Training complete

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: mit
-base_model: emilyalsentzer/Bio_ClinicalBERT
+license: apache-2.0
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
 datasets:
@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8054892601431981
+      value: 0.7806004618937644
     - name: Recall
       type: recall
-      value: 0.8576874205844981
+      value: 0.8589580686149937
     - name: F1
       type: f1
-      value: 0.8307692307692307
+      value: 0.8179068360556564
     - name: Accuracy
       type: accuracy
-      value: 0.9840901352648033
+      value: 0.9826963774430474
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,13 +43,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner
 
-This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the ncbi_disease dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the ncbi_disease dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0635
-- Precision: 0.8055
-- Recall: 0.8577
-- F1: 0.8308
-- Accuracy: 0.9841
+- Loss: 0.0745
+- Precision: 0.7806
+- Recall: 0.8590
+- F1: 0.8179
+- Accuracy: 0.9827
 
 ## Model description
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1248        | 1.0   | 680  | 0.0550          | 0.7560    | 0.8386 | 0.7952 | 0.9823   |
-| 0.0393        | 2.0   | 1360 | 0.0562          | 0.7740    | 0.8310 | 0.8015 | 0.9832   |
-| 0.0147        | 3.0   | 2040 | 0.0635          | 0.8055    | 0.8577 | 0.8308 | 0.9841   |
+| 0.1184        | 1.0   | 680  | 0.0607          | 0.7512    | 0.8285 | 0.7879 | 0.9823   |
+| 0.044         | 2.0   | 1360 | 0.0616          | 0.7635    | 0.8450 | 0.8022 | 0.9832   |
+| 0.0159        | 3.0   | 2040 | 0.0745          | 0.7806    | 0.8590 | 0.8179 | 0.9827   |
 
 
 ### Framework versions