lewtun's picture
lewtun HF staff
Upload eval_results/lewtun/zephyr-2b-gemma-sft-mix1/main/ifeval/results_2024-03-06T12-28-46.267773.json with huggingface_hub
f0213db 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": 1678847.593417615,
"end_time": 1679497.009577381,
"total_evaluation_time_secondes": "649.4161597660277",
"model_name": "lewtun/zephyr-2b-gemma-sft-mix1",
"model_sha": "ff58fa5d9a1404aa0ee18259c595d0a4aae5a6ec",
"model_dtype": "torch.bfloat16",
"model_size": "4.68 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.20702402957486138,
"prompt_level_strict_acc_stderr": 0.017435865587996542,
"inst_level_strict_acc": 0.3441247002398082,
"inst_level_strict_acc_stderr": 0.000498898092426453,
"prompt_level_loose_acc": 0.2199630314232902,
"prompt_level_loose_acc_stderr": 0.017825247192217102,
"inst_level_loose_acc": 0.35851318944844124,
"inst_level_loose_acc_stderr": 0.0004995723759459173
}
},
"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": "7ea7bf2a8edba8f4",
"hash_input_tokens": "89df3fff41e770ad",
"hash_cont_tokens": "4d86cc0ccd10b708"
},
"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": "917957472cc73e8e",
"hash_cont_tokens": "13c21260636b7311"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}