hp_ablations_qwen_bsz512 / all_results.json
sedrickkeh's picture
End of training
66b12bb verified
raw
history blame contribute delete
360 Bytes
{
"epoch": 2.996011396011396,
"eval_loss": 0.618689239025116,
"eval_runtime": 441.8642,
"eval_samples_per_second": 26.757,
"eval_steps_per_second": 0.419,
"total_flos": 2755219238682624.0,
"train_loss": 0.6040235166317434,
"train_runtime": 70686.1657,
"train_samples_per_second": 9.533,
"train_steps_per_second": 0.019
}