groderg's picture
Evaluation on the test set completed on 2024_10_31.
a3260b6 verified
raw
history blame
249 Bytes
{
"epoch": 60.0,
"learning_rate": 1.0000000000000002e-06,
"total_flos": 4.4402778184752e+17,
"train_loss": 0.6329069137573242,
"train_runtime": 375.0945,
"train_samples_per_second": 19.995,
"train_steps_per_second": 0.8
}