zijianh
/

DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-high-0_5-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-high-0_5-new

File size: 169 Bytes

796c834

{
    "eval_loss": 0.25781184434890747,
    "eval_runtime": 5754.34,
    "eval_samples": 5000,
    "eval_samples_per_second": 0.869,
    "eval_steps_per_second": 0.008
}