lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/starcoder2-15b-ift/v15.0/ifeval/results_2024-03-10T19-29-42.902201.json with huggingface_hub
7ddc755 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": 282649.968869656,
"end_time": 283518.52765483,
"total_evaluation_time_secondes": "868.558785174042",
"model_name": "HuggingFaceH4/starcoder2-15b-ift",
"model_sha": "76a4a3b275d5f110632609d9f9e219c79462c73e",
"model_dtype": "torch.bfloat16",
"model_size": "30.04 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.19963031423290203,
"prompt_level_strict_acc_stderr": 0.01720131626488992,
"inst_level_strict_acc": 0.31534772182254195,
"inst_level_strict_acc_stderr": 0.0004894833785085218,
"prompt_level_loose_acc": 0.2365988909426987,
"prompt_level_loose_acc_stderr": 0.018288827582625667,
"inst_level_loose_acc": 0.35251798561151076,
"inst_level_loose_acc_stderr": 0.0004995964911835686
}
},
"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": "b7db55e6d2dfe73f"
},
"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": "d709cbe7d88bb41c"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}