edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/qwen-1.5-1.8b-dpo/v0.13/ifeval/results_2024-03-18T16-40-04.435577.json with huggingface_hub
e9088c8 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": 376451.155473414,
"end_time": 376977.944369032,
"total_evaluation_time_secondes": "526.7888956179959",
"model_name": "HuggingFaceH4/qwen-1.5-1.8b-dpo",
"model_sha": "5e563f9fd85247bd7f626df0a47d7808cbd37450",
"model_dtype": "torch.bfloat16",
"model_size": "3.79 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.21626617375231053,
"prompt_level_strict_acc_stderr": 0.017716654428910118,
"inst_level_strict_acc": 0.33213429256594723,
"inst_level_strict_acc_stderr": 0.0004919006582435243,
"prompt_level_loose_acc": 0.22735674676524953,
"prompt_level_loose_acc_stderr": 0.018036262673640082,
"inst_level_loose_acc": 0.3489208633093525,
"inst_level_loose_acc_stderr": 0.0004949314146536762
}
},
"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": "406f216e2e739d61",
"hash_cont_tokens": "10faac6a842fc30f"
},
"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": "7be1d930c9579e40",
"hash_cont_tokens": "66cb865e57834ad9"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}