ekaterina-blatova-jb
/

model_lr4e-5_old_scheduler_with_warmup_100_3__epochs_relevant_v4

Text Generation

text-generation-inference

Model card Files Files and versions

## Evaluation results

Validation loss on the whole input: 0.8452366881538182

Validation loss on completion: 0.907067182008177

Downloads last month: 2

Safetensors

Model size

1B params

Tensor type

BF16

·