Spaces:
Sleeping
Sleeping
| { | |
| "average_CPS": 61.436353666666676, | |
| "config": { | |
| "model_name": "Qwen/Qwen2.5-14B-Instruct-1M", | |
| "num_fewshot": "10", | |
| "batch_size": 1, | |
| "LANG": "SL", | |
| "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": 64.67, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 61.78, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 64.67, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 63.70666666666667, | |
| "best_prompt": 64.67, | |
| "prompt_id": "p1", | |
| "CPS": 64.04701233333334, | |
| "is_dummy": false, | |
| "std_accuracy": 1.6685422779580188 | |
| }, | |
| "RE": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 59.489999999999995, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 57.82000000000001, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 57.809999999999995, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 58.373333333333335, | |
| "best_prompt": 59.489999999999995, | |
| "prompt_id": "p1", | |
| "CPS": 58.825695, | |
| "is_dummy": false, | |
| "std_accuracy": 0.967074626558533 | |
| }, | |
| "RML": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": null, | |
| "std_accuracy": null, | |
| "best_prompt": null, | |
| "prompt_id": null, | |
| "CPS": null, | |
| "is_dummy": true | |
| }, | |
| "HIS": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": null, | |
| "std_accuracy": null, | |
| "best_prompt": null, | |
| "prompt_id": null, | |
| "CPS": null, | |
| "is_dummy": true | |
| }, | |
| "DIA": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": null, | |
| "std_accuracy": null, | |
| "best_prompt": null, | |
| "prompt_id": null, | |
| "CPS": null, | |
| "is_dummy": true | |
| } | |
| } | |
| } |