lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-dpo/v0.2/ifeval/results_2024-03-02T19-27-03.867210.json with huggingface_hub
6158947 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": 6409288.883341623,
"end_time": 6410067.602640901,
"total_evaluation_time_secondes": "778.719299278222",
"model_name": "HuggingFaceH4/zephyr-7b-beta-dpo",
"model_sha": "43385469db5293505cceda2de19aef5fde21fca7",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.4214417744916821,
"prompt_level_strict_acc_stderr": 0.021249340085831084,
"inst_level_strict_acc": 0.5479616306954437,
"inst_level_strict_acc_stderr": 0.0005093337142728565,
"prompt_level_loose_acc": 0.48428835489833644,
"prompt_level_loose_acc_stderr": 0.021505948540061583,
"inst_level_loose_acc": 0.6031175059952039,
"inst_level_loose_acc_stderr": 0.0005171817821954635
}
},
"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": "ee0b09959568d62b"
},
"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": "64366b53211bc573"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}