Qwen2.5-1.5B-hl-false-v2 / train_results.json
Muennighoff's picture
Model save
e065767 verified
raw
history blame contribute delete
205 Bytes
{
"total_flos": 0.0,
"train_loss": -0.039273733161653585,
"train_runtime": 125060.3323,
"train_samples": 12000,
"train_samples_per_second": 11.463,
"train_steps_per_second": 0.013
}