lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/zephyr-7b-beta-dpo/v0.2.4/gsm8k/results_2024-03-13T22-28-19.904141.json with huggingface_hub
7aa3e77 verified
raw
history blame
2.17 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 600048.816544628,
"end_time": 601348.28878054,
"total_evaluation_time_secondes": "1299.4722359119914",
"model_name": "HuggingFaceH4/zephyr-7b-beta-dpo",
"model_sha": "09b84bad4c12c22de5d983565d4f6f37b51c2f67",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"lighteval|gsm8k|5": {
"qem": 0.1463229719484458,
"qem_stderr": 0.009735210557785253
}
},
"versions": {
"lighteval|gsm8k|5": 0
},
"config_tasks": {
"lighteval|gsm8k": {
"name": "gsm8k",
"prompt_function": "gsm8k",
"hf_repo": "gsm8k",
"hf_subset": "main",
"metric": [
"quasi_exact_match_gsm8k"
],
"hf_avail_splits": [
"train",
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling_from_train",
"generation_size": 256,
"stop_sequence": [
"Question:"
],
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 1319,
"effective_num_docs": 1319,
"trust_dataset": true
}
},
"summary_tasks": {
"lighteval|gsm8k|5": {
"hashes": {
"hash_examples": "0ed016e24e7512fd",
"hash_full_prompts": "a9c6515c2ecd2d07",
"hash_input_tokens": "56d913c067767423",
"hash_cont_tokens": "3e986f53f215a8e1"
},
"truncated": 0,
"non_truncated": 1319,
"padded": 0,
"non_padded": 1319,
"effective_few_shots": 5.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "bc71463e88551d0e",
"hash_full_prompts": "f49691ec139bfeac",
"hash_input_tokens": "6b72eede304aeb24",
"hash_cont_tokens": "1ce1d6da8cfb19c5"
},
"truncated": 0,
"non_truncated": 1319,
"padded": 0,
"non_padded": 1319,
"num_truncated_few_shots": 0
}
}