Model: W-61/llama3-8b-base-new-method-q_t-0.4-s_star0.6-beta-next-batch Source: Original Platform
9 lines
232 B
JSON
9 lines
232 B
JSON
{
|
|
"epoch": 0.9989528795811519,
|
|
"total_flos": 0.0,
|
|
"train_loss": 2.2929351502244577,
|
|
"train_runtime": 6534.1855,
|
|
"train_samples": 61135,
|
|
"train_samples_per_second": 9.356,
|
|
"train_steps_per_second": 0.073
|
|
} |