changes: 84 additions & 0 deletions benchmark/pytorch-m1-gpu/vgg16-cifar10-results/1650-mobile.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,84 @@
torch 1.11.0
device cuda
Files already downloaded and verified
Epoch: 001/001 | Batch 0000/7500 | Loss: 2.7112
Epoch: 001/001 | Batch 0100/7500 | Loss: 3.3736
Epoch: 001/001 | Batch 0200/7500 | Loss: 2.4909
Epoch: 001/001 | Batch 0300/7500 | Loss: 2.4650
Epoch: 001/001 | Batch 0400/7500 | Loss: 2.3477
Epoch: 001/001 | Batch 0500/7500 | Loss: 2.5414
Epoch: 001/001 | Batch 0600/7500 | Loss: 2.2295
Epoch: 001/001 | Batch 0700/7500 | Loss: 2.1820
Epoch: 001/001 | Batch 0800/7500 | Loss: 2.2750
Epoch: 001/001 | Batch 0900/7500 | Loss: 2.2879
Epoch: 001/001 | Batch 1000/7500 | Loss: 2.1813
Epoch: 001/001 | Batch 1100/7500 | Loss: 2.3119
Epoch: 001/001 | Batch 1200/7500 | Loss: 2.3572
Epoch: 001/001 | Batch 1300/7500 | Loss: 2.2303
Epoch: 001/001 | Batch 1400/7500 | Loss: 2.3146
Epoch: 001/001 | Batch 1500/7500 | Loss: 2.3390
Epoch: 001/001 | Batch 1600/7500 | Loss: 2.2801
Epoch: 001/001 | Batch 1700/7500 | Loss: 2.2589
Epoch: 001/001 | Batch 1800/7500 | Loss: 2.3259
Epoch: 001/001 | Batch 1900/7500 | Loss: 2.2918
Epoch: 001/001 | Batch 2000/7500 | Loss: 2.2828
Epoch: 001/001 | Batch 2100/7500 | Loss: 2.2876
Epoch: 001/001 | Batch 2200/7500 | Loss: 2.3170
Epoch: 001/001 | Batch 2300/7500 | Loss: 2.2883
Epoch: 001/001 | Batch 2400/7500 | Loss: 2.2963
Epoch: 001/001 | Batch 2500/7500 | Loss: 2.3111
Epoch: 001/001 | Batch 2600/7500 | Loss: 2.3091
Epoch: 001/001 | Batch 2700/7500 | Loss: 2.3158
Epoch: 001/001 | Batch 2800/7500 | Loss: 2.3067
Epoch: 001/001 | Batch 2900/7500 | Loss: 2.3496
Epoch: 001/001 | Batch 3000/7500 | Loss: 2.3086
Epoch: 001/001 | Batch 3100/7500 | Loss: 2.2959
Epoch: 001/001 | Batch 3200/7500 | Loss: 2.3301
Epoch: 001/001 | Batch 3300/7500 | Loss: 2.2873
Epoch: 001/001 | Batch 3400/7500 | Loss: 2.3042
Epoch: 001/001 | Batch 3500/7500 | Loss: 2.2933
Epoch: 001/001 | Batch 3600/7500 | Loss: 2.2993
Epoch: 001/001 | Batch 3700/7500 | Loss: 2.3330
Epoch: 001/001 | Batch 3800/7500 | Loss: 2.2996
Epoch: 001/001 | Batch 3900/7500 | Loss: 2.3007
Epoch: 001/001 | Batch 4000/7500 | Loss: 2.3114
Epoch: 001/001 | Batch 4100/7500 | Loss: 2.3171
Epoch: 001/001 | Batch 4200/7500 | Loss: 2.2754
Epoch: 001/001 | Batch 4300/7500 | Loss: 2.3120
Epoch: 001/001 | Batch 4400/7500 | Loss: 2.3021
Epoch: 001/001 | Batch 4500/7500 | Loss: 2.3274
Epoch: 001/001 | Batch 4600/7500 | Loss: 2.2762
Epoch: 001/001 | Batch 4700/7500 | Loss: 2.3018
Epoch: 001/001 | Batch 4800/7500 | Loss: 2.3128
Epoch: 001/001 | Batch 4900/7500 | Loss: 2.2862
Epoch: 001/001 | Batch 5000/7500 | Loss: 2.3215
Epoch: 001/001 | Batch 5100/7500 | Loss: 2.3133
Epoch: 001/001 | Batch 5200/7500 | Loss: 2.2790
Epoch: 001/001 | Batch 5300/7500 | Loss: 2.3116
Epoch: 001/001 | Batch 5400/7500 | Loss: 2.2879
Epoch: 001/001 | Batch 5500/7500 | Loss: 2.2910
Epoch: 001/001 | Batch 5600/7500 | Loss: 2.2535
Epoch: 001/001 | Batch 5700/7500 | Loss: 2.2963
Epoch: 001/001 | Batch 5800/7500 | Loss: 2.3441
Epoch: 001/001 | Batch 5900/7500 | Loss: 2.3322
Epoch: 001/001 | Batch 6000/7500 | Loss: 2.2994
Epoch: 001/001 | Batch 6100/7500 | Loss: 2.2874
Epoch: 001/001 | Batch 6200/7500 | Loss: 2.2989
Epoch: 001/001 | Batch 6300/7500 | Loss: 2.3250
Epoch: 001/001 | Batch 6400/7500 | Loss: 2.2876
Epoch: 001/001 | Batch 6500/7500 | Loss: 2.3035
Epoch: 001/001 | Batch 6600/7500 | Loss: 2.3119
Epoch: 001/001 | Batch 6700/7500 | Loss: 2.2984
Epoch: 001/001 | Batch 6800/7500 | Loss: 2.2805
Epoch: 001/001 | Batch 6900/7500 | Loss: 2.2990
Epoch: 001/001 | Batch 7000/7500 | Loss: 2.3076
Epoch: 001/001 | Batch 7100/7500 | Loss: 2.2989
Epoch: 001/001 | Batch 7200/7500 | Loss: 2.3211
Epoch: 001/001 | Batch 7300/7500 | Loss: 2.3158
Epoch: 001/001 | Batch 7400/7500 | Loss: 2.2926
Time / epoch without evaluation: 50.55 min
Epoch: 001/001 | Train: 10.18% | Validation: 9.72% | Best Validation (Ep. 001): 9.72%
Time elapsed: 67.65 min
Total Training Time: 67.65 min
Test accuracy 10.12%
Total Time: 71.19 min