open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-4B-Chat /main /ifeval /results_2024-03-02T15-33-34.597523.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-4B-Chat/main/ifeval/results_2024-03-02T15-33-34.597523.json with huggingface_hub
8d881bb verified
raw
history blame
2.47 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 6395487.916168673,
"end_time": 6396053.088844547,
"total_evaluation_time_secondes": "565.1726758740842",
"model_name": "Qwen/Qwen1.5-4B-Chat",
"model_sha": "ef715c26c82dd2d04634101d5fb9855ff3f45bc9",
"model_dtype": "torch.bfloat16",
"model_size": "7.98 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.25693160813308685,
"prompt_level_strict_acc_stderr": 0.018802962575636843,
"inst_level_strict_acc": 0.3657074340527578,
"inst_level_strict_acc_stderr": 0.0005244898147711835,
"prompt_level_loose_acc": 0.2920517560073937,
"prompt_level_loose_acc_stderr": 0.019567429846009426,
"inst_level_loose_acc": 0.407673860911271,
"inst_level_loose_acc_stderr": 0.0005331833682419662
}
},
"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": "1d8bccd45ca3707b",
"hash_input_tokens": "4aede348bfb0e38d",
"hash_cont_tokens": "342543e5ee47db51"
},
"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": "41a5572cc1263dc7",
"hash_input_tokens": "dc284e5de619e6a7",
"hash_cont_tokens": "c11fd9301cdb6887"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}