Qwen2.5-0.5B-Instruct / train_results.json
YangZhoumill's picture
Model save
b9b59cc verified
raw
history blame contribute delete
215 Bytes
{
"total_flos": 4.211382991139635e+16,
"train_loss": 0.7568846257527669,
"train_runtime": 323.9308,
"train_samples": 9308,
"train_samples_per_second": 3.704,
"train_steps_per_second": 0.463
}