hp_ablations_qwen_lr2e-6 / all_results.json
sedrickkeh's picture
End of training
72b71e9 verified
raw
history blame contribute delete
360 Bytes
{
"epoch": 2.996011396011396,
"eval_loss": 0.6223183870315552,
"eval_runtime": 446.084,
"eval_samples_per_second": 26.504,
"eval_steps_per_second": 0.415,
"total_flos": 2755219238682624.0,
"train_loss": 0.6269598571495741,
"train_runtime": 70419.7857,
"train_samples_per_second": 9.569,
"train_steps_per_second": 0.019
}