lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/starcoder2-15b-ift/v5.2/ifeval/results_2024-03-09T00-30-16.478094.json with huggingface_hub
f166949 verified
raw
history blame
2.51 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 1224200.014114546,
"end_time": 1225083.471038793,
"total_evaluation_time_secondes": "883.4569242470898",
"model_name": "HuggingFaceH4/starcoder2-15b-ift",
"model_sha": "76ce023c8237f363cd296616fc98bb76627a7489",
"model_dtype": "torch.bfloat16",
"model_size": "30.04 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.2828096118299446,
"prompt_level_strict_acc_stderr": 0.019380609595892773,
"inst_level_strict_acc": 0.4172661870503597,
"inst_level_strict_acc_stderr": 0.000517506739808199,
"prompt_level_loose_acc": 0.30129390018484287,
"prompt_level_loose_acc_stderr": 0.019744473483514293,
"inst_level_loose_acc": 0.4364508393285372,
"inst_level_loose_acc_stderr": 0.0005126157223052024
}
},
"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": "776adc7c61431ecf"
},
"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": "88b434172506cb39"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}