lewtun's picture
lewtun HF staff
Upload eval_results/databricks/dbrx-instruct/main/ifeval/results_2024-04-25T16-10-40.919095.json with huggingface_hub
f468030 verified
raw
history blame
3.02 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 3219024.946441267,
"end_time": 3231970.235250305,
"total_evaluation_time_secondes": "12945.288809037767",
"model_name": "databricks/dbrx-instruct",
"model_sha": "c0a9245908c187da8f43a81e538e67ff360904ea",
"model_dtype": "torch.bfloat16",
"model_size": "245.12 GB",
"config": null
},
"results": {
"extended|ifeval|0": {
"prompt_level_strict_acc": 0.48428835489833644,
"prompt_level_strict_acc_stderr": 0.02150594854006157,
"inst_level_strict_acc": 0.6079136690647482,
"inst_level_strict_acc_stderr": 0.0005089278370405485,
"prompt_level_loose_acc": 0.5249537892791127,
"prompt_level_loose_acc_stderr": 0.021489761058967348,
"inst_level_loose_acc": 0.6498800959232613,
"inst_level_loose_acc_stderr": 0.0004936512806223921
},
"all": {
"prompt_level_strict_acc": 0.48428835489833644,
"prompt_level_strict_acc_stderr": 0.02150594854006157,
"inst_level_strict_acc": 0.6079136690647482,
"inst_level_strict_acc_stderr": 0.0005089278370405485,
"prompt_level_loose_acc": 0.5249537892791127,
"prompt_level_loose_acc_stderr": 0.021489761058967348,
"inst_level_loose_acc": 0.6498800959232613,
"inst_level_loose_acc_stderr": 0.0004936512806223921
}
},
"versions": {
"extended|ifeval|0": 0
},
"config_tasks": {
"extended|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": [
"extended"
],
"original_num_docs": 541,
"effective_num_docs": 541,
"trust_dataset": null,
"must_remove_duplicate_docs": null
}
},
"summary_tasks": {
"extended|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "6a2c6e35df691ba3",
"hash_input_tokens": "c3c193f562a8265f",
"hash_cont_tokens": "6887b4d23cd5c2c4"
},
"truncated": 541,
"non_truncated": 0,
"padded": 0,
"non_padded": 541,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "ea046ab2c6fc5928",
"hash_full_prompts": "853afd6c0bbf0c6f",
"hash_input_tokens": "ead3df73a9b98053",
"hash_cont_tokens": "9947837007544e61"
},
"truncated": 541,
"non_truncated": 0,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}