Spaces:
Sleeping
Sleeping
| { | |
| "average_CPS": 43.527679133333336, | |
| "config": { | |
| "model_name": "Qwen/Qwen2.5-14B-Instruct-1M", | |
| "num_fewshot": "10", | |
| "batch_size": 1, | |
| "LANG": "IT", | |
| "model": "Qwen/Qwen2.5-14B-Instruct-1M", | |
| "base_model": "Qwen2ForCausalLM", | |
| "revision": "620fad32de7bdd2293b3d99b39eba2fe63e97438", | |
| "submitted_time": "2025-01-23 13:23:24+00:00", | |
| "num_params_billion": 14.770033664, | |
| "language": "en" | |
| }, | |
| "tasks": { | |
| "NER": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 67.19000000000001, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 63.27, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 66.61, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 65.69, | |
| "best_prompt": 67.19000000000001, | |
| "prompt_id": "p1", | |
| "CPS": 66.18215000000001, | |
| "is_dummy": false, | |
| "std_accuracy": 2.1157504578754107 | |
| }, | |
| "RE": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 57.67, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 59.98, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 60.92999999999999, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 59.526666666666664, | |
| "best_prompt": 60.92999999999999, | |
| "prompt_id": "p3", | |
| "CPS": 60.07494899999999, | |
| "is_dummy": false, | |
| "std_accuracy": 1.6766136505865978 | |
| }, | |
| "RML": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 11.110000000000001, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 15.989999999999998, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 19.6, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 15.566666666666668, | |
| "best_prompt": 19.6, | |
| "prompt_id": "p3", | |
| "CPS": 18.80946666666667, | |
| "is_dummy": false, | |
| "std_accuracy": 4.260801958943097 | |
| }, | |
| "DIA": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 44.07, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 13.28, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 17.53, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 24.959999999999997, | |
| "best_prompt": 44.07, | |
| "prompt_id": "p1", | |
| "CPS": 35.648223, | |
| "is_dummy": false, | |
| "std_accuracy": 16.68561356378602 | |
| }, | |
| "HIS": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 8.17, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 51.03, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 10.96, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 23.386666666666667, | |
| "best_prompt": 51.03, | |
| "prompt_id": "p2", | |
| "CPS": 36.923607000000004, | |
| "is_dummy": false, | |
| "std_accuracy": 23.980438555900797 | |
| } | |
| } | |
| } |