edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v48.107/ifeval/results_2024-03-12T23-44-59.878849.json with huggingface_hub
d2c0a82 verified
raw
history blame
2.47 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 518774.412506751,
"end_time": 519537.491138422,
"total_evaluation_time_secondes": "763.0786316709709",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "b670351302b0157effcaecdb0100e7ea8348e2ce",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.3678373382624769,
"prompt_level_strict_acc_stderr": 0.02075130655602968,
"inst_level_strict_acc": 0.4940047961630695,
"inst_level_strict_acc_stderr": 0.0005271291485296549,
"prompt_level_loose_acc": 0.4288354898336414,
"prompt_level_loose_acc_stderr": 0.021297522569050743,
"inst_level_loose_acc": 0.5587529976019184,
"inst_level_loose_acc_stderr": 0.0005180597280386676
}
},
"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": "6713088b78dd93b8"
},
"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": "38e613a3ca8b30f0"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}