edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-odpo/v3.2/gsm8k/results_2024-04-02T22-34-30.468109.json with huggingface_hub
9c3362f 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": 1268248.182424907,
"end_time": 1269539.891568115,
"total_evaluation_time_secondes": "1291.7091432078741",
"model_name": "HuggingFaceH4/mistral-7b-odpo",
"model_sha": "e07db7b28271d83777947af240e15ade33456f24",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"lighteval|gsm8k|5": {
"qem": 0.1819560272934041,
"qem_stderr": 0.010627077371675777
}
},
"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": "faa09535944c3187",
"hash_input_tokens": "b6842acfc19a5637",
"hash_cont_tokens": "bc37081c79da929f"
},
"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": "24555d96d1b06364",
"hash_input_tokens": "2efc02ed9cc6bfb4",
"hash_cont_tokens": "bf3984420c848128"
},
"truncated": 0,
"non_truncated": 1319,
"padded": 0,
"non_padded": 1319,
"num_truncated_few_shots": 0
}
}