edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v43.30/ifeval/results_2024-03-08T13-34-32.963540.json with huggingface_hub
25ea387 verified
raw
history blame
2.47 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 56446.071808607,
"end_time": 57218.130240875,
"total_evaluation_time_secondes": "772.0584322680006",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "2b5acc48d25cbfda90e24193dc80be9e50d58880",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.31053604436229204,
"prompt_level_strict_acc_stderr": 0.019912001290591255,
"inst_level_strict_acc": 0.45323741007194246,
"inst_level_strict_acc_stderr": 0.0005191045473570217,
"prompt_level_loose_acc": 0.3456561922365989,
"prompt_level_loose_acc_stderr": 0.020465779432682563,
"inst_level_loose_acc": 0.486810551558753,
"inst_level_loose_acc_stderr": 0.0005150337383623712
}
},
"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": "ac5c265d406be840"
},
"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": "faaca64694a372ff"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}