tied-proposed-checkpoint-25000 / train_results.json
gartland's picture
Model save
dec590c verified
raw
history blame contribute delete
237 Bytes
{
"epoch": 1.0,
"total_flos": 9.910910713856e+17,
"train_loss": 4.172763576631546,
"train_runtime": 31305.579,
"train_samples": 51200000,
"train_samples_per_second": 1635.491,
"train_steps_per_second": 0.799
}