gpt2-xl-lora-multi-3 / train_results.json
MHGanainy's picture
MHGanainy/gpt2-xl-lora-multi-3
fa018c9 verified
raw
history blame contribute delete
207 Bytes
{
"epoch": 1.0,
"total_flos": 8.372955480242258e+17,
"train_loss": 2.6846868539578486,
"train_runtime": 1624.688,
"train_samples_per_second": 56.585,
"train_steps_per_second": 3.537
}