TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
loubnabnl's picture
loubnabnl HF staff
End of training
cdd2791 verified
raw
history blame contribute delete
416 Bytes
{
"epoch": 1.9993181043300376,
"eval_loss": 0.8305559158325195,
"eval_runtime": 59.0293,
"eval_samples": 32534,
"eval_samples_per_second": 188.364,
"eval_steps_per_second": 5.895,
"total_flos": 143858545459200.0,
"train_loss": 0.8359313647060732,
"train_runtime": 3324.125,
"train_samples": 286314,
"train_samples_per_second": 56.452,
"train_steps_per_second": 0.441
}