BATCH_SIZE=8

LEARNING_RATE=1e-05
MAX_LENGTH=512
FOLD=7

README.md

@@ -15,7 +15,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.72
+      value: 0.66
 ---
 
 <!-- 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: 0.7971
-- Accuracy: 0.72
+- Loss: 1.0381
+- Accuracy: 0.66
 
 ## 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   | 0.9378          | 0.56     |
-| No log        | 2.0   | 114  | 0.9198          | 0.56     |
-| No log        | 3.0   | 171  | 0.8881          | 0.62     |
-| No log        | 4.0   | 228  | 0.8331          | 0.62     |
-| No log        | 5.0   | 285  | 0.7817          | 0.7      |
-| No log        | 6.0   | 342  | 0.7685          | 0.72     |
-| No log        | 7.0   | 399  | 0.7755          | 0.72     |
-| No log        | 8.0   | 456  | 0.7867          | 0.72     |
-| 0.6259        | 9.0   | 513  | 0.7955          | 0.74     |
-| 0.6259        | 10.0  | 570  | 0.7971          | 0.72     |
+| No log        | 1.0   | 57   | 0.9537          | 0.54     |
+| No log        | 2.0   | 114  | 0.9605          | 0.54     |
+| No log        | 3.0   | 171  | 0.9402          | 0.6      |
+| No log        | 4.0   | 228  | 0.9207          | 0.6      |
+| No log        | 5.0   | 285  | 0.9157          | 0.68     |
+| No log        | 6.0   | 342  | 0.9116          | 0.66     |
+| No log        | 7.0   | 399  | 0.9434          | 0.66     |
+| No log        | 8.0   | 456  | 1.0131          | 0.62     |
+| 0.6196        | 9.0   | 513  | 1.0314          | 0.64     |
+| 0.6196        | 10.0  | 570  | 1.0381          | 0.66     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c197434e3b58004a6cbe9665e1e3d25d63bcab7ad1ebd9cf31c4788486483a8f
+oid sha256:86de0b6f77437f12a8232e2f426508249222704d20bba4335f22e004590dae97
 size 438022317

runs/Sep15_03-15-04_c86ef10ea4b0/events.out.tfevents.1631676509.c86ef10ea4b0.88.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3312891684a67964459d495a910f6aa0624deeb227b5cce5ea87e5dac936f7
+size 363

runs/Sep15_03-28-37_c86ef10ea4b0/1631676523.7197928/events.out.tfevents.1631676523.c86ef10ea4b0.88.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5c1aa16e728353a145ce8e50694fb45fd02db27bcb1a0815050fcffb73c25a
+size 4427

runs/Sep15_03-28-37_c86ef10ea4b0/events.out.tfevents.1631676523.c86ef10ea4b0.88.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91cfc0f3463f851e77bc7a2e87ad32c2214864bdde9c6f39bbaae806c305aef6
+size 7058

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e3bf9259ed913197db61f651246a1b4acf71bfcc73ae0f411dc67094ed67f1
+oid sha256:a493d3c77be3f8b23697678cc3cd8ee9cb208792f55abd17504b101798f713ff
 size 2799