BATCH_SIZE=8

LEARNING_RATE=5e-05
MAX_LENGTH=512
FOLD=0

README.md

@@ -15,7 +15,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.624
+      value: 0.48
 ---
 
 <!-- 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: 2.2547
-- Accuracy: 0.624
+- Loss: 3.1085
+- Accuracy: 0.48
 
 ## 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   | 0.9716          | 0.52     |
-| No log        | 2.0   | 114  | 1.0295          | 0.54     |
-| No log        | 3.0   | 171  | 1.0311          | 0.54     |
-| No log        | 4.0   | 228  | 1.7516          | 0.44     |
-| No log        | 5.0   | 285  | 1.9604          | 0.54     |
-| No log        | 6.0   | 342  | 2.5517          | 0.48     |
-| No log        | 7.0   | 399  | 2.3635          | 0.62     |
-| No log        | 8.0   | 456  | 2.7461          | 0.52     |
-| 0.4018        | 9.0   | 513  | 2.8469          | 0.5      |
-| 0.4018        | 10.0  | 570  | 2.8675          | 0.52     |
+| No log        | 1.0   | 57   | 0.9812          | 0.36     |
+| No log        | 2.0   | 114  | 0.9754          | 0.54     |
+| No log        | 3.0   | 171  | 0.9586          | 0.54     |
+| No log        | 4.0   | 228  | 1.0887          | 0.54     |
+| No log        | 5.0   | 285  | 1.3056          | 0.5      |
+| No log        | 6.0   | 342  | 1.9388          | 0.48     |
+| No log        | 7.0   | 399  | 2.4752          | 0.48     |
+| No log        | 8.0   | 456  | 2.8226          | 0.52     |
+| 0.5686        | 9.0   | 513  | 3.0738          | 0.48     |
+| 0.5686        | 10.0  | 570  | 3.1085          | 0.48     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6b0add55e48f43cbe874ceb84765cfcc6eae8066da58239a4458c08a4bedce
+oid sha256:287a9c749bdbc15b46b3c5262da83fbf35d66903c9c09ee5a95ddd0a1b24f29d
 size 438022317

runs/Sep12_09-39-29_f75bc58113e9/1631439573.8743544/events.out.tfevents.1631439573.f75bc58113e9.87.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2383ce36e651a24d6aba60bfe2e04f8a19e2485833606c669879852c626472
+size 4247

runs/Sep12_09-39-29_f75bc58113e9/events.out.tfevents.1631439573.f75bc58113e9.87.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d712ea75af0c287ec4a2bca48d490848f9e8d342b176b9832414ba56e6d8986
+size 6878

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43284eae8d0b2e836d6d52b185c3dae9d72d21ff0f0807d934afb91201c2b97b
+oid sha256:3551566965e82e95b954a1fba4beff5a7fdfe4c5c7293f5a476bd9beb74827ab
 size 2735