Skip to main content
cjackson692-university-of-north-texas
Projects
nanoGPT_testing_gp1
Log in
Sign up
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Cjackson692's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
128
Name
20 visualized
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.2
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.2
run_block_size64_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer4_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer4_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1
run_block_size64_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1
run_block_size64_n_layer6_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer6_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size128_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size128_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size128_n_layer6_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size64_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size64_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size64_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.1
run_block_size128_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size128_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size128_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size128_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer4_n_head8_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
run_block_size64_n_layer4_n_head4_n_embd128_batch_size8_max_iters1000_dropout0.2
1-20
of 20
Previous
Next
mfu
mfu
Showing first 10 runs
0
2
4
6
8
Step
-100
-80
-60
-40
-20
0
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer6_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.2
run_block_size64_n_layer4_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size64_n_layer4_n_head8_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer6_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1
run_block_size64_n_layer6_n_head4_n_embd256_batch_size16_max_iters2000_dropout0.1
run_block_size128_n_layer4_n_head4_n_embd256_batch_size16_max_iters1000_dropout0.1