diff --git "a/.ipynb_checkpoints/README-checkpoint.md" "b/.ipynb_checkpoints/README-checkpoint.md" --- "a/.ipynb_checkpoints/README-checkpoint.md" +++ "b/.ipynb_checkpoints/README-checkpoint.md" @@ -88,49 +88,49 @@ model-index: type: unknown metrics: - type: cosine_accuracy@1 - value: 0.7175 + value: 0.7125 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.841 name: Cosine Accuracy@3 - type: cosine_accuracy@5 - value: 0.878 + value: 0.875 name: Cosine Accuracy@5 - type: cosine_accuracy@10 - value: 0.9155 + value: 0.9185 name: Cosine Accuracy@10 - type: cosine_precision@1 - value: 0.7175 + value: 0.7125 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.28033333333333327 name: Cosine Precision@3 - type: cosine_precision@5 - value: 0.17560000000000003 + value: 0.175 name: Cosine Precision@5 - type: cosine_precision@10 - value: 0.09155 + value: 0.09185000000000001 name: Cosine Precision@10 - type: cosine_recall@1 - value: 0.7175 + value: 0.7125 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.841 name: Cosine Recall@3 - type: cosine_recall@5 - value: 0.878 + value: 0.875 name: Cosine Recall@5 - type: cosine_recall@10 - value: 0.9155 + value: 0.9185 name: Cosine Recall@10 - type: cosine_ndcg@10 - value: 0.8172358824512647 + value: 0.816812320396416 name: Cosine Ndcg@10 - type: cosine_mrr@10 - value: 0.7856547619047611 + value: 0.7841432539682534 name: Cosine Mrr@10 - type: cosine_map@100 - value: 0.7890154491139222 + value: 0.7873817407743899 name: Cosine Map@100 - task: type: semantic-similarity @@ -140,34 +140,34 @@ model-index: type: sts-dev metrics: - type: pearson_cosine - value: 0.8015277726105404 + value: 0.8008104516836907 name: Pearson Cosine - type: spearman_cosine - value: 0.8038248041571585 + value: 0.8002890211207748 name: Spearman Cosine - type: pearson_manhattan - value: 0.7895258398435966 + value: 0.79082403574537 name: Pearson Manhattan - type: spearman_manhattan - value: 0.8012166855619245 + value: 0.7991895587398584 name: Spearman Manhattan - type: pearson_euclidean - value: 0.7893816883662468 + value: 0.790161427188963 name: Pearson Euclidean - type: spearman_euclidean - value: 0.8029392819509334 + value: 0.8010498090367393 name: Spearman Euclidean - type: pearson_dot - value: 0.7952010752539163 + value: 0.7964995245181878 name: Pearson Dot - type: spearman_dot - value: 0.7982104142453529 + value: 0.7955515456830666 name: Spearman Dot - type: pearson_max - value: 0.8015277726105404 + value: 0.8008104516836907 name: Pearson Max - type: spearman_max - value: 0.8038248041571585 + value: 0.8010498090367393 name: Spearman Max --- @@ -180,7 +180,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [e ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [egyllm/pretrained-arabert](https://huggingface.co/egyllm/pretrained-arabert) -- **Maximum Sequence Length:** 256 tokens +- **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity @@ -197,7 +197,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [e ``` SentenceTransformer( - (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel + (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` @@ -266,23 +266,23 @@ You can finetune this model on your own dataset. * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) -| Metric | Value | -|:--------------------|:----------| -| cosine_accuracy@1 | 0.7175 | -| cosine_accuracy@3 | 0.841 | -| cosine_accuracy@5 | 0.878 | -| cosine_accuracy@10 | 0.9155 | -| cosine_precision@1 | 0.7175 | -| cosine_precision@3 | 0.2803 | -| cosine_precision@5 | 0.1756 | -| cosine_precision@10 | 0.0916 | -| cosine_recall@1 | 0.7175 | -| cosine_recall@3 | 0.841 | -| cosine_recall@5 | 0.878 | -| cosine_recall@10 | 0.9155 | -| cosine_ndcg@10 | 0.8172 | -| cosine_mrr@10 | 0.7857 | -| **cosine_map@100** | **0.789** | +| Metric | Value | +|:--------------------|:-----------| +| cosine_accuracy@1 | 0.7125 | +| cosine_accuracy@3 | 0.841 | +| cosine_accuracy@5 | 0.875 | +| cosine_accuracy@10 | 0.9185 | +| cosine_precision@1 | 0.7125 | +| cosine_precision@3 | 0.2803 | +| cosine_precision@5 | 0.175 | +| cosine_precision@10 | 0.0919 | +| cosine_recall@1 | 0.7125 | +| cosine_recall@3 | 0.841 | +| cosine_recall@5 | 0.875 | +| cosine_recall@10 | 0.9185 | +| cosine_ndcg@10 | 0.8168 | +| cosine_mrr@10 | 0.7841 | +| **cosine_map@100** | **0.7874** | #### Semantic Similarity * Dataset: `sts-dev` @@ -290,16 +290,16 @@ You can finetune this model on your own dataset. | Metric | Value | |:--------------------|:-----------| -| pearson_cosine | 0.8015 | -| **spearman_cosine** | **0.8038** | -| pearson_manhattan | 0.7895 | -| spearman_manhattan | 0.8012 | -| pearson_euclidean | 0.7894 | -| spearman_euclidean | 0.8029 | -| pearson_dot | 0.7952 | -| spearman_dot | 0.7982 | -| pearson_max | 0.8015 | -| spearman_max | 0.8038 | +| pearson_cosine | 0.8008 | +| **spearman_cosine** | **0.8003** | +| pearson_manhattan | 0.7908 | +| spearman_manhattan | 0.7992 | +| pearson_euclidean | 0.7902 | +| spearman_euclidean | 0.801 | +| pearson_dot | 0.7965 | +| spearman_dot | 0.7956 | +| pearson_max | 0.8008 | +| spearman_max | 0.801 |