| { |
| "problems": 256, |
| "samples": 512, |
| "acc": 0.279296875, |
| "acc_se": 0.02452997910642615, |
| "cut_share": 0.712890625, |
| "mean_tokens": 27429.751953125, |
| "closed_share": 0.3125, |
| "p_finish": 0.287109375, |
| "p_correct_given_finished": 0.9591836734693877, |
| "p_correct_given_cut": 0.005479452054794521, |
| "no_answer_finished_share": 0.0, |
| "loop_end_share_of_cut": 0.5945205479452055, |
| "tail_dup8_cut_mean": 0.5797747945205479, |
| "median_tokens_correct": 12548, |
| "by_source": { |
| "gsm8k": { |
| "problems": 128, |
| "samples": 256, |
| "acc": 0.359375, |
| "acc_se": 0.03676172043807157, |
| "cut_share": 0.62109375, |
| "mean_tokens": 25482.21484375 |
| }, |
| "math": { |
| "problems": 128, |
| "samples": 256, |
| "acc": 0.19921875, |
| "acc_se": 0.03104749532145433, |
| "cut_share": 0.8046875, |
| "mean_tokens": 29377.2890625 |
| } |
| }, |
| "run": { |
| "name": "dev/base+temp1.0", |
| "model": "base", |
| "data": "dev256", |
| "n": 2, |
| "shards": 1, |
| "est": 15, |
| "set": [ |
| "temperature=1.0" |
| ] |
| }, |
| "sampling": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 20, |
| "presence_penalty": 1.5, |
| "repetition_penalty": 1.0, |
| "max_tokens": 32768, |
| "thinking": true |
| }, |
| "edit_note": null, |
| "tokens_total": 14044033, |
| "gpu_seconds": 2392, |
| "tok_per_s_per_gpu": 6019 |
| } |
