lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/starcoder2-15b-dpo/v2.1.3/ifeval/results_2024-03-11T17-08-01.854587.json with huggingface_hub
c966f90 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": 408437.093493187,
"end_time": 409318.911249856,
"total_evaluation_time_secondes": "881.8177566690138",
"model_name": "HuggingFaceH4/starcoder2-15b-dpo",
"model_sha": "2ff1599db9c51f736a6fd26ffa6e05d17185140e",
"model_dtype": "torch.bfloat16",
"model_size": "30.04 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.3031423290203327,
"prompt_level_strict_acc_stderr": 0.01977873237598547,
"inst_level_strict_acc": 0.44004796163069543,
"inst_level_strict_acc_stderr": 0.0005095784484723712,
"prompt_level_loose_acc": 0.32717190388170053,
"prompt_level_loose_acc_stderr": 0.020190318966906352,
"inst_level_loose_acc": 0.4628297362110312,
"inst_level_loose_acc_stderr": 0.0005209099895578227
}
},
"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,
"trust_dataset": null
}
},
"summary_tasks": {
"custom|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "7ea7bf2a8edba8f4",
"hash_input_tokens": "dc4c9014dffc6917",
"hash_cont_tokens": "3e5fdf6751d5eb3e"
},
"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": "5d5e6158af678a01",
"hash_cont_tokens": "54c50886f770a08b"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}