Files
sft__ot30k_SmolLM2-1.7B-Ins…/train_results.json

12 lines
338 B
JSON
Raw Normal View History

{
"epoch": 5.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.47408732771873474,
"total_flos": 1367215063302144.0,
"train_loss": 1.0890607003455466,
"train_runtime": 4651.4769,
"train_samples_per_second": 32.248,
"train_steps_per_second": 0.253,
"valid_targets_mean": 11629.8,
"valid_targets_min": 2098
}