NuminaMath-72B-TIR / train_results.json
lewtun's picture
lewtun HF staff
Add AI-MO/qwen2-72b-sft-aimo_v03.00 checkpoint
7682df3 verified
raw
history blame contribute delete
233 Bytes
{
"epoch": 4.0,
"total_flos": 2680278636036096.0,
"train_loss": 0.20304497943459596,
"train_runtime": 21214.9362,
"train_samples": 72441,
"train_samples_per_second": 4.806,
"train_steps_per_second": 0.15
}