lewtun's picture
lewtun HF staff
Upload eval_results/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/main/ifeval/results_2024-03-02T19-51-36.280411.json with huggingface_hub
3813b87 verified
raw
history blame
2.49 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 354992.033872076,
"end_time": 359731.094498258,
"total_evaluation_time_secondes": "4739.060626182007",
"model_name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"model_sha": "ba6df46252dff6f3978ed416fd95523a3aadb554",
"model_dtype": "torch.bfloat16",
"model_size": "87.49 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.5526802218114603,
"prompt_level_strict_acc_stderr": 0.021396815020425963,
"inst_level_strict_acc": 0.6426858513189448,
"inst_level_strict_acc_stderr": 0.000531251622637765,
"prompt_level_loose_acc": 0.5933456561922366,
"prompt_level_loose_acc_stderr": 0.021138283177336348,
"inst_level_loose_acc": 0.6762589928057554,
"inst_level_loose_acc_stderr": 0.000520801206074086
}
},
"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": "7ea7bf2a8edba8f4",
"hash_input_tokens": "cbf56a3804371c84",
"hash_cont_tokens": "64b9e3795a8a9298"
},
"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": "e8f96928ae2b5d8c",
"hash_cont_tokens": "807448eb1596b3de"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}