Training in progress epoch 3

README.md

@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.8288
-- Validation Loss: 6.4999
-- Train Accuracy: 0.0270
-- Epoch: 2
+- Train Loss: 5.3659
+- Validation Loss: 6.2816
+- Train Accuracy: 0.0376
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 7.0637     | 7.1983          | 0.0105         | 0     |
 | 6.4070     | 6.7814          | 0.0204         | 1     |
 | 5.8288     | 6.4999          | 0.0270         | 2     |
+| 5.3659     | 6.2816          | 0.0376         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1680560795.e6764e395944.388.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d5cf475e1165fa1ef3b59914bc19f5088de166fa575cb6d7909c696e1738d1
-size 3679130
+oid sha256:4c30de86f5ccf85dd62ac60b1528b0d72e964ea9157c32a7e169796f432b0182
+size 3679347

logs/validation/events.out.tfevents.1680561193.e6764e395944.388.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088d977c43b80b7fb403b186f531c7056e563905a0c5ca0f288a7a2d9067693a
-size 544
+oid sha256:b580bcc5b16bb2848ee29c8fa4984a95d35b6598bccdf998af0e0623598f8193
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ecf1c127304baabb7d63639b4b1ef5326b9fe886f5b11e8d76721a78d64a7a
+oid sha256:1421c0eb77f991b0be3ea0412c2120a71176994e6942ad7b96c0a2904903171d
 size 544532184