Files
openthoughts3_100k_qwen25_1…/train_results.json

8 lines
203 B
JSON
Raw Normal View History

{
"epoch": 7.0,
"total_flos": 9969287656374272.0,
"train_loss": 1.0345919296651762,
"train_runtime": 97654.46,
"train_samples_per_second": 7.168,
"train_steps_per_second": 0.028
}