Qwen-2.5-7B_Base_Math_smalllr / all_results.json
Dongwei's picture
Model save
e36cb67 verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 0.00010928502410594652,
"train_runtime": 12024.2367,
"train_samples": 7500,
"train_samples_per_second": 0.624,
"train_steps_per_second": 0.006
}