Files
oh-dcft-v3.1-llama-3.1-nemo…/train_results.json
ModelHub XC 807505246e 初始化项目,由ModelHub XC社区提供模型
Model: mlfoundations-dev/oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen
Source: Original Platform
2026-07-17 05:29:06 +08:00

8 lines
220 B
JSON

{
"epoch": 2.9993269015032533,
"total_flos": 3503854586953728.0,
"train_loss": 0.5125751896649332,
"train_runtime": 89473.4361,
"train_samples_per_second": 9.562,
"train_steps_per_second": 0.075
}