Qwen-2.5-7B_Math / train_results.json
Dongwei's picture
Model save
cff3a8c verified
raw
history blame contribute delete
198 Bytes
{
"total_flos": 0.0,
"train_loss": 0.6738471064660976,
"train_runtime": 7514.6892,
"train_samples": 7500,
"train_samples_per_second": 0.998,
"train_steps_per_second": 0.009
}