llama3-1_8b_r1_annotated_math / train_results.json
gsmyrnis's picture
End of training
8e680a3 verified
raw
history blame
202 Bytes
{
"epoch": 3.0,
"total_flos": 60301340835840.0,
"train_loss": 0.6545261012183295,
"train_runtime": 627.5494,
"train_samples_per_second": 27.043,
"train_steps_per_second": 0.057
}