lewtun's picture
lewtun HF staff
Upload eval_results/alignment-handbook/zephyr-2b-gemma-dpo-mix6-beta-0.2/main/ifeval/results_2024-03-06T20-26-59.064736.json with huggingface_hub
b0680e2 verified
raw
history blame
2.5 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 6758669.700341984,
"end_time": 6759266.96671964,
"total_evaluation_time_secondes": "597.2663776567206",
"model_name": "alignment-handbook/zephyr-2b-gemma-dpo-mix6-beta-0.2",
"model_sha": "fe6b14abb6fe0e43b96205f12988e56a073083de",
"model_dtype": "torch.bfloat16",
"model_size": "4.68 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.2033271719038817,
"prompt_level_strict_acc_stderr": 0.01731971864183471,
"inst_level_strict_acc": 0.3393285371702638,
"inst_level_strict_acc_stderr": 0.0004893794187937949,
"prompt_level_loose_acc": 0.2144177449168207,
"prompt_level_loose_acc_stderr": 0.017661570312173934,
"inst_level_loose_acc": 0.3513189448441247,
"inst_level_loose_acc_stderr": 0.0004889980009456045
}
},
"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": "0f910480d235c712"
},
"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": "24d0c76ee306c7e6"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}