ai-maker-space/medical_nonmedical-classifier

README.md

@@ -8,8 +8,6 @@ metrics:
 model-index:
 - name: med_nonmed
   results: []
-datasets:
-- ai-maker-space/medical_nonmedical
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,25 +15,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # med_nonmed
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [Medical/Non-Medical Dataset](https://huggingface.co/datasets/ai-maker-space/medical_nonmedical) dataset.
-
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0135
-- F1: 0.9934
+- Loss: 0.0260
+- F1: 0.9910
 
 ## Model description
 
-A fine-tuned classifier based on the DistilBERT Base Uncased model. 
+More information needed
 
 ## Intended uses & limitations
 
-This model can be used for rough filtering of medical/non-medical text. Potential use-case includes filtering emails.
-
-The model is in v0 and should not be used in critical functions without proper evaluation and risk assessment. 
+More information needed
 
 ## Training and evaluation data
 
-The model was trained on a custom dataset that can be found [here](https://huggingface.co/datasets/ai-maker-space/medical_nonmedical) which is a composite of two separate medical and non-medical datasets.
+More information needed
 
 ## Training procedure
 
@@ -54,13 +49,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.0587        | 1.0   | 622  | 0.0279          | 0.9871 |
-| 0.0088        | 2.0   | 1244 | 0.0135          | 0.9934 |
+| 0.0581        | 1.0   | 622  | 0.0220          | 0.9895 |
+| 0.0102        | 2.0   | 1244 | 0.0260          | 0.9910 |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.5
-- Tokenizers 0.14.1
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

runs/Mar19_16-43-56_24c553500917/events.out.tfevents.1710866638.24c553500917.243.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c526c4755f4e8442c0a03167bb534225a8667f82c995d719eb217d3fb7f94c1
-size 4955
+oid sha256:352f5116387b910707324e8b1e0a8a66b889eff7feb52f59b87ebd9112783ca2
+size 5837