Skip to main content
zaydzuhri
Projects
fla
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Zaydzuhri's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
334
Name
3 visualized
top_transformer-top.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
top_transformer-top.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
mtp_transformer-mtp.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
mtp_transformer-mtp.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
top_transformer-top.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
top_transformer-top.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup400.update1.steps40000.lr5e-5.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
top_transformer-top.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
top_transformer-top.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
transformer-vanilla.code.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine
mtp_transformer-mtp.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
mtp_transformer-mtp.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
top_transformer-top.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
top_transformer-top.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
transformer-vanilla.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
transformer-vanilla.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
transformer-vanilla.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
transformer-vanilla.code.340M.batch16.seqlen4096.context4096.warmup1000.update1.steps100000.lr3e-4.cosine
1-14
of 14
optimizer/lr
optimizer/lr
10k
20k
30k
40k
Step
0.000005
0.00001
0.000015
top_transformer-top.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
transformer-vanilla.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine
Previous
Next