martimfasantos
/

tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_3epochs_old

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_3epochs_old / runs /Jun27_22-38-11_poseidon

1 contributor

History: 42 commits

martimfasantos's picture

Training in progress, step 4200

e2f2c66 verified 6 months ago

events.out.tfevents.1719528220.poseidon.708792.0

326 kB
LFS

Training in progress, step 4200 6 months ago