lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/pythia-70m-orpo/v0.0/ifeval/results_2024-03-28T21-48-27.934433.json with huggingface_hub
3a81546 verified
raw
history blame
3.03 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 277396.414850693,
"end_time": 277583.46162239,
"total_evaluation_time_secondes": "187.04677169700153",
"model_name": "HuggingFaceH4/pythia-70m-orpo",
"model_sha": "c8bf1aaa611b23300a8c3678d0f3d6b9dba2ee85",
"model_dtype": "torch.bfloat16",
"model_size": "138.83 MB",
"config": null
},
"results": {
"extended|ifeval|0": {
"prompt_level_strict_acc": 0.11829944547134935,
"prompt_level_strict_acc_stderr": 0.01389808717670658,
"inst_level_strict_acc": 0.2314148681055156,
"inst_level_strict_acc_stderr": 0.00043540412671258164,
"prompt_level_loose_acc": 0.11829944547134935,
"prompt_level_loose_acc_stderr": 0.01389808717670658,
"inst_level_loose_acc": 0.2314148681055156,
"inst_level_loose_acc_stderr": 0.00043540412671258164
},
"all": {
"prompt_level_strict_acc": 0.11829944547134935,
"prompt_level_strict_acc_stderr": 0.01389808717670658,
"inst_level_strict_acc": 0.2314148681055156,
"inst_level_strict_acc_stderr": 0.00043540412671258164,
"prompt_level_loose_acc": 0.11829944547134935,
"prompt_level_loose_acc_stderr": 0.01389808717670658,
"inst_level_loose_acc": 0.2314148681055156,
"inst_level_loose_acc_stderr": 0.00043540412671258164
}
},
"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": "7ea7bf2a8edba8f4",
"hash_input_tokens": "0fef131547fe066d",
"hash_cont_tokens": "358e25dbb94f82a2"
},
"truncated": 541,
"non_truncated": 0,
"padded": 123,
"non_padded": 418,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "ea046ab2c6fc5928",
"hash_full_prompts": "45f8422f6ad2da79",
"hash_input_tokens": "5d98b4411acadd74",
"hash_cont_tokens": "b0a95b2bd23dd1ea"
},
"truncated": 541,
"non_truncated": 0,
"padded": 123,
"non_padded": 418,
"num_truncated_few_shots": 0
}
}