Model: ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated-masked Source: Original Platform
8 lines
217 B
JSON
8 lines
217 B
JSON
{
|
|
"total_flos": 2054605533544448.0,
|
|
"train_loss": 0.6844859028735806,
|
|
"train_runtime": 36489.0201,
|
|
"train_samples": 936509,
|
|
"train_samples_per_second": 51.331,
|
|
"train_steps_per_second": 0.401
|
|
} |