zijianh
/

DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-medium-0_05-new

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-medium-0_05-new

File size: 171 Bytes

2005bcf

{
    "eval_loss": 0.19285601377487183,
    "eval_runtime": 5347.8013,
    "eval_samples": 5000,
    "eval_samples_per_second": 0.935,
    "eval_steps_per_second": 0.008
}