finewebedu-24K-base-seed84 / train_results.json
gartland's picture
Model save
9739637 verified
raw
history blame contribute delete
240 Bytes
{
"epoch": 1.0,
"total_flos": 4.2193166778142556e+18,
"train_loss": 3.2925657239619093,
"train_runtime": 59835.7309,
"train_samples": 3305453,
"train_samples_per_second": 55.242,
"train_steps_per_second": 0.216
}