edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v48.2/ifeval/results_2024-03-05T16-06-47.179537.json with huggingface_hub
072d977 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": 3958412.071709505,
"end_time": 3959228.698943298,
"total_evaluation_time_secondes": "816.6272337930277",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "d3dfe12a63f7651fc8fa033a4fd2f725011a00fb",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.27726432532347506,
"prompt_level_strict_acc_stderr": 0.019263706963479364,
"inst_level_strict_acc": 0.41007194244604317,
"inst_level_strict_acc_stderr": 0.000525693328708648,
"prompt_level_loose_acc": 0.3031423290203327,
"prompt_level_loose_acc_stderr": 0.019778732375985472,
"inst_level_loose_acc": 0.43285371702637887,
"inst_level_loose_acc_stderr": 0.0005239556191081224
}
},
"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": "46932ca113ba6b0c",
"hash_input_tokens": "8b2e0300fbfb70bc",
"hash_cont_tokens": "03d85f64a29cf153"
},
"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": "8ed52f7b74eb0590",
"hash_input_tokens": "9f4b7e9e7ff95d4a",
"hash_cont_tokens": "14177e0ae9548c24"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}