update model card README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: mit
 tags:
 - generated_from_trainer
 datasets:
@@ -21,18 +21,13 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.7376642982556899
+      value: 0.8030010681183889
     - name: Recall
       type: recall
-      value: 0.8167811330353574
+      value: 0.837754771918473
     - name: F1
       type: f1
-      value: 0.7752093051328258
-      
-widget:
- - text: "Confocal images of Bmm-GFP (green) in 3rd instar larval fat bodies of different genotypes. DAPI (blue) stains nuclei. Scale bar represents 25 µm. (A) Knocking down CSN2 or overexpressing RDH/CG2064 in animals with DGAT1 overexpression (ppl>DGAT1) decreases the level and lipid droplet localization of Bmm-GFP."
- - text: "The GFP intensity along the line across a lipid droplet in (A) was measured by ImageJ.The lipid droplet localization of Bmm-GFP, represented by two peaks, is clearly visible in fat cells from ppl > DGAT1 larvae , but it is lost in fat cells from ppl > DGAT1 larvae with CSN2 RNAi or overexpression of RDH/CG2064. More than 30 lipid droplets of each genotype were measured. One typical image curve is shown for each genotype."
- - text: "XPT of siRNA treated DC3. 2R cells after 48 hours of knockdown. Treated cells were fed with the indicated amounts of C8L peptid conjugated to iron oxide beads via a disulfide bond. The cells were then exposed to RF33. 70-Luc Reporter CD8 T cells overnight. Error bars show SD of >3 replicate wells. * p<0.05 for siRNA vs control I-Ab using two-way ANOVA. Representative plot of 3 independent experiments."      
+      value: 0.8200098518700961
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,71 +35,33 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sd-ner-v2
 
-This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) on the source_data_nlp dataset.
+This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract) on the source_data_nlp dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1685
-- Accuracy Score: 0.9438
-- Precision: 0.7377
-- Recall: 0.8168
-- F1: 0.7752
+- Loss: 0.1551
+- Accuracy Score: 0.9513
+- Precision: 0.8030
+- Recall: 0.8378
+- F1: 0.8200
 
 ## Model description
 
-The generation of this model is explained in more detail in Abreu-Vicente & Lemberger (in prep). 
-The model is fine-tuned from [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large). 
-The use of [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) was decided after proceeding to the analysis of 14 different models
-in the [SourceData](https://huggingface.co/datasets/EMBO/sd-nlp-non-tokenized) dataset. 
-
-### The SourceData dataset
-
-This dataset is based on the content of the SourceData (https://sourcedata.embo.org) database, which contains manually annotated figure legends written in English and extracted from scientific papers in the domain of cell and molecular biology (Liechti et al, Nature Methods, 2017, https://doi.org/10.1038/nmeth.4471). Unlike the dataset sd-nlp, pre-tokenized with the roberta-base tokenizer, this dataset is not previously tokenized, but just splitted into words. Users can therefore use it to fine-tune other models. Additional details at https://github.com/source-data/soda-roberta
-
-The dataset in the 🤗 Hub is just a processed version of the entire annotated dataset that is presented also in Abreu-Vicente & Lemberger (in prep).
-Further details on the entire dataset can be found in the [BCVI BIO-ID track](https://biocreative.bioinformatics.udel.edu/resources/corpora/bcvi-bio-id-track/) task associated.
-
-This model is fine-tuned in the biological `NER` task. On it, biological and chemical entities are labeled. Specifically the following entities are tagged:
-
-`NER`: biological and chemical entities are labeled. Specifically the following entities are tagged:
-- `SMALL_MOLECULE`: small molecules
-- `GENEPROD`: gene products (genes and proteins)
-- `SUBCELLULAR`: subcellular components
-- `CELL`: cell types and cell lines.
-- `TISSUE`: tissues and organs
-- `ORGANISM`: species
-- `EXP_ASSAY`: experimental assays
+More information needed
 
 ## Intended uses & limitations
 
-The intended use of this model is for Named Entity Recognition of biological entities used in SourceData annotations (https://sourcedata.embo.org), including small molecules, gene products (genes and proteins), subcellular components, cell line and cell types, organ and tissues, species as well as experimental methods.
-
-To have a quick check of the model:
-
-```python
-  from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
-  example = """<s> F. Western blot of input and eluates of Upf1 domains purification in a Nmd4-HA strain. The band with the # might corresponds to a dimer of Upf1-CH, bands marked with a star correspond to residual signal with the anti-HA antibodies (Nmd4). Fragments in the eluate have a smaller size because the protein A part of the tag was removed by digestion with the TEV protease. G6PDH served as a loading control in the input samples </s>"""
-  tokenizer = AutoTokenizer.from_pretrained('EMBO/sd-ner-v2', max_len=512)
-  model = AutoModelForTokenClassification.from_pretrained('EMBO/sd-ner-v2')
-  ner = pipeline('ner', model, tokenizer=tokenizer)
-  res = ner(example)
-  for r in res:
-      print(r['word'], r['entity'])
-```
-
-### Possible limitations
-
-The model has been trained on pre-tokenized words. Although in general the SentencePiece tokenizer and part of the pre-processing included in the 🤗 tokenizers library seem to do a good job, this might generate some issues related to the use of white spaces between characters. 
+More information needed
 
 ## Training and evaluation data
 
-The training, evaluation, and test splits of the data used can be found in [SourceData dataset](https://huggingface.co/datasets/EMBO/sd-nlp-non-tokenized).
+More information needed
 
 ## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
+- learning_rate: 0.0001
+- train_batch_size: 64
 - eval_batch_size: 256
 - seed: 42
 - optimizer: Adafactor
@@ -115,32 +72,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Score | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:---------:|:------:|:------:|
-| 0.1308        | 1.0   | 2066 | 0.1634          | 0.9414         | 0.7155    | 0.8278 | 0.7676 |
-| 0.0885        | 2.0   | 4132 | 0.1685          | 0.9438         | 0.7377    | 0.8168 | 0.7752 |
-
-
-## Performance of the model in the training dataset
-
-```
-              precision    recall  f1-score support
-  CELL           0.71      0.79      0.75      4948 
-  EXP_ASSAY      0.59      0.60      0.60      9885  
-  GENEPROD       0.79      0.89      0.84     21865                                                                       
-  ORGANISM       0.72      0.85      0.78      3464  
-  SMALL_MOLECULE 0.72      0.81      0.76      6431
-  SUBCELLULAR    0.72      0.77      0.74      3850 
-  TISSUE         0.68      0.76      0.72      2975 
-  
-  micro avg       0.72      0.80      0.76
-  macro avg       0.70      0.78      0.74     53418 
-  weighted avg    0.72      0.80      0.76     53418 
-  
-{'test_loss': 0.16807569563388824, 'test_accuracy_score': 0.9427137503742414, 'test_precision': 0.7242540660382148, 'test_recall': 0.8011157287805608, 'test_f1': 0.7607484111817252, 'test_runtime': 88.1851, 'test_samples_per_second': 93.27, 'test_steps_per_second': 0.374}
-```
+| 0.1082        | 1.0   | 785  | 0.1550          | 0.9493         | 0.7826    | 0.8402 | 0.8104 |
+| 0.073         | 2.0   | 1570 | 0.1551          | 0.9513         | 0.8030    | 0.8378 | 0.8200 |
+
 
 ### Framework versions
 
-- Transformers 4.15.0
+- Transformers 4.20.0
 - Pytorch 1.11.0a0+bfe5ad2
 - Datasets 1.17.0
-- Tokenizers 0.10.3
+- Tokenizers 0.12.1