lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/starcoder2-15b-ift/v9.0/ifeval/results_2024-03-10T22-28-10.487979.json with huggingface_hub
e0a2339 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": 3567190.712551267,
"end_time": 3568107.715915767,
"total_evaluation_time_secondes": "917.003364500124",
"model_name": "HuggingFaceH4/starcoder2-15b-ift",
"model_sha": "98df46f74f0c1d9d9c061215f2dac04f231d516a",
"model_dtype": "torch.bfloat16",
"model_size": "30.04 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.23844731977818853,
"prompt_level_strict_acc_stderr": 0.018337888094243953,
"inst_level_strict_acc": 0.3645083932853717,
"inst_level_strict_acc_stderr": 0.0005025728906006933,
"prompt_level_loose_acc": 0.27911275415896486,
"prompt_level_loose_acc_stderr": 0.019303080958497212,
"inst_level_loose_acc": 0.40047961630695444,
"inst_level_loose_acc_stderr": 0.0005132042112416943
}
},
"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": "e69cf6ff7afb9ed5"
},
"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": "33be886acbbf9bb5"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}