Model: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.35-20260428-045924 Source: Original Platform
9 lines
218 B
JSON
9 lines
218 B
JSON
{
|
|
"epoch": 1.0,
|
|
"total_flos": 0.0,
|
|
"train_loss": 1.1324475014612363,
|
|
"train_runtime": 1725.4575,
|
|
"train_samples": 43598,
|
|
"train_samples_per_second": 25.268,
|
|
"train_steps_per_second": 0.395
|
|
} |