model update

README.md

@@ -0,0 +1,122 @@
+---
+datasets:
+- bc5cdr
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: tner/deberta-v3-large-bc5cdr
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: bc5cdr
+      type: bc5cdr
+      args: bc5cdr
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.8902493653874869
+    - name: Precision
+      type: precision
+      value: 0.8697724178175452
+    - name: Recall
+      type: recall
+      value: 0.9117137322866755
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8863403908610603
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.8657302393432342
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.9080747413030301
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.8929371360310587
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.8723983660766388
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.9144663064532572
+
+pipeline_tag: token-classification
+widget:
+- text: "Jacob Collier is a Grammy awarded artist from England."
+  example_title: "NER Example 1"
+---
+# tner/deberta-v3-large-bc5cdr
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the 
+[tner/bc5cdr](https://huggingface.co/datasets/tner/bc5cdr) dataset.
+Model fine-tuning is done via [T-NER](https://github.com/asahi417/tner)'s hyper-parameter search (see the repository
+for more detail). It achieves the following results on the test set:
+- F1 (micro): 0.8902493653874869
+- Precision (micro): 0.8697724178175452
+- Recall (micro): 0.9117137322866755
+- F1 (macro): 0.8863403908610603
+- Precision (macro): 0.8657302393432342
+- Recall (macro): 0.9080747413030301
+
+The per-entity breakdown of the F1 score on the test set are below:
+- chemical: 0.9298502009499452
+- disease: 0.8428305807721753 
+
+For F1 scores, the confidence interval is obtained by bootstrap as below:
+- F1 (micro): 
+    - 90%: [0.885162383660078, 0.8951239957151518]
+    - 95%: [0.8838793313408008, 0.8959517574197015] 
+- F1 (macro): 
+    - 90%: [0.885162383660078, 0.8951239957151518]
+    - 95%: [0.8838793313408008, 0.8959517574197015] 
+
+Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/deberta-v3-large-bc5cdr/raw/main/eval/metric.json) 
+and [metric file of entity span](https://huggingface.co/tner/deberta-v3-large-bc5cdr/raw/main/eval/metric_span.json).
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+ - dataset: ['tner/bc5cdr']
+ - dataset_split: train
+ - dataset_name: None
+ - local_dataset: None
+ - model: microsoft/deberta-v3-large
+ - crf: True
+ - max_length: 128
+ - epoch: 15
+ - batch_size: 16
+ - lr: 1e-05
+ - random_seed: 42
+ - gradient_accumulation_steps: 4
+ - weight_decay: 1e-07
+ - lr_warmup_step_ratio: 0.1
+ - max_grad_norm: None
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/deberta-v3-large-bc5cdr/raw/main/trainer_config.json).
+
+### Reference
+If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
+
+```
+
+@inproceedings{ushio-camacho-collados-2021-ner,
+    title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
+    author = "Ushio, Asahi  and
+      Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
+    month = apr,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.eacl-demos.7",
+    doi = "10.18653/v1/2021.eacl-demos.7",
+    pages = "53--62",
+    abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
+}
+
+```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "tner_ckpt/bc5cdr_deberta_v3_large/best_model",
+  "_name_or_path": "tner_ckpt/bc5cdr_deberta_large/model_rgwuwr/epoch_5",
   "architectures": [
     "DebertaV2ForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"micro/f1": 0.8902493653874869, "micro/f1_ci": {"90": [0.885162383660078, 0.8951239957151518], "95": [0.8838793313408008, 0.8959517574197015]}, "micro/recall": 0.9117137322866755, "micro/precision": 0.8697724178175452, "macro/f1": 0.8863403908610603, "macro/f1_ci": {"90": [0.8811004739263217, 0.8914186170057118], "95": [0.8799998974087929, 0.8921780784816905]}, "macro/recall": 0.9080747413030301, "macro/precision": 0.8657302393432342, "per_entity_metric": {"chemical": {"f1": 0.9298502009499452, "f1_ci": {"90": [0.9248183132385925, 0.9347984838913667], "95": [0.9240282546607785, 0.9357697901181058]}, "precision": 0.9149739349271976, "recall": 0.9452181987000928}, "disease": {"f1": 0.8428305807721753, "f1_ci": {"90": [0.8337110247777506, 0.8512171182854413], "95": [0.8319540592803863, 0.8529680090572098]}, "precision": 0.816486543759271, "recall": 0.8709312839059674}}}

eval/metric_span.json

@@ -0,0 +1 @@
+{"micro/f1": 0.8929371360310587, "micro/f1_ci": {"90": [0.8879351802324504, 0.8977068245813511], "95": [0.886871208477677, 0.8984731182484651]}, "micro/recall": 0.9144663064532572, "micro/precision": 0.8723983660766388, "macro/f1": 0.8929371360310587, "macro/f1_ci": {"90": [0.8879351802324504, 0.8977068245813511], "95": [0.886871208477677, 0.8984731182484651]}, "macro/recall": 0.9144663064532572, "macro/precision": 0.8723983660766388}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b16a3c69f179b4728b87bf14ccedfda1cbd4d741f56b524b6f4cc7e38b00a4
-size 1736201135
+oid sha256:5fc7547eccd625261acc96bafe85b803440e4c400c8976e10a6ead823d5a4819
+size 1736206639

tokenizer_config.json

@@ -4,7 +4,7 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "name_or_path": "tner_ckpt/bc5cdr_deberta_v3_large/best_model",
+  "name_or_path": "tner_ckpt/bc5cdr_deberta_large/model_rgwuwr/epoch_5",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},

trainer_config.json

@@ -0,0 +1 @@
+{"dataset": ["tner/bc5cdr"], "dataset_split": "train", "dataset_name": null, "local_dataset": null, "model": "microsoft/deberta-v3-large", "crf": true, "max_length": 128, "epoch": 15, "batch_size": 16, "lr": 1e-05, "random_seed": 42, "gradient_accumulation_steps": 4, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.1, "max_grad_norm": null}