Spaces:
Sleeping
Sleeping
| { | |
| "average_CPS": 16.729891099999996, | |
| "config": { | |
| "model_name": "Qwen/Qwen2.5-32B-Instruct", | |
| "num_fewshot": "0", | |
| "batch_size": 1, | |
| "LANG": "EN", | |
| "model": "Qwen/Qwen2.5-32B-Instruct", | |
| "base_model": "Qwen2ForCausalLM", | |
| "revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd", | |
| "submitted_time": "2024-09-17 04:17:55+00:00", | |
| "num_params_billion": 32.763876352, | |
| "language": "en" | |
| }, | |
| "tasks": { | |
| "NER": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 38.04, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 30.680000000000003, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 29.64, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 32.78666666666667, | |
| "best_prompt": 38.04, | |
| "prompt_id": "p1", | |
| "CPS": 36.041632, | |
| "is_dummy": false, | |
| "std_accuracy": 4.5791411130618505 | |
| }, | |
| "RE": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 47.339999999999996, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 46.489999999999995, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 45.910000000000004, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 46.57999999999999, | |
| "best_prompt": 47.339999999999996, | |
| "prompt_id": "p1", | |
| "CPS": 46.98021599999999, | |
| "is_dummy": false, | |
| "std_accuracy": 0.7192357054540571 | |
| }, | |
| "RML": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.05, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 0.5700000000000001, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 0.15500000000000003, | |
| "best_prompt": 0.5700000000000001, | |
| "prompt_id": "p2", | |
| "CPS": 0.5676345, | |
| "is_dummy": false, | |
| "std_accuracy": 0.27766886753829645 | |
| }, | |
| "DIA": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 0.06, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 0.015, | |
| "best_prompt": 0.06, | |
| "prompt_id": "p3", | |
| "CPS": 0.059973, | |
| "is_dummy": false, | |
| "std_accuracy": 0.03 | |
| }, | |
| "HIS": { | |
| "prompts": [ | |
| { | |
| "prompt": "p1", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p2", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| }, | |
| { | |
| "prompt": "p3", | |
| "metric": "f1", | |
| "value": 0.0, | |
| "stderr": 0.0 | |
| } | |
| ], | |
| "average_accuracy": 0.0, | |
| "best_prompt": 0.0, | |
| "prompt_id": "p1", | |
| "CPS": 0.0, | |
| "is_dummy": false, | |
| "std_accuracy": 0.0 | |
| } | |
| } | |
| } |