openwebtext-196K-base / all_results.json
gartland's picture
Model save
fbe5fdd verified
raw
history blame contribute delete
236 Bytes
{
"epoch": 1.0,
"total_flos": 784469399961600.0,
"train_loss": 3.5054829134226324,
"train_runtime": 13203.7025,
"train_samples": 3323380,
"train_samples_per_second": 251.701,
"train_steps_per_second": 0.983
}