edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v48.100/ifeval/results_2024-03-13T08-57-15.932368.json with huggingface_hub
c343eae 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": 403598.243946091,
"end_time": 404435.589480715,
"total_evaluation_time_secondes": "837.345534624008",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "1469be99e9c768830265c2bf2c6959849d96d79c",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.2476894639556377,
"prompt_level_strict_acc_stderr": 0.018576139285185193,
"inst_level_strict_acc": 0.36930455635491605,
"inst_level_strict_acc_stderr": 0.0005224013671745301,
"prompt_level_loose_acc": 0.30129390018484287,
"prompt_level_loose_acc_stderr": 0.019744473483514307,
"inst_level_loose_acc": 0.4196642685851319,
"inst_level_loose_acc_stderr": 0.0005392635515542589
}
},
"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": "dcb7421156d2a1d0"
},
"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": "a48e0dd994aee004"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}