opt-125m-sft-full / train_results.json
SebastianSchramm's picture
Model save
4a6e432
raw
history blame contribute delete
No virus
196 Bytes
{
"epoch": 0.62,
"train_loss": 1.8920561942240952,
"train_runtime": 23913.723,
"train_samples": 207865,
"train_samples_per_second": 8.692,
"train_steps_per_second": 0.272
}