hp_ablations_qwen_bsz512 / train_results.json
sedrickkeh's picture
End of training
66b12bb verified
raw
history blame contribute delete
219 Bytes
{
"epoch": 2.996011396011396,
"total_flos": 2755219238682624.0,
"train_loss": 0.6040235166317434,
"train_runtime": 70686.1657,
"train_samples_per_second": 9.533,
"train_steps_per_second": 0.019
}