Model: huseyinatahaninan/appworld_distillation_sft_v2-SFT-Qwen3-4B-Instruct-2507 Source: Original Platform
12 lines
347 B
JSON
12 lines
347 B
JSON
{
|
|
"epoch": 30.0,
|
|
"eval_loss": 0.7485920190811157,
|
|
"eval_runtime": 7.2071,
|
|
"eval_samples_per_second": 4.856,
|
|
"eval_steps_per_second": 0.694,
|
|
"total_flos": 1.0166485230865613e+18,
|
|
"train_loss": 0.5314400238295396,
|
|
"train_runtime": 1496.8474,
|
|
"train_samples_per_second": 1.022,
|
|
"train_steps_per_second": 0.04
|
|
} |