lewtun's picture
lewtun HF staff
Upload eval_results/NousResearch/Nous-Hermes-2-Yi-34B/main/ifeval/results_2024-03-05T00-32-10.317065.json with huggingface_hub
867496e 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": 4234089.961510135,
"end_time": 4248689.822375883,
"total_evaluation_time_secondes": "14599.860865748487",
"model_name": "NousResearch/Nous-Hermes-2-Yi-34B",
"model_sha": "fcb0a8847e76aea14aba9aa44009d4418ad7c18f",
"model_dtype": "torch.bfloat16",
"model_size": "64.17 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.37153419593345655,
"prompt_level_strict_acc_stderr": 0.020794253888707544,
"inst_level_strict_acc": 0.5011990407673861,
"inst_level_strict_acc_stderr": 0.0005421591980743841,
"prompt_level_loose_acc": 0.3900184842883549,
"prompt_level_loose_acc_stderr": 0.020989594697345362,
"inst_level_loose_acc": 0.5239808153477218,
"inst_level_loose_acc_stderr": 0.0005308672441756221
}
},
"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": "f395f74d675b8fad",
"hash_cont_tokens": "5240805486e81aa1"
},
"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": "498f547bcc343a73",
"hash_cont_tokens": "11c48a35c359d017"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}