Spaces:
Sleeping
Sleeping
| { | |
| "average_CPS": 43.13491793333334, | |
| "config": { | |
| "model_name": "Qwen/Qwen2.5-14B-Instruct-1M", | |
| "num_fewshot": "10", | |
| "batch_size": 1, | |
| "LANG": "EN", | |
| "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": 60.91, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 56.46, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 62.43, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 59.93333333333334, | |
| "best_prompt": 62.43, | |
| "prompt_id": "p3", | |
| "CPS": 60.871331000000005, | |
| "is_dummy": false, | |
| "std_accuracy": 3.1025204807274562 | |
| }, | |
| "RE": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 63.32, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 60.25, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 61.33, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 61.633333333333326, | |
| "best_prompt": 63.32, | |
| "prompt_id": "p1", | |
| "CPS": 62.25200266666666, | |
| "is_dummy": false, | |
| "std_accuracy": 1.5573160672558843 | |
| }, | |
| "RML": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 21.29, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 32.22, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 31.78, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 28.429999999999996, | |
| "best_prompt": 32.22, | |
| "prompt_id": "p2", | |
| "CPS": 30.998862, | |
| "is_dummy": false, | |
| "std_accuracy": 6.1873338361526935 | |
| }, | |
| "DIA": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 30.73, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 11.37, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 7.64, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 16.580000000000002, | |
| "best_prompt": 30.73, | |
| "prompt_id": "p1", | |
| "CPS": 26.381705, | |
| "is_dummy": false, | |
| "std_accuracy": 12.395366069624568 | |
| }, | |
| "HIS": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 12.44, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 44.29, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 14.37, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 23.7, | |
| "best_prompt": 44.29, | |
| "prompt_id": "p2", | |
| "CPS": 35.170689, | |
| "is_dummy": false, | |
| "std_accuracy": 17.857555823796268 | |
| } | |
| } | |
| } |