indonesian-embedding-small / pytorch /comprehensive_evaluation_results.json
asmud's picture
Initial Release: Indonesian Embedding Small with PyTorch and ONNX variants...
4b80424
{
"semantic_similarity": {
"accuracy": 100.0,
"correct_predictions": 12,
"total_tests": 12,
"detailed_results": [
{
"pair": 1,
"similarity": "0.71942925",
"expected": "high",
"threshold": 0.7,
"correct": true
},
{
"pair": 2,
"similarity": "0.7370041",
"expected": "high",
"threshold": 0.7,
"correct": true
},
{
"pair": 3,
"similarity": "0.9284322",
"expected": "high",
"threshold": 0.7,
"correct": true
},
{
"pair": 4,
"similarity": "0.6480197",
"expected": "high",
"threshold": 0.6,
"correct": true
},
{
"pair": 5,
"similarity": "0.58356583",
"expected": "high",
"threshold": 0.5,
"correct": true
},
{
"pair": 6,
"similarity": "0.54717076",
"expected": "medium",
"threshold": 0.4,
"correct": true
},
{
"pair": 7,
"similarity": "0.49372473",
"expected": "medium",
"threshold": 0.3,
"correct": true
},
{
"pair": 8,
"similarity": "0.43846166",
"expected": "medium",
"threshold": 0.3,
"correct": true
},
{
"pair": 9,
"similarity": "-0.06786405",
"expected": "low",
"threshold": 0.3,
"correct": true
},
{
"pair": 10,
"similarity": "0.1027292",
"expected": "low",
"threshold": 0.2,
"correct": true
},
{
"pair": 11,
"similarity": "0.028663296",
"expected": "low",
"threshold": 0.2,
"correct": true
},
{
"pair": 12,
"similarity": "0.050983254",
"expected": "low",
"threshold": 0.3,
"correct": true
}
]
},
"performance": {
"single_short": {
"time_ms": 9.330987930297852,
"std_ms": 0.25900265208905177
},
"single_medium": {
"time_ms": 10.157299041748047,
"std_ms": 0.183147367263395
},
"single_long": {
"time_ms": 13.341379165649414,
"std_ms": 0.8901414648164488
},
"batch_small": {
"total_time_ms": 10.205698013305664,
"per_item_time_ms": 5.102849006652832,
"throughput_per_sec": 195.96895747772496,
"std_ms": 0.4837328576887996
},
"batch_medium": {
"total_time_ms": 22.638392448425293,
"per_item_time_ms": 2.2638392448425293,
"throughput_per_sec": 441.7274779020624,
"std_ms": 0.2929920292291012
},
"batch_large": {
"total_time_ms": 149.32355880737305,
"per_item_time_ms": 2.986471176147461,
"throughput_per_sec": 334.8433455466987,
"std_ms": 1.8578833280673674
},
"memory_usage_mb": 4.28125
},
"robustness": {
"robustness_score": 100.0,
"passed": 15,
"total": 15,
"detailed_results": {
"empty_string": "PASS",
"single_char": "PASS",
"single_word": "PASS",
"numbers_only": "PASS",
"punctuation": "PASS",
"mixed_script": "PASS",
"very_long": "PASS",
"repeated_words": "PASS",
"special_unicode": "PASS",
"html_tags": "PASS",
"code_snippet": "PASS",
"multiple_languages": "PASS",
"whitespace_heavy": "PASS",
"newlines": "PASS",
"tabs": "PASS"
}
},
"domain_knowledge": {
"technology": {
"avg_intra_similarity": "0.3058956",
"std_intra_similarity": "0.11448153",
"sentences_count": 5
},
"business": {
"avg_intra_similarity": "0.16541281",
"std_intra_similarity": "0.092469",
"sentences_count": 5
},
"education": {
"avg_intra_similarity": "0.36788327",
"std_intra_similarity": "0.10402755",
"sentences_count": 5
},
"health": {
"avg_intra_similarity": "0.33086413",
"std_intra_similarity": "0.11471059",
"sentences_count": 5
},
"domain_separation": 0.08586536347866058
},
"vector_quality": {
"embedding_dimension": 384,
"effective_dimension": "9",
"vector_norm_mean": 2.873112201690674,
"vector_norm_std": 0.0988447293639183,
"value_range": [
-0.6662746667861938,
0.5068685412406921
],
"sparsity_percent": 0.0,
"similarity_mean": 0.2025408148765564,
"similarity_std": 0.1270897388458252,
"explained_variance_95": 0.9999999403953552
},
"clustering": {
"silhouette_score": 0.06952675431966782,
"cluster_purity": 0.8,
"n_clusters": 4,
"n_samples": 20
},
"retrieval": {
"avg_precision_at_5": 1.0,
"avg_recall_at_5": 1.0,
"detailed_results": [
{
"query": "AI dan machine learning",
"precision_at_k": 1.0,
"recall_at_k": 1.0,
"relevant_docs": 5,
"retrieved_relevant": 5
},
{
"query": "Indonesia dan budaya",
"precision_at_k": 1.0,
"recall_at_k": 1.0,
"relevant_docs": 5,
"retrieved_relevant": 5
},
{
"query": "olahraga dan aktivitas fisik",
"precision_at_k": 1.0,
"recall_at_k": 1.0,
"relevant_docs": 5,
"retrieved_relevant": 5
}
]
}
}