opensource/self-llm
3
0
Fork 0
mirror of https://github.com/datawhalechina/self-llm.git synced 2026-08-28 15:11:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 添加BGE-M3 MTEB变量

Browse Source 
feat: update

feat: update

feat: update
This commit is contained in:
dapeng
2025-09-04 10:03:22 +08:00
parent e9e6280bf9
commit 57fbcec057
1 changed files with 55 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/BGE-M3-finetune-embedding-with-valid/02-C-MTEB_retrieval_evaluation.ipynb
+55 -1
View File
@@ -879,6 +879,60 @@
"all_results[\"BGE-M3\"][0].scores"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"总共有 20 个评估指标\n",
"指标列表：\n",
" 1. ndcg_at_1\n",
" 2. ndcg_at_3\n",
" 3. ndcg_at_5\n",
" 4. ndcg_at_10\n",
" 5. map_at_1\n",
" 6. map_at_3\n",
" 7. map_at_5\n",
" 8. map_at_10\n",
" 9. recall_at_1\n",
"10. recall_at_3\n",
"11. recall_at_5\n",
"12. recall_at_10\n",
"13. precision_at_1\n",
"14. precision_at_3\n",
"15. precision_at_5\n",
"16. precision_at_10\n",
"17. mrr_at_1\n",
"18. mrr_at_3\n",
"19. mrr_at_5\n",
"20. mrr_at_10\n"
]
}
],
"source": [
"# 提取两个模型的评测结果\n",
"scores_m3 = all_results[\"BGE-M3\"][0].scores['dev'][0]\n",
"scores_reranker = all_results[\"BGE-M3-Finetuned\"][0].scores['dev'][0]\n",
"\n",
"# 完整的评估指标列表\n",
"metrics = [\n",
" 'ndcg_at_1', 'ndcg_at_3', 'ndcg_at_5', 'ndcg_at_10',\n",
" 'map_at_1', 'map_at_3', 'map_at_5', 'map_at_10', \n",
" 'recall_at_1', 'recall_at_3', 'recall_at_5', 'recall_at_10',\n",
" 'precision_at_1', 'precision_at_3', 'precision_at_5', 'precision_at_10',\n",
" 'mrr_at_1', 'mrr_at_3', 'mrr_at_5', 'mrr_at_10'\n",
"]\n",
"\n",
"print(f\"总共有 {len(metrics)} 个评估指标\")\n",
"print(\"指标列表：\")\n",
"for i, metric in enumerate(metrics, 1):\n",
" print(f\"{i:2d}. {metric}\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
@@ -948,4 +1002,4 @@
},
"nbformat": 4,
"nbformat_minor": 4
}
}