tiny-gpt2 / train_results.json
taufeeque's picture
Update to 1M parameter model
9763874
raw
history blame contribute delete
198 Bytes
{
"epoch": 14.01,
"train_loss": 5.854185776367188,
"train_runtime": 10672.3435,
"train_samples": 114149,
"train_samples_per_second": 149.92,
"train_steps_per_second": 4.685
}