finewebedu-24K-embdnorm-seed336 / train_results.json
gartland's picture
Model save
cba9202 verified
raw
history blame contribute delete
237 Bytes
{
"epoch": 1.0,
"total_flos": 3.842835153776804e+17,
"train_loss": 3.367125130811293,
"train_runtime": 61395.5579,
"train_samples": 3305453,
"train_samples_per_second": 53.839,
"train_steps_per_second": 0.21
}