PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
lillian039's picture
End of training
013b42c verified
raw
history blame contribute delete
190 Bytes
{
"epoch": 3.0,
"eval_loss": 0.03329204395413399,
"eval_runtime": 1932.0264,
"eval_samples": 10376,
"eval_samples_per_second": 5.371,
"eval_steps_per_second": 0.671
}