deberta-v3-large_spell_10k_2_p3 / train_results.json
stuartmesham's picture
Upload with huggingface_hub
ca1c328
raw
history blame contribute delete
195 Bytes
{
"epoch": 4.0,
"train_loss": 0.2823717478495925,
"train_runtime": 470.053,
"train_samples": 34304,
"train_samples_per_second": 1094.685,
"train_steps_per_second": 8.552
}