add model

README.md

@@ -21,7 +21,7 @@ model_index:
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.8863127100709574
+      value: 0.9827274990663513
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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
+- Loss: 0.0657
+- Precision: 0.8338
+- Recall: 0.8933
+- F1: 0.8625
+- Accuracy: 0.9827
 
 ## Model description
 
@@ -54,24 +54,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.2
+- learning_rate: 2e-05
 - 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
+- num_epochs: 3
 
 ### 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   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 340  | 0.0612          | 0.8268    | 0.85   | 0.8382 | 0.9806   |
+| 0.0987        | 2.0   | 680  | 0.0604          | 0.8397    | 0.8848 | 0.8616 | 0.9829   |
+| 0.0272        | 3.0   | 1020 | 0.0657          | 0.8338    | 0.8933 | 0.8625 | 0.9827   |
 
 
 ### Framework versions
 
-- Transformers 4.8.2
+- Transformers 4.8.1
 - Pytorch 1.9.0
 - Datasets 1.6.2
 - Tokenizers 0.10.3

config.json

@@ -27,7 +27,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.8.2",
+  "transformers_version": "4.8.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8085ba79eedaabcffe8b4bd8d6364a7072f570a8735a7733df64ac3fa993de1
+oid sha256:fb97943e0ea7c821994c417883540bc7628b0585a1237f483d7da42194bc8b7a
 size 430968561

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221e550972ee5d7d72c9adfb45e4f51df514377bfb275ba9c09cca41f6e969e1
+oid sha256:68033417b0213b00f1511d37bcca2e514c6c17c0759ef523f7f17e67ce4160c7
 size 2671