GuCuChiara
/

NLP-HIBA_DisTEMIST_fine_tuned_ClinicalBERT-pretrained-model

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

GuCuChiara commited on Nov 12, 2023

Commit

6245525

•

1 Parent(s): 6389fee

Training complete

Files changed (1) hide show

README.md +11 -14

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3611
-- Precision: 0.4742
-- Recall: 0.5039
-- F1: 0.4886
-- Accuracy: 0.9342
 ## Model description
@@ -49,20 +49,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 71   | 0.3097          | 0.5425    | 0.3819 | 0.4482 | 0.9390   |
-| No log        | 2.0   | 142  | 0.2600          | 0.4345    | 0.4927 | 0.4618 | 0.9312   |
-| No log        | 3.0   | 213  | 0.3000          | 0.4698    | 0.4745 | 0.4721 | 0.9347   |
-| No log        | 4.0   | 284  | 0.3039          | 0.4675    | 0.4861 | 0.4766 | 0.9346   |
-| No log        | 5.0   | 355  | 0.3237          | 0.4434    | 0.5044 | 0.4719 | 0.9310   |
-| No log        | 6.0   | 426  | 0.3457          | 0.4706    | 0.4948 | 0.4824 | 0.9345   |
-| No log        | 7.0   | 497  | 0.3500          | 0.4736    | 0.5023 | 0.4875 | 0.9341   |
-| 0.0246        | 8.0   | 568  | 0.3611          | 0.4742    | 0.5039 | 0.4886 | 0.9342   |
 ### Framework versions

 This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2059
+- Precision: 0.4811
+- Recall: 0.4468
+- F1: 0.4633
+- Accuracy: 0.9329
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 71   | 0.2327          | 0.3130    | 0.2534 | 0.2801 | 0.9173   |
+| No log        | 2.0   | 142  | 0.2009          | 0.4039    | 0.3745 | 0.3886 | 0.9260   |
+| No log        | 3.0   | 213  | 0.1973          | 0.4479    | 0.4302 | 0.4389 | 0.9287   |
+| No log        | 4.0   | 284  | 0.2155          | 0.4223    | 0.4673 | 0.4437 | 0.9233   |
+| No log        | 5.0   | 355  | 0.2059          | 0.4811    | 0.4468 | 0.4633 | 0.9329   |
 ### Framework versions