lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/starcoder2-15b-dpo/v2.2.4/ifeval/results_2024-03-12T09-17-38.865201.json with huggingface_hub
7c09b1d verified
raw
history blame
2.5 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 4315340.361092552,
"end_time": 4316286.1698945,
"total_evaluation_time_secondes": "945.8088019480929",
"model_name": "HuggingFaceH4/starcoder2-15b-dpo",
"model_sha": "2206b0d03c5b8d3811470b04a49cc59149082bd0",
"model_dtype": "torch.bfloat16",
"model_size": "30.04 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.28835489833641403,
"prompt_level_strict_acc_stderr": 0.0194938903506547,
"inst_level_strict_acc": 0.41606714628297364,
"inst_level_strict_acc_stderr": 0.000527830844269824,
"prompt_level_loose_acc": 0.30868761552680224,
"prompt_level_loose_acc_stderr": 0.019879245251116444,
"inst_level_loose_acc": 0.434052757793765,
"inst_level_loose_acc_stderr": 0.0005387120098493463
}
},
"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,
"trust_dataset": null
}
},
"summary_tasks": {
"custom|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "7ea7bf2a8edba8f4",
"hash_input_tokens": "dc4c9014dffc6917",
"hash_cont_tokens": "0a5981b746f56c98"
},
"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": "5d5e6158af678a01",
"hash_cont_tokens": "88e3ebbb0068e0b4"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}