edbeeching's picture
edbeeching HF staff
Upload eval_results/AI-MO/mistral-7b-sft/aimo_v01.10/gsm8k/results_2024-04-24T17-52-04.162351.json with huggingface_hub
dcb6edc verified
raw
history blame
2.3 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 3490767.824887148,
"end_time": 3491219.400846146,
"total_evaluation_time_secondes": "451.5759589979425",
"model_name": "AI-MO/mistral-7b-sft",
"model_sha": "71c0d7cf9eb202b6b3429b5eda017fb0c6f168e1",
"model_dtype": "torch.bfloat16",
"model_size": "12.93 GB",
"config": null
},
"results": {
"lighteval|gsm8k|5": {
"qem": 0.6603487490523123,
"qem_stderr": 0.013045045067665241
},
"all": {
"qem": 0.6603487490523123,
"qem_stderr": 0.013045045067665241
}
},
"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,
"must_remove_duplicate_docs": null
}
},
"summary_tasks": {
"lighteval|gsm8k|5": {
"hashes": {
"hash_examples": "0ed016e24e7512fd",
"hash_full_prompts": "b6d97958f0ed1df8",
"hash_input_tokens": "3f58ee5e568409ec",
"hash_cont_tokens": "f4617b3fe0f21196"
},
"truncated": 1319,
"non_truncated": 0,
"padded": 611,
"non_padded": 708,
"effective_few_shots": 5.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "bc71463e88551d0e",
"hash_full_prompts": "b5a5dacaed0816ff",
"hash_input_tokens": "e4e0fd8eba82bd47",
"hash_cont_tokens": "140937d2a5143a42"
},
"truncated": 1319,
"non_truncated": 0,
"padded": 611,
"non_padded": 708,
"num_truncated_few_shots": 0
}
}