edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v41.26/ifeval/results_2024-03-12T10-53-19.387627.json with huggingface_hub
3c54f95 verified
raw
history blame
2.48 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 3641696.492103449,
"end_time": 3642450.150185744,
"total_evaluation_time_secondes": "753.6580822947435",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "b1e3e3b4929d32d41d7b5fb1d73024ad5ba5f850",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.37153419593345655,
"prompt_level_strict_acc_stderr": 0.020794253888707544,
"inst_level_strict_acc": 0.49160671462829736,
"inst_level_strict_acc_stderr": 0.000556665540938584,
"prompt_level_loose_acc": 0.41035120147874304,
"prompt_level_loose_acc_stderr": 0.02116789554279182,
"inst_level_loose_acc": 0.5323741007194245,
"inst_level_loose_acc_stderr": 0.0005431871796718605
}
},
"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": "46932ca113ba6b0c",
"hash_input_tokens": "8b2e0300fbfb70bc",
"hash_cont_tokens": "33d17430cf179a81"
},
"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": "137a4fa6e9c945f8"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}