Model: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48 Source: Original Platform
9 lines
218 B
JSON
9 lines
218 B
JSON
{
|
|
"epoch": 1.0,
|
|
"total_flos": 0.0,
|
|
"train_loss": 1.0968060302664355,
|
|
"train_runtime": 1742.1859,
|
|
"train_samples": 43598,
|
|
"train_samples_per_second": 25.025,
|
|
"train_steps_per_second": 0.391
|
|
} |