add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,62 @@
+---
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+
+model-index:
+- name: test-ner
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test-ner
+
+This model was trained from scratch on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4357
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.8863
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.02
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 340  | 0.4357          | 0.0       | 0.0    | 0.0 | 0.8863   |
+
+
+### Framework versions
+
+- Transformers 4.6.1
+- Pytorch 1.9.0
+- Datasets 1.6.2
+- Tokenizers 0.10.3

README.md

@@ -0,0 +1,77 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- ncbi_disease
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: biobert_v1.1_pubmed-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: ncbi_disease
+      type: ncbi_disease
+      args: ncbi_disease
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.8863127100709574
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# biobert_v1.1_pubmed-finetuned-ner
+
+This model is a fine-tuned version of [monologg/biobert_v1.1_pubmed](https://huggingface.co/monologg/biobert_v1.1_pubmed) on the ncbi_disease dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4343
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.8863
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.2
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 340  | 0.4343          | 0.0       | 0.0    | 0.0 | 0.8863   |
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0
+- Datasets 1.6.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "monologg/biobert_v1.1_pubmed",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8085ba79eedaabcffe8b4bd8d6364a7072f570a8735a7733df64ac3fa993de1
+size 430968561

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/ed9bbe6348755db01a526f9467c73a8c8f55a43191f892374c9ed386b4525997.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "monologg/biobert_v1.1_pubmed", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221e550972ee5d7d72c9adfb45e4f51df514377bfb275ba9c09cca41f6e969e1
+size 2671