phi-2-gpo-test-iter-2 / train_results.json
lole25's picture
Model save
3a1c508 verified
raw
history blame contribute delete
194 Bytes
{
"epoch": 2.0,
"train_loss": 0.00022506012464873493,
"train_runtime": 14.2725,
"train_samples": 30567,
"train_samples_per_second": 0.28,
"train_steps_per_second": 0.14
}