llama3-8b-closedqa-gpt4o-100k / train_results.json
chansung's picture
Model save
edd93d9 verified
raw
history blame
250 Bytes
{
"epoch": 9.991416309012875,
"total_flos": 8.683561975386472e+18,
"train_loss": 0.6765515476977293,
"train_runtime": 24420.5896,
"train_samples": 111440,
"train_samples_per_second": 7.63,
"train_steps_per_second": 0.238
}