Qwen2.5-1.5B-Instruct_Short_CoT / train_results.json
TaiGary's picture
Add files using upload-large-folder tool
b42204c verified
raw
history blame contribute delete
202 Bytes
{
"epoch": 2.0,
"total_flos": 7302035079168.0,
"train_loss": 0.08638812355909073,
"train_runtime": 520.9989,
"train_samples_per_second": 20.457,
"train_steps_per_second": 1.282
}