lewtun's picture
lewtun HF staff
Upload eval_results/alignment-handbook/zephyr-2b-gemma-sft-v1/main/ifeval/results_2024-03-05T08-31-00.299982.json with huggingface_hub
002be70 verified
raw
history blame
2.49 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 1578207.249988045,
"end_time": 1578831.926880584,
"total_evaluation_time_secondes": "624.6768925390206",
"model_name": "alignment-handbook/zephyr-2b-gemma-sft-v1",
"model_sha": "6607539d04bc66d5856772cc04b3b1ce17ebe644",
"model_dtype": "torch.bfloat16",
"model_size": "4.68 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.2088724584103512,
"prompt_level_strict_acc_stderr": 0.01749310734779331,
"inst_level_strict_acc": 0.35851318944844124,
"inst_level_strict_acc_stderr": 0.0004983948326086951,
"prompt_level_loose_acc": 0.21626617375231053,
"prompt_level_loose_acc_stderr": 0.017716654428910135,
"inst_level_loose_acc": 0.36930455635491605,
"inst_level_loose_acc_stderr": 0.0004892692514010516
}
},
"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": "dffcf9a3b5dd7b3d",
"hash_input_tokens": "697d713cee490081",
"hash_cont_tokens": "819f459ad247aa67"
},
"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": "74abf332fe1a119c",
"hash_input_tokens": "369e8568d4bc5b04",
"hash_cont_tokens": "153972cb2d729443"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}