Qwen2.5-3B-Instruct_Long_CoT / all_results.json
TaiGary's picture
Add files using upload-large-folder tool
f5f8437 verified
raw
history blame contribute delete
342 Bytes
{
"epoch": 2.0,
"eval_loss": 0.3268175721168518,
"eval_runtime": 3.6236,
"eval_samples_per_second": 14.903,
"eval_steps_per_second": 3.864,
"total_flos": 35357291446272.0,
"train_loss": 0.2874097045131786,
"train_runtime": 2068.8682,
"train_samples_per_second": 5.152,
"train_steps_per_second": 0.323
}