BATCH_SIZE=8

LEARNING_RATE=1e-05
MAX_LENGTH=512
FOLD=3

README.md

@@ -15,7 +15,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.62
+      value: 0.56
 ---
 
 <!-- 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: 0.8622
-- Accuracy: 0.62
+- Loss: 1.5452
+- Accuracy: 0.56
 
 ## 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   | 0.9205          | 0.56     |
-| No log        | 2.0   | 114  | 0.9104          | 0.56     |
-| No log        | 3.0   | 171  | 0.8670          | 0.56     |
-| No log        | 4.0   | 228  | 0.8159          | 0.62     |
-| No log        | 5.0   | 285  | 0.8142          | 0.6      |
-| No log        | 6.0   | 342  | 0.8350          | 0.6      |
-| No log        | 7.0   | 399  | 0.7887          | 0.64     |
-| No log        | 8.0   | 456  | 0.8264          | 0.64     |
-| 0.6501        | 9.0   | 513  | 0.8814          | 0.58     |
-| 0.6501        | 10.0  | 570  | 0.8622          | 0.62     |
+| No log        | 1.0   | 57   | 0.9420          | 0.54     |
+| No log        | 2.0   | 114  | 0.9420          | 0.54     |
+| No log        | 3.0   | 171  | 1.0119          | 0.54     |
+| No log        | 4.0   | 228  | 1.0724          | 0.54     |
+| No log        | 5.0   | 285  | 1.1676          | 0.56     |
+| No log        | 6.0   | 342  | 1.3050          | 0.56     |
+| No log        | 7.0   | 399  | 1.3693          | 0.58     |
+| No log        | 8.0   | 456  | 1.4860          | 0.56     |
+| 0.6035        | 9.0   | 513  | 1.5319          | 0.56     |
+| 0.6035        | 10.0  | 570  | 1.5452          | 0.56     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29cb84ef4b72b22df4296dc09cf880c258a3e59ca32d8921de27f3792595e36c
+oid sha256:4c0eacc620c690d5c7cc6260114c2ab88a7199af54c0ca9226185b22c7f72cdc
 size 438022317

runs/Sep15_06-00-32_6f87b01ed96f/events.out.tfevents.1631686675.6f87b01ed96f.89.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ee5f2c57333b95bfd87eb96f83d254ed4905f5449e7c04494a72aa9f291196
+size 363

runs/Sep15_06-18-04_6f87b01ed96f/1631686689.7106612/events.out.tfevents.1631686689.6f87b01ed96f.89.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf7c26c77865360a0165dbc4f7576ded1134a2cc1beeafdfb5405152fdd1695
+size 4429

runs/Sep15_06-18-04_6f87b01ed96f/events.out.tfevents.1631686689.6f87b01ed96f.89.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbf5adbb18493d230c51b5fefd51d977714fe24945f0f7f52bad45f240660f3
+size 7060

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12b455d16ca5f1094915eeb8adf9d29ffad4c14c9a84d48817fb55cfe504b44
+oid sha256:5e49c03282e95d4c8fbab066878842bc6304d239ebdd982f8f20e5d4d16a1658
 size 2863