lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-dpo/v0.2.6/ifeval/results_2024-03-14T20-36-49.238793.json with huggingface_hub
46ddb36 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": 2951725.775990107,
"end_time": 2952563.210285495,
"total_evaluation_time_secondes": "837.4342953879386",
"model_name": "HuggingFaceH4/zephyr-7b-beta-dpo",
"model_sha": "fbc77de22eab5551456609294192795860b093fd",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.4121996303142329,
"prompt_level_strict_acc_stderr": 0.021182238151733205,
"inst_level_strict_acc": 0.5215827338129496,
"inst_level_strict_acc_stderr": 0.0005603943573577837,
"prompt_level_loose_acc": 0.45286506469500926,
"prompt_level_loose_acc_stderr": 0.02142075394952956,
"inst_level_loose_acc": 0.5671462829736211,
"inst_level_loose_acc_stderr": 0.0005451188242360516
}
},
"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": "46932ca113ba6b0c",
"hash_input_tokens": "8b2e0300fbfb70bc",
"hash_cont_tokens": "eb061308289ed12a"
},
"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": "5f0890d83e3c1487"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}