ekaterina-blatova-jb
/

model_lr1e-4_old_scheduler_with_t_max_275_all_v3

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

## Evaluation results

Validation loss on the whole input: 0.8534868267597631

Validation loss on completion: 0.9337991051143035

Downloads last month: 1

Safetensors

Model size

1.35B params

Tensor type

BF16

·