| { |
| "schema_version": "0.2.2", |
| "evaluation_id": "ifeval/Qwen/Qwen3.6-35B-A3B/1782386605.760545", |
| "evaluation_timestamp": "1782270017", |
| "retrieved_timestamp": "1782386605.760545", |
| "source_metadata": { |
| "source_name": "lm-evaluation-harness", |
| "source_type": "evaluation_run", |
| "source_organization_name": "RedHatAI", |
| "evaluator_relationship": "third_party" |
| }, |
| "eval_library": { |
| "name": "lm_eval", |
| "version": "0.4.13.dev0" |
| }, |
| "model_info": { |
| "name": "Qwen/Qwen3.6-35B-A3B", |
| "id": "Qwen/Qwen3.6-35B-A3B", |
| "developer": "Qwen", |
| "additional_details": { |
| "model_args": "{'model': 'Qwen/Qwen3.6-35B-A3B', 'max_length': 262144, 'base_url': 'http://0.0.0.0:8700/v1/chat/completions', 'num_concurrent': 64, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 1200}", |
| "num_seeds_merged": "3" |
| } |
| }, |
| "evaluation_results": [ |
| { |
| "evaluation_name": "ifeval", |
| "source_data": { |
| "dataset_name": "ifeval", |
| "source_type": "hf_dataset", |
| "hf_repo": "google/IFEval", |
| "hf_split": "train" |
| }, |
| "metric_config": { |
| "evaluation_description": "prompt_level_strict_acc", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.9014171287738755, |
| "details": { |
| "seed_scores": "[0.9020332717190388, 0.9020332717190388, 0.9001848428835489]", |
| "evaluation_timestamps": "[1782272527, 1782274610, 1782270017]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0006161429451632857, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 20.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "ifeval", |
| "source_data": { |
| "dataset_name": "ifeval", |
| "source_type": "hf_dataset", |
| "hf_repo": "google/IFEval", |
| "hf_split": "train" |
| }, |
| "metric_config": { |
| "evaluation_description": "inst_level_strict_acc", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.9308553157474021, |
| "details": { |
| "seed_scores": "[0.9316546762589928, 0.9328537170263789, 0.9280575539568345]", |
| "evaluation_timestamps": "[1782272527, 1782274610, 1782270017]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0014410676560607384, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 20.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "ifeval", |
| "source_data": { |
| "dataset_name": "ifeval", |
| "source_type": "hf_dataset", |
| "hf_repo": "google/IFEval", |
| "hf_split": "train" |
| }, |
| "metric_config": { |
| "evaluation_description": "prompt_level_loose_acc", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.9285274183610598, |
| "details": { |
| "seed_scores": "[0.9279112754158965, 0.933456561922366, 0.9242144177449169]", |
| "evaluation_timestamps": "[1782272527, 1782274610, 1782270017]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.002685704832742256, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 20.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| }, |
| { |
| "evaluation_name": "ifeval", |
| "source_data": { |
| "dataset_name": "ifeval", |
| "source_type": "hf_dataset", |
| "hf_repo": "google/IFEval", |
| "hf_split": "train" |
| }, |
| "metric_config": { |
| "evaluation_description": "inst_level_loose_acc", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.9484412470023981, |
| "details": { |
| "seed_scores": "[0.9484412470023981, 0.9532374100719424, 0.9436450839328537]", |
| "evaluation_timestamps": "[1782272527, 1782274610, 1782270017]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0027690660392787636, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| }, |
| "generation_config": { |
| "generation_args": { |
| "temperature": 1.0, |
| "top_p": 0.95, |
| "top_k": 20.0, |
| "max_tokens": 64000, |
| "max_attempts": 1 |
| }, |
| "additional_details": { |
| "until": "[]", |
| "do_sample": "true", |
| "min_p": "0.0", |
| "seed": "1234", |
| "num_fewshot": "0" |
| } |
| } |
| } |
| ] |
| } |
