Model: W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.8-20260428-045924 Source: Original Platform
9 lines
231 B
JSON
9 lines
231 B
JSON
{
|
|
"epoch": 0.999244142101285,
|
|
"total_flos": 0.0,
|
|
"train_loss": 1.068178587349388,
|
|
"train_runtime": 1640.4212,
|
|
"train_samples": 42336,
|
|
"train_samples_per_second": 25.808,
|
|
"train_steps_per_second": 0.403
|
|
} |