Qwen2.5-Math-7B-Instruct-SFT / all_results.json
edbeeching's picture
edbeeching HF Staff
Model save
bbdcdf2 verified
raw
history blame contribute delete
218 Bytes
{
"total_flos": 6.2367671592178156e+19,
"train_loss": 1.1144484827174477,
"train_runtime": 39508.3376,
"train_samples": 93733,
"train_samples_per_second": 1.304,
"train_steps_per_second": 0.01
}