open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-7B-Chat /main /gsm8k /results_2024-03-02T15-33-14.411760.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-7B-Chat/main/gsm8k/results_2024-03-02T15-33-14.411760.json with huggingface_hub
b700328 verified
raw
history blame
2.16 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 1340066.550592904,
"end_time": 1340612.129863269,
"total_evaluation_time_secondes": "545.5792703649495",
"model_name": "Qwen/Qwen1.5-7B-Chat",
"model_sha": "a2662f4bc1afe913a91cd49f794d229a8c28f97e",
"model_dtype": "torch.bfloat16",
"model_size": "14.88 GB",
"config": null
},
"results": {
"lighteval|gsm8k|5": {
"qem": 0.06368460955269144,
"qem_stderr": 0.00672621307880569
}
},
"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:",
"Question"
],
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 1319,
"effective_num_docs": 1319
}
},
"summary_tasks": {
"lighteval|gsm8k|5": {
"hashes": {
"hash_examples": "0ed016e24e7512fd",
"hash_full_prompts": "66ff2108d151c6de",
"hash_input_tokens": "aa57736f8c45c33c",
"hash_cont_tokens": "180586c5f7c0f6d1"
},
"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": "84c6a9cfa115dda5",
"hash_input_tokens": "5aac43a2850ca464",
"hash_cont_tokens": "b73eeb6d9fabc03d"
},
"truncated": 0,
"non_truncated": 1319,
"padded": 0,
"non_padded": 1319,
"num_truncated_few_shots": 0
}
}