martimfasantos
/

tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_4epochs_old

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_4epochs_old / runs

449 kB

1 contributor

History: 60 commits

martimfasantos's picture

End of training

929369c verified over 1 year ago

Jun29_09-38-28_poseidon
End of training over 1 year ago