Files
sft_ot30k_1.7b-MixtureVitae…/train_results.json

12 lines
337 B
JSON
Raw Normal View History

{
"epoch": 5.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.43892961740493774,
"total_flos": 9938320304898048.0,
"train_loss": 0.9563364079150748,
"train_runtime": 6894.0534,
"train_samples_per_second": 21.758,
"train_steps_per_second": 0.17,
"valid_targets_mean": 11464.1,
"valid_targets_min": 2081
}