lewtun's picture
lewtun HF staff
Upload eval_results/alignment-handbook/zephyr-2b-gemma-dpo-mix6-beta-0.05-epoch-9/main/ifeval/results_2024-03-06T21-53-04.385295.json with huggingface_hub
3b92c49 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": 1133165.636556282,
"end_time": 1133758.551466504,
"total_evaluation_time_secondes": "592.9149102221709",
"model_name": "alignment-handbook/zephyr-2b-gemma-dpo-mix6-beta-0.05-epoch-9",
"model_sha": "01e4935f1d0857606dc07779a14da1fbc5dc9eba",
"model_dtype": "torch.bfloat16",
"model_size": "4.68 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.21626617375231053,
"prompt_level_strict_acc_stderr": 0.01771665442891013,
"inst_level_strict_acc": 0.35851318944844124,
"inst_level_strict_acc_stderr": 0.00048292280227006234,
"prompt_level_loose_acc": 0.22181146025878004,
"prompt_level_loose_acc_stderr": 0.01787876540794438,
"inst_level_loose_acc": 0.36330935251798563,
"inst_level_loose_acc_stderr": 0.00048537186307284747
}
},
"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": "7ea7bf2a8edba8f4",
"hash_input_tokens": "89df3fff41e770ad",
"hash_cont_tokens": "e680c38da5e7c930"
},
"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": "917957472cc73e8e",
"hash_cont_tokens": "4292b604bdaa7ec7"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}