BATCH_SIZE=8

LEARNING_RATE=5e-05
MAX_LENGTH=512
FOLD=6

README.md

@@ -15,7 +15,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.4
+      value: 0.58
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -25,8 +25,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7283
-- Accuracy: 0.4
+- Loss: 2.3170
+- Accuracy: 0.58
 
 ## Model description
 
@@ -57,16 +57,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 57   | 0.9481          | 0.56     |
-| No log        | 2.0   | 114  | 1.0163          | 0.56     |
-| No log        | 3.0   | 171  | 1.1452          | 0.38     |
-| No log        | 4.0   | 228  | 1.9038          | 0.54     |
-| No log        | 5.0   | 285  | 2.5529          | 0.4      |
-| No log        | 6.0   | 342  | 3.3545          | 0.42     |
-| No log        | 7.0   | 399  | 3.4529          | 0.44     |
-| No log        | 8.0   | 456  | 3.5855          | 0.4      |
-| 0.3564        | 9.0   | 513  | 3.7481          | 0.38     |
-| 0.3564        | 10.0  | 570  | 3.7283          | 0.4      |
+| No log        | 1.0   | 57   | 1.0118          | 0.32     |
+| No log        | 2.0   | 114  | 0.9242          | 0.58     |
+| No log        | 3.0   | 171  | 1.1096          | 0.42     |
+| No log        | 4.0   | 228  | 1.0027          | 0.5      |
+| No log        | 5.0   | 285  | 1.5517          | 0.5      |
+| No log        | 6.0   | 342  | 1.7520          | 0.56     |
+| No log        | 7.0   | 399  | 2.2123          | 0.56     |
+| No log        | 8.0   | 456  | 2.1874          | 0.6      |
+| 0.4415        | 9.0   | 513  | 2.2495          | 0.58     |
+| 0.4415        | 10.0  | 570  | 2.3170          | 0.58     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926b8fb185544d418286ecfb2a9ad25abbda2fc9fab2cf0f37f99bab4c36f9fc
+oid sha256:f4a1337541428630b2e992c2026cd4a3b71500172d26d08688bf021e66949261
 size 438022317

runs/Sep12_11-10-36_f75bc58113e9/events.out.tfevents.1631445926.f75bc58113e9.87.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba9e39eb763547eb59459802c88500bb15db03d8f89164135cbf8c492d054b8
+size 363

runs/Sep12_11-25-29_f75bc58113e9/1631445934.2590873/events.out.tfevents.1631445934.f75bc58113e9.87.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467f62051f0210bb867782bc9099249250eba05c5e40ef6c8eefe1cc285b261d
+size 4247

runs/Sep12_11-25-29_f75bc58113e9/events.out.tfevents.1631445934.f75bc58113e9.87.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6374037f9ab68600667875380c2b58054caeab3defa460063c554269946f73cd
+size 6878

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b1c67ade52b42ac09b58505530c2d501396654041c23fd3248d63a7d9eca4e
+oid sha256:61df601f417a28b0a3259bc7b9fd12dbcaa086bd9b9b829e1c199437feb66373
 size 2735