lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-dpo/v0.2.5/ifeval/results_2024-03-14T18-01-32.182660.json with huggingface_hub
8f343ec verified
raw
history blame
2.5 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 642252.192839565,
"end_time": 642998.038669202,
"total_evaluation_time_secondes": "745.8458296370227",
"model_name": "HuggingFaceH4/zephyr-7b-beta-dpo",
"model_sha": "ef5ae3104d45d8e26a3bb760a5b46a89c41e564c",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.43807763401109057,
"prompt_level_strict_acc_stderr": 0.021350931135490935,
"inst_level_strict_acc": 0.5515587529976019,
"inst_level_strict_acc_stderr": 0.0005426849637643184,
"prompt_level_loose_acc": 0.512014787430684,
"prompt_level_loose_acc_stderr": 0.021510361193439093,
"inst_level_loose_acc": 0.617505995203837,
"inst_level_loose_acc_stderr": 0.0005277813201969411
}
},
"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": "6dece37405c5fda1"
},
"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": "466db76df159abca"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}