Model: promotion/qwen3-8b-aaai27-p3-ronpo-alpha050_anchor0035_lr7p5e8-s42 Source: Original Platform
9 lines
232 B
JSON
9 lines
232 B
JSON
{
|
|
"epoch": 0.2860548271752086,
|
|
"total_flos": 0.0,
|
|
"train_loss": 0.4220078429910872,
|
|
"train_runtime": 7042.2326,
|
|
"train_samples": 50340,
|
|
"train_samples_per_second": 2.045,
|
|
"train_steps_per_second": 0.128
|
|
} |