tmy100000001 commited on
Commit
d26796d
·
verified ·
1 Parent(s): 2343e88

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,388 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - cross-encoder
5
+ - reranker
6
+ - generated_from_trainer
7
+ - dataset_size:35474
8
+ - loss:BinaryCrossEntropyLoss
9
+ base_model: ncbi/MedCPT-Cross-Encoder
10
+ pipeline_tag: text-ranking
11
+ library_name: sentence-transformers
12
+ metrics:
13
+ - accuracy
14
+ - accuracy_threshold
15
+ - f1
16
+ - f1_threshold
17
+ - precision
18
+ - recall
19
+ - average_precision
20
+ model-index:
21
+ - name: CrossEncoder based on ncbi/MedCPT-Cross-Encoder
22
+ results:
23
+ - task:
24
+ type: cross-encoder-classification
25
+ name: Cross Encoder Classification
26
+ dataset:
27
+ name: anno test
28
+ type: anno_test
29
+ metrics:
30
+ - type: accuracy
31
+ value: 0.824009900990099
32
+ name: Accuracy
33
+ - type: accuracy_threshold
34
+ value: 0.9996383786201477
35
+ name: Accuracy Threshold
36
+ - type: f1
37
+ value: 0.3841536614645858
38
+ name: F1
39
+ - type: f1_threshold
40
+ value: 0.9992461800575256
41
+ name: F1 Threshold
42
+ - type: precision
43
+ value: 0.26981450252951095
44
+ name: Precision
45
+ - type: recall
46
+ value: 0.6666666666666666
47
+ name: Recall
48
+ - type: average_precision
49
+ value: 0.3289533283996273
50
+ name: Average Precision
51
+ ---
52
+
53
+ # CrossEncoder based on ncbi/MedCPT-Cross-Encoder
54
+
55
+ This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [ncbi/MedCPT-Cross-Encoder](https://huggingface.co/ncbi/MedCPT-Cross-Encoder) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
56
+
57
+ ## Model Details
58
+
59
+ ### Model Description
60
+ - **Model Type:** Cross Encoder
61
+ - **Base model:** [ncbi/MedCPT-Cross-Encoder](https://huggingface.co/ncbi/MedCPT-Cross-Encoder) <!-- at revision 71caf65d4927987813984f54c284405a13fcca49 -->
62
+ - **Maximum Sequence Length:** 512 tokens
63
+ - **Number of Output Labels:** 1 label
64
+ <!-- - **Training Dataset:** Unknown -->
65
+ <!-- - **Language:** Unknown -->
66
+ <!-- - **License:** Unknown -->
67
+
68
+ ### Model Sources
69
+
70
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
71
+ - **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
72
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
73
+ - **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
74
+
75
+ ## Usage
76
+
77
+ ### Direct Usage (Sentence Transformers)
78
+
79
+ First install the Sentence Transformers library:
80
+
81
+ ```bash
82
+ pip install -U sentence-transformers
83
+ ```
84
+
85
+ Then you can load this model and run inference.
86
+ ```python
87
+ from sentence_transformers import CrossEncoder
88
+
89
+ # Download from the 🤗 Hub
90
+ model = CrossEncoder("cross_encoder_model_id")
91
+ # Get scores for pairs of texts
92
+ pairs = [
93
+ ['Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.', 'G2P01414 - PIGN - 606097.0 - HGNC:8967 - MCD4; PIG-N - PIGN-related multiple congenital anomalies-hypotonia-seizures syndrome - 614080 - nan - biallelic_autosomal - nan - definitive - absent gene product; altered gene product structure - inframe_insertion; missense_variant; inframe_deletion - undetermined - inferred'],
94
+ ['Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.', 'G2P02996 - MFF - 614785.0 - HGNC:24858 - C2ORF33; GL004 - MFF-related encephalopathy due to defective mitochondrial and peroxisomal fission - 617086 - nan - biallelic_autosomal - nan - definitive - absent gene product - nan - loss of function - inferred'],
95
+ ['Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.', 'G2P01166 - CERT1 - 604677.0 - HGNC:2205 - CERT; COL4A3BP; GPBP; STARD11 - CERT1-related intellectual disability - 616351 - nan - monoallelic_autosomal - restricted mutation set - definitive - altered gene product structure - nan - gain of function - inferred'],
96
+ ['Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.', 'G2P01646 - STAT2 - 600556.0 - HGNC:11363 - STAT113 - STAT2-related viral induced severe multiorgan dysfunction related with impaired mitochondrial fission - nan - nan - biallelic_autosomal - nan - limited - absent gene product - nan - loss of function - inferred'],
97
+ ['Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.', 'G2P03036 - NDUFA8 - 603359.0 - HGNC:7692 - MGC793; PGIV - NDUFA8-related developmental disorder - nan - nan - biallelic_autosomal - nan - strong - absent gene product - nan - loss of function - inferred'],
98
+ ]
99
+ scores = model.predict(pairs)
100
+ print(scores.shape)
101
+ # (5,)
102
+
103
+ # Or rank different texts based on similarity to a single text
104
+ ranks = model.rank(
105
+ 'Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Osmotic stabilization suppressed these morphological defects, indicating that cell wall weakness caused by impaired GPI anchor synthesis resulted in abnormal cytokinesis. Furthermore, calcineurin-deleted cells exhibited hypersensitivity to BE49385A, and FK506 exacerbated the cytokinesis defects of the its8-1 mutant. Thus, calcineurin and Its8 may share an essential function in cytokinesis and cell viability through the regulation of cell wall integrity.',
106
+ [
107
+ 'G2P01414 - PIGN - 606097.0 - HGNC:8967 - MCD4; PIG-N - PIGN-related multiple congenital anomalies-hypotonia-seizures syndrome - 614080 - nan - biallelic_autosomal - nan - definitive - absent gene product; altered gene product structure - inframe_insertion; missense_variant; inframe_deletion - undetermined - inferred',
108
+ 'G2P02996 - MFF - 614785.0 - HGNC:24858 - C2ORF33; GL004 - MFF-related encephalopathy due to defective mitochondrial and peroxisomal fission - 617086 - nan - biallelic_autosomal - nan - definitive - absent gene product - nan - loss of function - inferred',
109
+ 'G2P01166 - CERT1 - 604677.0 - HGNC:2205 - CERT; COL4A3BP; GPBP; STARD11 - CERT1-related intellectual disability - 616351 - nan - monoallelic_autosomal - restricted mutation set - definitive - altered gene product structure - nan - gain of function - inferred',
110
+ 'G2P01646 - STAT2 - 600556.0 - HGNC:11363 - STAT113 - STAT2-related viral induced severe multiorgan dysfunction related with impaired mitochondrial fission - nan - nan - biallelic_autosomal - nan - limited - absent gene product - nan - loss of function - inferred',
111
+ 'G2P03036 - NDUFA8 - 603359.0 - HGNC:7692 - MGC793; PGIV - NDUFA8-related developmental disorder - nan - nan - biallelic_autosomal - nan - strong - absent gene product - nan - loss of function - inferred',
112
+ ]
113
+ )
114
+ # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
115
+ ```
116
+
117
+ <!--
118
+ ### Direct Usage (Transformers)
119
+
120
+ <details><summary>Click to see the direct usage in Transformers</summary>
121
+
122
+ </details>
123
+ -->
124
+
125
+ <!--
126
+ ### Downstream Usage (Sentence Transformers)
127
+
128
+ You can finetune this model on your own dataset.
129
+
130
+ <details><summary>Click to expand</summary>
131
+
132
+ </details>
133
+ -->
134
+
135
+ <!--
136
+ ### Out-of-Scope Use
137
+
138
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
139
+ -->
140
+
141
+ ## Evaluation
142
+
143
+ ### Metrics
144
+
145
+ #### Cross Encoder Classification
146
+
147
+ * Dataset: `anno_test`
148
+ * Evaluated with [<code>CrossEncoderClassificationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderClassificationEvaluator)
149
+
150
+ | Metric | Value |
151
+ |:----------------------|:----------|
152
+ | accuracy | 0.824 |
153
+ | accuracy_threshold | 0.9996 |
154
+ | f1 | 0.3842 |
155
+ | f1_threshold | 0.9992 |
156
+ | precision | 0.2698 |
157
+ | recall | 0.6667 |
158
+ | **average_precision** | **0.329** |
159
+
160
+ <!--
161
+ ## Bias, Risks and Limitations
162
+
163
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
164
+ -->
165
+
166
+ <!--
167
+ ### Recommendations
168
+
169
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
170
+ -->
171
+
172
+ ## Training Details
173
+
174
+ ### Training Dataset
175
+
176
+ #### Unnamed Dataset
177
+
178
+ * Size: 35,474 training samples
179
+ * Columns: <code>tiab</code>, <code>g2p_lgmde</code>, and <code>label</code>
180
+ * Approximate statistics based on the first 1000 samples:
181
+ | | tiab | g2p_lgmde | label |
182
+ |:--------|:---------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:------------------------------------------------|
183
+ | type | string | string | int |
184
+ | details | <ul><li>min: 30 characters</li><li>mean: 1348.52 characters</li><li>max: 2802 characters</li></ul> | <ul><li>min: 177 characters</li><li>mean: 258.9 characters</li><li>max: 407 characters</li></ul> | <ul><li>0: ~72.90%</li><li>1: ~27.10%</li></ul> |
185
+ * Samples:
186
+ | tiab | g2p_lgmde | label |
187
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
188
+ | <code>Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Os...</code> | <code>G2P01414 - PIGN - 606097.0 - HGNC:8967 - MCD4; PIG-N - PIGN-related multiple congenital anomalies-hypotonia-seizures syndrome - 614080 - nan - biallelic_autosomal - nan - definitive - absent gene product; altered gene product structure - inframe_insertion; missense_variant; inframe_deletion - undetermined - inferred</code> | <code>1</code> |
189
+ | <code>Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Os...</code> | <code>G2P02996 - MFF - 614785.0 - HGNC:24858 - C2ORF33; GL004 - MFF-related encephalopathy due to defective mitochondrial and peroxisomal fission - 617086 - nan - biallelic_autosomal - nan - definitive - absent gene product - nan - loss of function - inferred</code> | <code>0</code> |
190
+ | <code>Its8, a fission yeast homolog of Mcd4 and Pig-n, is involved in GPI anchor synthesis and shares an essential function with calcineurin in cytokinesis. In fission yeast, calcineurin is required for cytokinesis and ion homeostasis; however, most of its physiological roles remain obscure. To identify genes that share an essential function with calcineurin, we screened for mutations that confer sensitivity to the calcineurin inhibitor FK506 and high temperature and isolated the mutant its8-1. its8(+) encodes a homolog of the budding yeast MCD4 and human Pig-n that are involved in glycosylphosphatidylinositol (GPI) anchor synthesis. Consistently, reduced inositol labeling of proteins suggested impaired GPI anchor synthesis in its8-1 mutants. The temperature upshift induced a further decrease in inositol labeling and caused dramatic increases in the frequency of septation in its8-1 mutants. BE49385A, an inhibitor of MCD4 and Pig-n, also increased the septation index of the wild-type cell. Os...</code> | <code>G2P01166 - CERT1 - 604677.0 - HGNC:2205 - CERT; COL4A3BP; GPBP; STARD11 - CERT1-related intellectual disability - 616351 - nan - monoallelic_autosomal - restricted mutation set - definitive - altered gene product structure - nan - gain of function - inferred</code> | <code>0</code> |
191
+ * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
192
+ ```json
193
+ {
194
+ "activation_fn": "torch.nn.modules.linear.Identity",
195
+ "pos_weight": null
196
+ }
197
+ ```
198
+
199
+ ### Training Hyperparameters
200
+ #### Non-Default Hyperparameters
201
+
202
+ - `per_device_train_batch_size`: 16
203
+ - `per_device_eval_batch_size`: 16
204
+ - `learning_rate`: 3.879271032713091e-05
205
+ - `num_train_epochs`: 2
206
+ - `warmup_ratio`: 0.1
207
+
208
+ #### All Hyperparameters
209
+ <details><summary>Click to expand</summary>
210
+
211
+ - `overwrite_output_dir`: False
212
+ - `do_predict`: False
213
+ - `eval_strategy`: no
214
+ - `prediction_loss_only`: True
215
+ - `per_device_train_batch_size`: 16
216
+ - `per_device_eval_batch_size`: 16
217
+ - `per_gpu_train_batch_size`: None
218
+ - `per_gpu_eval_batch_size`: None
219
+ - `gradient_accumulation_steps`: 1
220
+ - `eval_accumulation_steps`: None
221
+ - `torch_empty_cache_steps`: None
222
+ - `learning_rate`: 3.879271032713091e-05
223
+ - `weight_decay`: 0.0
224
+ - `adam_beta1`: 0.9
225
+ - `adam_beta2`: 0.999
226
+ - `adam_epsilon`: 1e-08
227
+ - `max_grad_norm`: 1.0
228
+ - `num_train_epochs`: 2
229
+ - `max_steps`: -1
230
+ - `lr_scheduler_type`: linear
231
+ - `lr_scheduler_kwargs`: {}
232
+ - `warmup_ratio`: 0.1
233
+ - `warmup_steps`: 0
234
+ - `log_level`: passive
235
+ - `log_level_replica`: warning
236
+ - `log_on_each_node`: True
237
+ - `logging_nan_inf_filter`: True
238
+ - `save_safetensors`: True
239
+ - `save_on_each_node`: False
240
+ - `save_only_model`: False
241
+ - `restore_callback_states_from_checkpoint`: False
242
+ - `no_cuda`: False
243
+ - `use_cpu`: False
244
+ - `use_mps_device`: False
245
+ - `seed`: 42
246
+ - `data_seed`: None
247
+ - `jit_mode_eval`: False
248
+ - `use_ipex`: False
249
+ - `bf16`: False
250
+ - `fp16`: False
251
+ - `fp16_opt_level`: O1
252
+ - `half_precision_backend`: auto
253
+ - `bf16_full_eval`: False
254
+ - `fp16_full_eval`: False
255
+ - `tf32`: None
256
+ - `local_rank`: 0
257
+ - `ddp_backend`: None
258
+ - `tpu_num_cores`: None
259
+ - `tpu_metrics_debug`: False
260
+ - `debug`: []
261
+ - `dataloader_drop_last`: False
262
+ - `dataloader_num_workers`: 0
263
+ - `dataloader_prefetch_factor`: None
264
+ - `past_index`: -1
265
+ - `disable_tqdm`: False
266
+ - `remove_unused_columns`: True
267
+ - `label_names`: None
268
+ - `load_best_model_at_end`: False
269
+ - `ignore_data_skip`: False
270
+ - `fsdp`: []
271
+ - `fsdp_min_num_params`: 0
272
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
273
+ - `fsdp_transformer_layer_cls_to_wrap`: None
274
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
275
+ - `deepspeed`: None
276
+ - `label_smoothing_factor`: 0.0
277
+ - `optim`: adamw_torch
278
+ - `optim_args`: None
279
+ - `adafactor`: False
280
+ - `group_by_length`: False
281
+ - `length_column_name`: length
282
+ - `ddp_find_unused_parameters`: None
283
+ - `ddp_bucket_cap_mb`: None
284
+ - `ddp_broadcast_buffers`: False
285
+ - `dataloader_pin_memory`: True
286
+ - `dataloader_persistent_workers`: False
287
+ - `skip_memory_metrics`: True
288
+ - `use_legacy_prediction_loop`: False
289
+ - `push_to_hub`: False
290
+ - `resume_from_checkpoint`: None
291
+ - `hub_model_id`: None
292
+ - `hub_strategy`: every_save
293
+ - `hub_private_repo`: None
294
+ - `hub_always_push`: False
295
+ - `hub_revision`: None
296
+ - `gradient_checkpointing`: False
297
+ - `gradient_checkpointing_kwargs`: None
298
+ - `include_inputs_for_metrics`: False
299
+ - `include_for_metrics`: []
300
+ - `eval_do_concat_batches`: True
301
+ - `fp16_backend`: auto
302
+ - `push_to_hub_model_id`: None
303
+ - `push_to_hub_organization`: None
304
+ - `mp_parameters`:
305
+ - `auto_find_batch_size`: False
306
+ - `full_determinism`: False
307
+ - `torchdynamo`: None
308
+ - `ray_scope`: last
309
+ - `ddp_timeout`: 1800
310
+ - `torch_compile`: False
311
+ - `torch_compile_backend`: None
312
+ - `torch_compile_mode`: None
313
+ - `include_tokens_per_second`: False
314
+ - `include_num_input_tokens_seen`: False
315
+ - `neftune_noise_alpha`: None
316
+ - `optim_target_modules`: None
317
+ - `batch_eval_metrics`: False
318
+ - `eval_on_start`: False
319
+ - `use_liger_kernel`: False
320
+ - `liger_kernel_config`: None
321
+ - `eval_use_gather_object`: False
322
+ - `average_tokens_across_devices`: False
323
+ - `prompts`: None
324
+ - `batch_sampler`: batch_sampler
325
+ - `multi_dataset_batch_sampler`: proportional
326
+ - `router_mapping`: {}
327
+ - `learning_rate_mapping`: {}
328
+
329
+ </details>
330
+
331
+ ### Training Logs
332
+ | Epoch | Step | Training Loss | anno_test_average_precision |
333
+ |:------:|:----:|:-------------:|:---------------------------:|
334
+ | -1 | -1 | - | 0.6910 |
335
+ | 0.2254 | 500 | 0.0908 | - |
336
+ | 0.4509 | 1000 | 0.0266 | - |
337
+ | 0.6763 | 1500 | 0.0207 | - |
338
+ | 0.9017 | 2000 | 0.0126 | - |
339
+ | 1.1271 | 2500 | 0.0082 | - |
340
+ | 1.3526 | 3000 | 0.0098 | - |
341
+ | 1.5780 | 3500 | 0.0072 | - |
342
+ | 1.8034 | 4000 | 0.0098 | - |
343
+ | -1 | -1 | - | 0.3290 |
344
+
345
+
346
+ ### Framework Versions
347
+ - Python: 3.10.12
348
+ - Sentence Transformers: 5.1.0
349
+ - Transformers: 4.55.0
350
+ - PyTorch: 2.7.1+cu126
351
+ - Accelerate: 1.10.0
352
+ - Datasets: 4.0.0
353
+ - Tokenizers: 0.21.4
354
+
355
+ ## Citation
356
+
357
+ ### BibTeX
358
+
359
+ #### Sentence Transformers
360
+ ```bibtex
361
+ @inproceedings{reimers-2019-sentence-bert,
362
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
363
+ author = "Reimers, Nils and Gurevych, Iryna",
364
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
365
+ month = "11",
366
+ year = "2019",
367
+ publisher = "Association for Computational Linguistics",
368
+ url = "https://arxiv.org/abs/1908.10084",
369
+ }
370
+ ```
371
+
372
+ <!--
373
+ ## Glossary
374
+
375
+ *Clearly define terms in order to be accessible across audiences.*
376
+ -->
377
+
378
+ <!--
379
+ ## Model Card Authors
380
+
381
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
382
+ -->
383
+
384
+ <!--
385
+ ## Model Card Contact
386
+
387
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
388
+ -->
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "sentence_transformers": {
26
+ "activation_fn": "torch.nn.modules.activation.Sigmoid",
27
+ "version": "5.1.0"
28
+ },
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774e1259e9888ab867dfc7d88c4cf8bf3494b0f10835058ca675efa3baaaefd3
3
+ size 437955572
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "extra_special_tokens": {},
56
+ "mask_token": "[MASK]",
57
+ "max_length": 512,
58
+ "model_max_length": 512,
59
+ "never_split": null,
60
+ "pad_to_multiple_of": null,
61
+ "pad_token": "[PAD]",
62
+ "pad_token_type_id": 0,
63
+ "padding_side": "right",
64
+ "sep_token": "[SEP]",
65
+ "stride": 0,
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "BertTokenizer",
69
+ "truncation_side": "right",
70
+ "truncation_strategy": "longest_first",
71
+ "unk_token": "[UNK]"
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b3fa7153debd63c6fec278b403772c028cd4845e39998141fa0697a2055777
3
+ size 6097
vocab.txt ADDED
The diff for this file is too large to render. See raw diff