18 lines
1.5 KiB
Plaintext
18 lines
1.5 KiB
Plaintext
|
|
Evaluation Summary for
|
||
|
|
codingmonster1234/Qwen3-4B-Instruct-2507-Chess-Reasonin
|
||
|
|
g-SFT-v2
|
||
|
|
╔══════════╤══════════════════════════════╤═══════════╗
|
||
|
|
║ Category │ Metric │ Value ║
|
||
|
|
╟──────────┼──────────────────────────────┼───────────╢
|
||
|
|
║ eval │ format_accuracy │ 0.9510 ║
|
||
|
|
║ eval │ legal_move_accuracy │ 0.9080 ║
|
||
|
|
║ eval │ valid_move_notation_accuracy │ 0.9080 ║
|
||
|
|
║ eval │ perfect_move_accuracy │ 0.2710 ║
|
||
|
|
║ eval │ avg_eval_diff │ 1746.4540 ║
|
||
|
|
║ eval │ avg_length_penalty │ 0.0106 ║
|
||
|
|
║ eval │ avg_final_reward │ 0.1882 ║
|
||
|
|
║ eval │ avg_eval_reward │ 0.1983 ║
|
||
|
|
║ eval │ avg_elo_solved │ 1167.1661 ║
|
||
|
|
╟──────────┼──────────────────────────────┼───────────╢
|
||
|
|
║ │ │ ║
|
||
|
|
╚══════════╧══════════════════════════════╧═══════════╝
|