Qwen2.5-1.5B-hl-baseline-v26 / train_results.json
Muennighoff's picture
Model save
24219b4 verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 19.090027208828705,
"train_runtime": 110532.8464,
"train_samples": 1200000,
"train_samples_per_second": 12.97,
"train_steps_per_second": 0.014
}