Qwen2.5-1.5B-hl-false-v16 / train_results.json
Muennighoff's picture
Model save
65e4475 verified
raw
history blame contribute delete
207 Bytes
{
"total_flos": 0.0,
"train_loss": 1.3027437901511778e-05,
"train_runtime": 176.4542,
"train_samples": 1200000,
"train_samples_per_second": 8124.487,
"train_steps_per_second": 9.068
}