edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v41.5/ifeval/results_2024-03-08T13-53-30.040622.json with huggingface_hub
dd5f8a8 verified
raw
history blame
2.48 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 2309218.520432824,
"end_time": 2310011.123780343,
"total_evaluation_time_secondes": "792.6033475194126",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "2b0260b650bbd0ab4e39f203d6698dd6c0d9f9d9",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.22365988909426987,
"prompt_level_strict_acc_stderr": 0.017931771054658378,
"inst_level_strict_acc": 0.34772182254196643,
"inst_level_strict_acc_stderr": 0.0004993477181474577,
"prompt_level_loose_acc": 0.28650646950092423,
"prompt_level_loose_acc_stderr": 0.019456528583211702,
"inst_level_loose_acc": 0.4064748201438849,
"inst_level_loose_acc_stderr": 0.0005320421942355588
}
},
"versions": {
"custom|ifeval|0": 0
},
"config_tasks": {
"custom|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": [
"custom"
],
"original_num_docs": 541,
"effective_num_docs": 541
}
},
"summary_tasks": {
"custom|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "46932ca113ba6b0c",
"hash_input_tokens": "8b2e0300fbfb70bc",
"hash_cont_tokens": "2065f9e7f6bb346f"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "ea046ab2c6fc5928",
"hash_full_prompts": "8ed52f7b74eb0590",
"hash_input_tokens": "9f4b7e9e7ff95d4a",
"hash_cont_tokens": "cf630d9ecbce6014"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}