full_1-2_3B / train_results.json
gulaschnascher4000's picture
End of training
7b54d8b verified
raw
history blame contribute delete
224 Bytes
{
"epoch": 0.4998118178396688,
"total_flos": 2.9336259752728986e+17,
"train_loss": 1.3684147273201541,
"train_runtime": 1819.5691,
"train_samples_per_second": 23.361,
"train_steps_per_second": 0.182
}