Qwen2.5-7B-Instruct_Long_CoT / train_results.json
TaiGary's picture
Add files using upload-large-folder tool
8841a78 verified
raw
history blame contribute delete
202 Bytes
{
"epoch": 2.0,
"total_flos": 39377831657472.0,
"train_loss": 0.2224826162912767,
"train_runtime": 4117.8607,
"train_samples_per_second": 2.588,
"train_steps_per_second": 0.324
}