open-r1-eval-leaderboard
/
eval_results
/abhishek
/autotrain-llama3-oh-sft-v0-2
/main
/ifeval
/results_2024-05-03T12-35-08.809758.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 1828301.892495373, | |
"end_time": 1833735.67522596, | |
"total_evaluation_time_secondes": "5433.78273058706", | |
"model_name": "abhishek/autotrain-llama3-oh-sft-v0-2", | |
"model_sha": "14e07850d3e1ee35f5788270ab514c2e3b3821bf", | |
"model_dtype": "torch.float16", | |
"model_size": "131.73 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.7190388170055453, | |
"prompt_level_strict_acc_stderr": 0.019342047683777005, | |
"inst_level_strict_acc": 0.7925659472422062, | |
"inst_level_strict_acc_stderr": 0.0004413743052536302, | |
"prompt_level_loose_acc": 0.7504621072088724, | |
"prompt_level_loose_acc_stderr": 0.01862240450980586, | |
"inst_level_loose_acc": 0.815347721822542, | |
"inst_level_loose_acc_stderr": 0.0004260985348952384 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.7190388170055453, | |
"prompt_level_strict_acc_stderr": 0.019342047683777005, | |
"inst_level_strict_acc": 0.7925659472422062, | |
"inst_level_strict_acc_stderr": 0.0004413743052536302, | |
"prompt_level_loose_acc": 0.7504621072088724, | |
"prompt_level_loose_acc_stderr": 0.01862240450980586, | |
"inst_level_loose_acc": 0.815347721822542, | |
"inst_level_loose_acc_stderr": 0.0004260985348952384 | |
} | |
}, | |
"versions": { | |
"extended|ifeval|0": 0 | |
}, | |
"config_tasks": { | |
"extended|ifeval": { | |
"name": "ifeval", | |
"prompt_function": "ifeval_prompt", | |
"hf_repo": "wis-k/instruction-following-eval", | |
"hf_subset": "default", | |
"metric": [ | |
"ifeval_metric" | |
], | |
"hf_avail_splits": [ | |
"train" | |
], | |
"evaluation_splits": [ | |
"train" | |
], | |
"few_shots_split": "train", | |
"few_shots_select": "random_sampling", | |
"generation_size": 1280, | |
"stop_sequence": [], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"extended" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541, | |
"trust_dataset": null, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"extended|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "7ea7bf2a8edba8f4", | |
"hash_input_tokens": "16c7deaf8d8cfab4", | |
"hash_cont_tokens": "eab235a27e73dbcd" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 115, | |
"non_padded": 426, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "45f8422f6ad2da79", | |
"hash_input_tokens": "91a30a216e4e8fc8", | |
"hash_cont_tokens": "f161624aec3dfa92" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 115, | |
"non_padded": 426, | |
"num_truncated_few_shots": 0 | |
} | |
} |