lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-dpo/v0.2.4/ifeval/results_2024-03-13T22-20-56.658219.json with huggingface_hub
8acb1a4 verified
raw
history blame
2.5 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 451812.658222179,
"end_time": 452659.542926409,
"total_evaluation_time_secondes": "846.884704230004",
"model_name": "HuggingFaceH4/zephyr-7b-beta-dpo",
"model_sha": "09b84bad4c12c22de5d983565d4f6f37b51c2f67",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.32162661737523107,
"prompt_level_strict_acc_stderr": 0.02010080781364547,
"inst_level_strict_acc": 0.4364508393285372,
"inst_level_strict_acc_stderr": 0.0005336997161512694,
"prompt_level_loose_acc": 0.3659889094269871,
"prompt_level_loose_acc_stderr": 0.02072934168450661,
"inst_level_loose_acc": 0.4724220623501199,
"inst_level_loose_acc_stderr": 0.0005507484759892764
}
},
"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,
"trust_dataset": null
}
},
"summary_tasks": {
"custom|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "7ea7bf2a8edba8f4",
"hash_input_tokens": "1674fbca8428210a",
"hash_cont_tokens": "eba52e78af91394b"
},
"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": "45f8422f6ad2da79",
"hash_input_tokens": "211ca010114f2960",
"hash_cont_tokens": "ab04c35ea38132a7"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}