Skip to main content
ai2-llm
Projects
olmoe
Reports
OLMoE-1B-7B-0924
Log in
Sign up
Share
Comment
5 stars
Share
Comment
5 stars
OLMoE-1B-7B-0924
Niklas Muennighoff
Created on August 8
|
Last edited on October 9
Comment
eval/c4_en-validation/CrossEntropyLoss
eval/c4_en-validation/CrossEntropyLoss
200k
400k
600k
800k
1M
1.2M
Step
2
2.2
2.4
2.6
2.8
3
olmoe-8x1b-newhp-newds-final-annealFrom1200000
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
train/CrossEntropyLoss
train/CrossEntropyLoss
0
200k
400k
600k
800k
1M
1.2M
Step
2
2.2
2.4
2.6
2.8
3
olmoe-8x1b-newhp-newds-final-annealFrom1200000
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
olmoe-8x1b-newhp-newds-final
Run set
7
Add a comment