Training in progress epoch 2

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1075
-- Validation Loss: 0.2618
-- Train Accuracy: 0.9071
-- Epoch: 1
+- Train Loss: 0.0669
+- Validation Loss: 0.3267
+- Train Accuracy: 0.8933
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:--------------:|:-----:|
 | 0.2133     | 0.2615          | 0.9083         | 0     |
 | 0.1075     | 0.2618          | 0.9071         | 1     |
+| 0.0669     | 0.3267          | 0.8933         | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1659891609.datascience-1-0-ml-g4dn-16xlarge-0857614900e4015bb2bd851cec87.13488.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83799fe5ef068ecc7ff4d616dd3851295b46fda483a37c72b072f044d75d2573
-size 1590708
+oid sha256:439739ff530ec6f068e4accbbac487ab134fa6e863cba124bb247369183a273e
+size 1590925

logs/validation/events.out.tfevents.1659892589.datascience-1-0-ml-g4dn-16xlarge-0857614900e4015bb2bd851cec87.13488.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f46c63e19710e7ba80e702c5ed8aa95156b7aa97c1bc3379ec214c1f74a1aa
-size 350
+oid sha256:d9b8995f659834e86b73305acdd45f9f95dc36e3264642fd2a834e415e092298
+size 506

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368653aa89e93570b52c17a51e3a35e488ebd5eb03a635106448ae1b1062fdf9
+oid sha256:1e965d061facbd3ed80fdb6940c64c856947073aaba0b53b2188c7fdb28d20c5
 size 267952512