lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-ift/v1.4/ifeval/results_2024-03-13T20-27-54.934967.json with huggingface_hub
dfd9a4b verified
raw
history blame
2.51 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 2771191.064320888,
"end_time": 2771979.675093506,
"total_evaluation_time_secondes": "788.6107726180926",
"model_name": "HuggingFaceH4/zephyr-7b-beta-ift",
"model_sha": "0a50b8076f15d8735364b82bcc234a142998519a",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.23475046210720887,
"prompt_level_strict_acc_stderr": 0.01823928821343378,
"inst_level_strict_acc": 0.3609112709832134,
"inst_level_strict_acc_stderr": 0.000523075024048356,
"prompt_level_loose_acc": 0.24399260628465805,
"prompt_level_loose_acc_stderr": 0.018482234430967866,
"inst_level_loose_acc": 0.37410071942446044,
"inst_level_loose_acc_stderr": 0.0005079063982466114
}
},
"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": "1980ab156a87f38f"
},
"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": "4a134c2a3d05f58e"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}